update

* add requirements + fix link to bghira's guide

* text ecnoder training fixes

* text encoder training fixes

* text encoder training fixes

* text encoder training fixes

* style

* add tests

* fix encode_prompt call

* style

* unpack_latents test

* fix lora saving

* remove default val for max_sequenece_length in encode_prompt

* remove default val for max_sequenece_length in encode_prompt

* style

* testing

* style

* testing

* testing

* style

* fix sizing issue

* style

* revert scaling

* style

* style

* scaling test

* style

* scaling test

* remove model pred operation left from pre-conditioning

* remove model pred operation left from pre-conditioning

* fix trainable params

* remove te2 from casting

* transformer to accelerator

* remove prints

* empty commit

.github/workflows/benchmark.yml

@@ -13,16 +13,17 @@ env:
 
 jobs:
   torch_pipelines_cuda_benchmark_tests:
-    env: 
+    env:
       SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL_BENCHMARK }}
     name: Torch Core Pipelines CUDA Benchmarking Tests
     strategy:
       fail-fast: false
       max-parallel: 1
-    runs-on: [single-gpu, nvidia-gpu, a10, ci]
+    runs-on:
+      group: aws-g6-4xlarge-plus
     container:
       image: diffusers/diffusers-pytorch-compile-cuda
-      options: --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/ --gpus 0
+      options: --shm-size "16gb" --ipc host --gpus 0
     steps:
       - name: Checkout diffusers
         uses: actions/checkout@v3
@@ -58,7 +59,7 @@ jobs:
         if: ${{ success() }}
         run: |
           pip install requests && python utils/notify_benchmarking_status.py --status=success
-        
+
       - name: Report failure status
         if: ${{ failure() }}
         run: |

.github/workflows/build_docker_images.yml

@@ -20,7 +20,8 @@ env:
 
 jobs:
   test-build-docker-images:
-    runs-on: [ self-hosted, intel-cpu, 8-cpu, ci ]
+    runs-on:
+      group: aws-general-8-plus
     if: github.event_name == 'pull_request'
     steps:
       - name: Set up Docker Buildx
@@ -50,7 +51,8 @@ jobs:
         if: steps.file_changes.outputs.all != ''
 
   build-and-push-docker-images:
-    runs-on: [ self-hosted, intel-cpu, 8-cpu, ci ]
+    runs-on:
+      group: aws-general-8-plus
     if: github.event_name != 'pull_request'
 
     permissions:
@@ -98,4 +100,4 @@ jobs:
           slack_channel: ${{ env.CI_SLACK_CHANNEL }}
           title: "🤗 Results of the ${{ matrix.image-name }} Docker Image build"
           status: ${{ job.status }}
-          slack_token: ${{ secrets.SLACK_CIFEEDBACK_BOT_TOKEN }}
+          slack_token: ${{ secrets.SLACK_CIFEEDBACK_BOT_TOKEN }}

.github/workflows/mirror_community_pipeline.yml

@@ -24,7 +24,7 @@ jobs:
   mirror_community_pipeline:
     env:
       SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL_COMMUNITY_MIRROR }}
-    
+
     runs-on: ubuntu-latest
     steps:
       # Checkout to correct ref
@@ -95,7 +95,7 @@ jobs:
         if: ${{ success() }}
         run: |
           pip install requests && python utils/notify_community_pipelines_mirror.py --status=success
-      
+
       - name: Report failure status
         if: ${{ failure() }}
         run: |

.github/workflows/nightly_tests.yml

@@ -7,7 +7,7 @@ on:
 
 env:
   DIFFUSERS_IS_CI: yes
-  HF_HOME: /mnt/cache
+  HF_HUB_ENABLE_HF_TRANSFER: 1
   OMP_NUM_THREADS: 8
   MKL_NUM_THREADS: 8
   PYTEST_TIMEOUT: 600
@@ -18,8 +18,11 @@ env:
 
 jobs:
   setup_torch_cuda_pipeline_matrix:
-    name: Setup Torch Pipelines Matrix
-    runs-on: diffusers/diffusers-pytorch-cpu
+    name: Setup Torch Pipelines CUDA Slow Tests Matrix
+    runs-on:
+      group: aws-general-8-plus
+    container:
+      image: diffusers/diffusers-pytorch-cpu
     outputs:
       pipeline_test_matrix: ${{ steps.fetch_pipeline_matrix.outputs.pipeline_test_matrix }}
     steps:
@@ -27,13 +30,9 @@ jobs:
         uses: actions/checkout@v3
         with:
           fetch-depth: 2
-      - name: Set up Python
-        uses: actions/setup-python@v4
-        with:
-          python-version: "3.8"
       - name: Install dependencies
         run: |
-          pip install -e .
+          pip install -e .[test]
           pip install huggingface_hub
       - name: Fetch Pipeline Matrix
         id: fetch_pipeline_matrix
@@ -50,16 +49,18 @@ jobs:
           path: reports
 
   run_nightly_tests_for_torch_pipelines:
-    name: Torch Pipelines CUDA Nightly Tests
+    name: Nightly Torch Pipelines CUDA Tests
     needs: setup_torch_cuda_pipeline_matrix
     strategy:
       fail-fast: false
+      max-parallel: 8
       matrix:
         module: ${{ fromJson(needs.setup_torch_cuda_pipeline_matrix.outputs.pipeline_test_matrix) }}
-    runs-on: [single-gpu, nvidia-gpu, t4, ci]
+    runs-on:
+      group: aws-g4dn-2xlarge
     container:
       image: diffusers/diffusers-pytorch-cuda
-      options: --shm-size "16gb" --ipc host -v /mnt/cache/.cache/huggingface/diffusers:/mnt/cache/ --gpus 0
+      options: --shm-size "16gb" --ipc host --gpus 0
     steps:
       - name: Checkout diffusers
         uses: actions/checkout@v3
@@ -67,19 +68,16 @@ jobs:
           fetch-depth: 2
       - name: NVIDIA-SMI
         run: nvidia-smi
-
       - name: Install dependencies
         run: |
           python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
           python -m uv pip install -e [quality,test]
           python -m uv pip install accelerate@git+https://github.com/huggingface/accelerate.git
           python -m uv pip install pytest-reportlog
-
       - name: Environment
         run: |
           python utils/print_env.py
-
-      - name: Nightly PyTorch CUDA checkpoint (pipelines) tests
+      - name: Pipeline CUDA Test
         env:
           HF_TOKEN: ${{ secrets.HF_TOKEN }}
           # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
@@ -90,38 +88,37 @@ jobs:
             --make-reports=tests_pipeline_${{ matrix.module }}_cuda \
             --report-log=tests_pipeline_${{ matrix.module }}_cuda.log \
             tests/pipelines/${{ matrix.module }}
-
       - name: Failure short reports
         if: ${{ failure() }}
         run: |
           cat reports/tests_pipeline_${{ matrix.module }}_cuda_stats.txt
           cat reports/tests_pipeline_${{ matrix.module }}_cuda_failures_short.txt
-
       - name: Test suite reports artifacts
         if: ${{ always() }}
         uses: actions/upload-artifact@v2
         with:
           name: pipeline_${{ matrix.module }}_test_reports
           path: reports
-
       - name: Generate Report and Notify Channel
         if: always()
         run: |
           pip install slack_sdk tabulate
-          python scripts/log_reports.py >> $GITHUB_STEP_SUMMARY
+          python utils/log_reports.py >> $GITHUB_STEP_SUMMARY
 
   run_nightly_tests_for_other_torch_modules:
-    name: Torch Non-Pipelines CUDA Nightly Tests
-    runs-on: [single-gpu, nvidia-gpu, t4, ci]
+    name: Nightly Torch CUDA Tests
+    runs-on:
+      group: aws-g4dn-2xlarge
     container:
       image: diffusers/diffusers-pytorch-cuda
-      options: --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/ --gpus 0
+      options: --shm-size "16gb" --ipc host --gpus 0
     defaults:
       run:
         shell: bash
     strategy:
+      max-parallel: 2
       matrix:
-        module: [models, schedulers, others, examples]
+        module: [models, schedulers, lora, others, single_file, examples]
     steps:
     - name: Checkout diffusers
       uses: actions/checkout@v3
@@ -133,8 +130,8 @@ jobs:
         python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
         python -m uv pip install -e [quality,test]
         python -m uv pip install accelerate@git+https://github.com/huggingface/accelerate.git
+        python -m uv pip install peft@git+https://github.com/huggingface/peft.git
         python -m uv pip install pytest-reportlog
-
     - name: Environment
       run: python utils/print_env.py
 
@@ -158,7 +155,6 @@ jobs:
         # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
         CUBLAS_WORKSPACE_CONFIG: :16:8
       run: |
-        python -m uv pip install peft@git+https://github.com/huggingface/peft.git
         python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
           -s -v --make-reports=examples_torch_cuda \
           --report-log=examples_torch_cuda.log \
@@ -181,64 +177,7 @@ jobs:
       if: always()
       run: |
         pip install slack_sdk tabulate
-        python scripts/log_reports.py >> $GITHUB_STEP_SUMMARY
-
-  run_lora_nightly_tests:
-    name: Nightly LoRA Tests with PEFT and TORCH
-    runs-on: [single-gpu, nvidia-gpu, t4, ci]
-    container:
-      image: diffusers/diffusers-pytorch-cuda
-      options: --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/ --gpus 0
-    defaults:
-      run:
-        shell: bash
-    steps:
-    - name: Checkout diffusers
-      uses: actions/checkout@v3
-      with:
-        fetch-depth: 2
-
-    - name: Install dependencies
-      run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m uv pip install -e [quality,test]
-        python -m uv pip install accelerate@git+https://github.com/huggingface/accelerate.git
-        python -m uv pip install peft@git+https://github.com/huggingface/peft.git
-        python -m uv pip install pytest-reportlog
-
-    - name: Environment
-      run: python utils/print_env.py
-
-    - name: Run nightly LoRA tests with PEFT and Torch
-      env:
-        HF_TOKEN: ${{ secrets.HF_TOKEN }}
-        # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
-        CUBLAS_WORKSPACE_CONFIG: :16:8
-      run: |
-        python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-          -s -v -k "not Flax and not Onnx" \
-          --make-reports=tests_torch_lora_cuda \
-          --report-log=tests_torch_lora_cuda.log \
-          tests/lora
-
-    - name: Failure short reports
-      if: ${{ failure() }}
-      run: |
-        cat reports/tests_torch_lora_cuda_stats.txt
-        cat reports/tests_torch_lora_cuda_failures_short.txt
-
-    - name: Test suite reports artifacts
-      if: ${{ always() }}
-      uses: actions/upload-artifact@v2
-      with:
-        name: torch_lora_cuda_test_reports
-        path: reports
-
-    - name: Generate Report and Notify Channel
-      if: always()
-      run: |
-        pip install slack_sdk tabulate
-        python scripts/log_reports.py >> $GITHUB_STEP_SUMMARY
+        python utils/log_reports.py >> $GITHUB_STEP_SUMMARY
 
   run_flax_tpu_tests:
     name: Nightly Flax TPU Tests
@@ -294,14 +233,15 @@ jobs:
       if: always()
       run: |
         pip install slack_sdk tabulate
-        python scripts/log_reports.py >> $GITHUB_STEP_SUMMARY
+        python utils/log_reports.py >> $GITHUB_STEP_SUMMARY
 
   run_nightly_onnx_tests:
     name: Nightly ONNXRuntime CUDA tests on Ubuntu
-    runs-on: [single-gpu, nvidia-gpu, t4, ci]
+    runs-on:
+      group: aws-g4dn-2xlarge
     container:
       image: diffusers/diffusers-onnxruntime-cuda
-      options: --gpus 0 --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/
+      options: --gpus 0 --shm-size "16gb" --ipc host
 
     steps:
     - name: Checkout diffusers
@@ -318,11 +258,10 @@ jobs:
         python -m uv pip install -e [quality,test]
         python -m uv pip install accelerate@git+https://github.com/huggingface/accelerate.git
         python -m uv pip install pytest-reportlog
-
     - name: Environment
       run: python utils/print_env.py
 
-    - name: Run nightly ONNXRuntime CUDA tests
+    - name: Run Nightly ONNXRuntime CUDA tests
       env:
         HF_TOKEN: ${{ secrets.HF_TOKEN }}
       run: |
@@ -349,7 +288,7 @@ jobs:
       if: always()
       run: |
         pip install slack_sdk tabulate
-        python scripts/log_reports.py >> $GITHUB_STEP_SUMMARY
+        python utils/log_reports.py >> $GITHUB_STEP_SUMMARY
 
   run_nightly_tests_apple_m1:
     name: Nightly PyTorch MPS tests on MacOS
@@ -411,4 +350,4 @@ jobs:
         if: always()
         run: |
           pip install slack_sdk tabulate
-          python scripts/log_reports.py >> $GITHUB_STEP_SUMMARY
+          python utils/log_reports.py >> $GITHUB_STEP_SUMMARY

.github/workflows/pr_test_fetcher.yml

@@ -15,7 +15,8 @@ concurrency:
 jobs:
   setup_pr_tests:
     name: Setup PR Tests
-    runs-on: [ self-hosted, intel-cpu, 8-cpu, ci ]
+    runs-on:
+      group: aws-general-8-plus
     container:
       image: diffusers/diffusers-pytorch-cpu
       options: --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/
@@ -73,7 +74,8 @@ jobs:
       max-parallel: 2
       matrix:
         modules: ${{ fromJson(needs.setup_pr_tests.outputs.matrix) }}
-    runs-on: [ self-hosted, intel-cpu, 8-cpu, ci ]
+    runs-on:
+      group: aws-general-8-plus
     container:
       image: diffusers/diffusers-pytorch-cpu
       options: --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/
@@ -123,12 +125,13 @@ jobs:
         config:
           - name: Hub tests for models, schedulers, and pipelines
             framework: hub_tests_pytorch
-            runner: [ self-hosted, intel-cpu, 8-cpu, ci ]
+            runner: aws-general-8-plus
             image: diffusers/diffusers-pytorch-cpu
             report: torch_hub
 
     name: ${{ matrix.config.name }}
-    runs-on: ${{ matrix.config.runner }}
+    runs-on:
+      group: ${{ matrix.config.runner }}
     container:
       image: ${{ matrix.config.image }}
       options: --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/

.github/workflows/pr_test_peft_backend.yml

@@ -71,7 +71,8 @@ jobs:
 
     name: LoRA - ${{ matrix.lib-versions }}
 
-    runs-on: [ self-hosted, intel-cpu, 8-cpu, ci ]
+    runs-on:
+      group: aws-general-8-plus
 
     container:
       image: diffusers/diffusers-pytorch-cpu
@@ -128,4 +129,4 @@ jobs:
       uses: actions/upload-artifact@v2
       with:
         name: pr_${{ matrix.config.report }}_test_reports
-        path: reports
+        path: reports

.github/workflows/pr_tests.yml

@@ -77,28 +77,29 @@ jobs:
         config:
           - name: Fast PyTorch Pipeline CPU tests
             framework: pytorch_pipelines
-            runner: [ self-hosted, intel-cpu, 32-cpu, 256-ram, ci ]
+            runner: aws-highmemory-32-plus
             image: diffusers/diffusers-pytorch-cpu
             report: torch_cpu_pipelines
           - name: Fast PyTorch Models & Schedulers CPU tests
             framework: pytorch_models
-            runner: [ self-hosted, intel-cpu, 8-cpu, ci ]
+            runner: aws-general-8-plus
             image: diffusers/diffusers-pytorch-cpu
             report: torch_cpu_models_schedulers
           - name: Fast Flax CPU tests
             framework: flax
-            runner: [ self-hosted, intel-cpu, 8-cpu, ci ]
+            runner: aws-general-8-plus
             image: diffusers/diffusers-flax-cpu
             report: flax_cpu
           - name: PyTorch Example CPU tests
             framework: pytorch_examples
-            runner: [ self-hosted, intel-cpu, 8-cpu, ci ]
+            runner: aws-general-8-plus
             image: diffusers/diffusers-pytorch-cpu
             report: torch_example_cpu
 
     name: ${{ matrix.config.name }}
 
-    runs-on: ${{ matrix.config.runner }}
+    runs-on:
+      group: ${{ matrix.config.runner }}
 
     container:
       image: ${{ matrix.config.image }}
@@ -180,7 +181,8 @@ jobs:
         config:
           - name: Hub tests for models, schedulers, and pipelines
             framework: hub_tests_pytorch
-            runner: [ self-hosted, intel-cpu, 8-cpu, ci ]
+            runner:
+              group: aws-general-8-plus
             image: diffusers/diffusers-pytorch-cpu
             report: torch_hub
 

.github/workflows/push_tests.yml

@@ -11,17 +11,16 @@ on:
 
 env:
   DIFFUSERS_IS_CI: yes
-  HF_HOME: /mnt/cache
   OMP_NUM_THREADS: 8
   MKL_NUM_THREADS: 8
   PYTEST_TIMEOUT: 600
-  RUN_SLOW: yes
   PIPELINE_USAGE_CUTOFF: 50000
 
 jobs:
   setup_torch_cuda_pipeline_matrix:
     name: Setup Torch Pipelines CUDA Slow Tests Matrix
-    runs-on: [ self-hosted, intel-cpu, 8-cpu, ci ]
+    runs-on:
+      group: aws-general-8-plus
     container:
       image: diffusers/diffusers-pytorch-cpu
     outputs:
@@ -52,17 +51,18 @@ jobs:
           path: reports
 
   torch_pipelines_cuda_tests:
-    name: Torch Pipelines CUDA Slow Tests
+    name: Torch Pipelines CUDA Tests
     needs: setup_torch_cuda_pipeline_matrix
     strategy:
       fail-fast: false
       max-parallel: 8
       matrix:
         module: ${{ fromJson(needs.setup_torch_cuda_pipeline_matrix.outputs.pipeline_test_matrix) }}
-    runs-on: [single-gpu, nvidia-gpu, t4, ci]
+    runs-on:
+      group: aws-g4dn-2xlarge
     container:
       image: diffusers/diffusers-pytorch-cuda
-      options: --shm-size "16gb" --ipc host -v /mnt/cache/.cache/huggingface/diffusers:/mnt/cache/ --gpus 0
+      options: --shm-size "16gb" --ipc host --gpus 0
     steps:
       - name: Checkout diffusers
         uses: actions/checkout@v3
@@ -103,10 +103,11 @@ jobs:
 
   torch_cuda_tests:
     name: Torch CUDA Tests
-    runs-on: [single-gpu, nvidia-gpu, t4, ci]
+    runs-on:
+      group: aws-g4dn-2xlarge
     container:
       image: diffusers/diffusers-pytorch-cuda
-      options: --shm-size "16gb" --ipc host -v /mnt/cache/.cache/huggingface/diffusers:/mnt/cache/ --gpus 0
+      options: --shm-size "16gb" --ipc host --gpus 0
     defaults:
       run:
         shell: bash
@@ -124,12 +125,13 @@ jobs:
         python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
         python -m uv pip install -e [quality,test]
         python -m uv pip install accelerate@git+https://github.com/huggingface/accelerate.git
+        python -m uv pip install peft@git+https://github.com/huggingface/peft.git
 
     - name: Environment
       run: |
         python utils/print_env.py
 
-    - name: Run slow PyTorch CUDA tests
+    - name: Run PyTorch CUDA tests
       env:
         HF_TOKEN: ${{ secrets.HF_TOKEN }}
         # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
@@ -153,61 +155,6 @@ jobs:
         name: torch_cuda_test_reports
         path: reports
 
-  peft_cuda_tests:
-    name: PEFT CUDA Tests
-    runs-on: [single-gpu, nvidia-gpu, t4, ci]
-    container:
-      image: diffusers/diffusers-pytorch-cuda
-      options: --shm-size "16gb" --ipc host -v /mnt/cache/.cache/huggingface/diffusers:/mnt/cache/ --gpus 0
-    defaults:
-      run:
-        shell: bash
-    steps:
-    - name: Checkout diffusers
-      uses: actions/checkout@v3
-      with:
-        fetch-depth: 2
-
-    - name: Install dependencies
-      run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m uv pip install -e [quality,test]
-        python -m uv pip install accelerate@git+https://github.com/huggingface/accelerate.git
-        python -m pip install -U peft@git+https://github.com/huggingface/peft.git
-
-    - name: Environment
-      run: |
-        python utils/print_env.py
-
-    - name: Run slow PEFT CUDA tests
-      env:
-        HF_TOKEN: ${{ secrets.HF_TOKEN }}
-        # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
-        CUBLAS_WORKSPACE_CONFIG: :16:8
-      run: |
-        python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-          -s -v -k "not Flax and not Onnx and not PEFTLoRALoading" \
-          --make-reports=tests_peft_cuda \
-          tests/lora/
-        python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-          -s -v -k "lora and not Flax and not Onnx and not PEFTLoRALoading" \
-          --make-reports=tests_peft_cuda_models_lora \
-          tests/models/
-
-    - name: Failure short reports
-      if: ${{ failure() }}
-      run: |
-        cat reports/tests_peft_cuda_stats.txt
-        cat reports/tests_peft_cuda_failures_short.txt
-        cat reports/tests_peft_cuda_models_lora_failures_short.txt
-
-    - name: Test suite reports artifacts
-      if: ${{ always() }}
-      uses: actions/upload-artifact@v2
-      with:
-        name: torch_peft_test_reports
-        path: reports
-
   flax_tpu_tests:
     name: Flax TPU Tests
     runs-on: docker-tpu
@@ -257,7 +204,8 @@ jobs:
 
   onnx_cuda_tests:
     name: ONNX CUDA Tests
-    runs-on: [single-gpu, nvidia-gpu, t4, ci]
+    runs-on:
+      group: aws-g4dn-2xlarge
     container:
       image: diffusers/diffusers-onnxruntime-cuda
       options: --shm-size "16gb" --ipc host -v /mnt/cache/.cache/huggingface:/mnt/cache/ --gpus 0
@@ -305,11 +253,12 @@ jobs:
   run_torch_compile_tests:
     name: PyTorch Compile CUDA tests
 
-    runs-on: [single-gpu, nvidia-gpu, t4, ci]
+    runs-on:
+      group: aws-g4dn-2xlarge
 
     container:
       image: diffusers/diffusers-pytorch-compile-cuda
-      options: --gpus 0 --shm-size "16gb" --ipc host -v /mnt/cache/.cache/huggingface:/mnt/cache/
+      options: --gpus 0 --shm-size "16gb" --ipc host
 
     steps:
     - name: Checkout diffusers
@@ -347,11 +296,12 @@ jobs:
   run_xformers_tests:
     name: PyTorch xformers CUDA tests
 
-    runs-on: [single-gpu, nvidia-gpu, t4, ci]
+    runs-on:
+      group: aws-g4dn-2xlarge
 
     container:
       image: diffusers/diffusers-pytorch-xformers-cuda
-      options: --gpus 0 --shm-size "16gb" --ipc host -v /mnt/cache/.cache/huggingface:/mnt/cache/
+      options: --gpus 0 --shm-size "16gb" --ipc host
 
     steps:
     - name: Checkout diffusers
@@ -388,11 +338,12 @@ jobs:
   run_examples_tests:
     name: Examples PyTorch CUDA tests on Ubuntu
 
-    runs-on: [single-gpu, nvidia-gpu, t4, ci]
+    runs-on:
+      group: aws-g4dn-2xlarge
 
     container:
       image: diffusers/diffusers-pytorch-cuda
-      options: --gpus 0 --shm-size "16gb" --ipc host -v /mnt/cache/.cache/huggingface:/mnt/cache/
+      options: --gpus 0 --shm-size "16gb" --ipc host
 
     steps:
     - name: Checkout diffusers

.github/workflows/push_tests_fast.yml

@@ -29,28 +29,29 @@ jobs:
         config:
           - name: Fast PyTorch CPU tests on Ubuntu
             framework: pytorch
-            runner: [ self-hosted, intel-cpu, 8-cpu, ci ]
+            runner: aws-general-8-plus
             image: diffusers/diffusers-pytorch-cpu
             report: torch_cpu
           - name: Fast Flax CPU tests on Ubuntu
             framework: flax
-            runner: [ self-hosted, intel-cpu, 8-cpu, ci ]
+            runner: aws-general-8-plus
             image: diffusers/diffusers-flax-cpu
             report: flax_cpu
           - name: Fast ONNXRuntime CPU tests on Ubuntu
             framework: onnxruntime
-            runner: [ self-hosted, intel-cpu, 8-cpu, ci ]
+            runner: aws-general-8-plus
             image: diffusers/diffusers-onnxruntime-cpu
             report: onnx_cpu
           - name: PyTorch Example CPU tests on Ubuntu
             framework: pytorch_examples
-            runner: [ self-hosted, intel-cpu, 8-cpu, ci ]
+            runner: aws-general-8-plus
             image: diffusers/diffusers-pytorch-cpu
             report: torch_example_cpu
 
     name: ${{ matrix.config.name }}
 
-    runs-on: ${{ matrix.config.runner }}
+    runs-on:
+      group: ${{ matrix.config.runner }}
 
     container:
       image: ${{ matrix.config.image }}

.github/workflows/run_tests_from_a_pr.yml

@@ -26,7 +26,8 @@ env:
 jobs:
   run_tests:
     name: "Run a test on our runner from a PR"
-    runs-on: [single-gpu, nvidia-gpu, t4, ci]
+    runs-on:
+      group: aws-g4dn-2xlarge
     container:
       image: ${{ github.event.inputs.docker_image }}
       options: --gpus 0 --privileged --ipc host -v /mnt/cache/.cache/huggingface:/mnt/cache/
@@ -70,4 +71,4 @@ jobs:
         env:
             PY_TEST: ${{ github.event.inputs.test }}
         run: |
-          pytest "$PY_TEST"
+          pytest "$PY_TEST"

.github/workflows/ssh-pr-runner.yml

@@ -0,0 +1,40 @@
+name: SSH into PR runners
+
+on:
+  workflow_dispatch:
+    inputs:
+      docker_image:
+        description: 'Name of the Docker image'
+        required: true
+
+env:
+  IS_GITHUB_CI: "1"
+  HF_HUB_READ_TOKEN: ${{ secrets.HF_HUB_READ_TOKEN }}
+  HF_HOME: /mnt/cache
+  DIFFUSERS_IS_CI: yes
+  OMP_NUM_THREADS: 8
+  MKL_NUM_THREADS: 8
+  RUN_SLOW: yes
+
+jobs:
+  ssh_runner:
+    name: "SSH"
+    runs-on:
+      group: aws-highmemory-32-plus
+    container:
+      image: ${{ github.event.inputs.docker_image }}
+      options: --shm-size "16gb" --ipc host -v /mnt/cache/.cache/huggingface/diffusers:/mnt/cache/ --privileged
+
+    steps:
+      - name: Checkout diffusers
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 2
+
+      - name: Tailscale # In order to be able to SSH when a test fails
+        uses: huggingface/tailscale-action@main
+        with:
+          authkey: ${{ secrets.TAILSCALE_SSH_AUTHKEY }}
+          slackChannel: ${{ secrets.SLACK_CIFEEDBACK_CHANNEL }}
+          slackToken: ${{ secrets.SLACK_CIFEEDBACK_BOT_TOKEN }}
+          waitForSSH: true

.github/workflows/ssh-runner.yml

@@ -1,4 +1,4 @@
-name: SSH into runners
+name: SSH into GPU runners
 
 on:
   workflow_dispatch:
@@ -22,7 +22,8 @@ env:
 jobs:
   ssh_runner:
     name: "SSH"
-    runs-on: [single-gpu, nvidia-gpu, "${{ github.event.inputs.runner_type }}", ci]
+    runs-on:
+      group: "${{ github.event.inputs.runner_type }}"
     container:
       image: ${{ github.event.inputs.docker_image }}
       options: --shm-size "16gb" --ipc host -v /mnt/cache/.cache/huggingface/diffusers:/mnt/cache/ --gpus 0 --privileged

CONTRIBUTING.md

@@ -63,7 +63,7 @@ In the same spirit, you are of immense help to the community by answering such q
 
 **Please** keep in mind that the more effort you put into asking or answering a question, the higher
 the quality of the publicly documented knowledge. In the same way, well-posed and well-answered questions create a high-quality knowledge database accessible to everybody, while badly posed questions or answers reduce the overall quality of the public knowledge database.
-In short, a high quality question or answer is *precise*, *concise*, *relevant*, *easy-to-understand*, *accessible*, and *well-formated/well-posed*. For more information, please have a look through the [How to write a good issue](#how-to-write-a-good-issue) section.
+In short, a high quality question or answer is *precise*, *concise*, *relevant*, *easy-to-understand*, *accessible*, and *well-formatted/well-posed*. For more information, please have a look through the [How to write a good issue](#how-to-write-a-good-issue) section.
 
 **NOTE about channels**:
 [*The forum*](https://discuss.huggingface.co/c/discussion-related-to-httpsgithubcomhuggingfacediffusers/63) is much better indexed by search engines, such as Google. Posts are ranked by popularity rather than chronologically. Hence, it's easier to look up questions and answers that we posted some time ago.

README.md

@@ -67,7 +67,7 @@ Please refer to the [How to use Stable Diffusion in Apple Silicon](https://huggi
 
 ## Quickstart
 
-Generating outputs is super easy with 🤗 Diffusers. To generate an image from text, use the `from_pretrained` method to load any pretrained diffusion model (browse the [Hub](https://huggingface.co/models?library=diffusers&sort=downloads) for 27.000+ checkpoints):
+Generating outputs is super easy with 🤗 Diffusers. To generate an image from text, use the `from_pretrained` method to load any pretrained diffusion model (browse the [Hub](https://huggingface.co/models?library=diffusers&sort=downloads) for 30,000+ checkpoints):
 
 ```python
 from diffusers import DiffusionPipeline
@@ -202,6 +202,7 @@ Also, say 👋 in our public Discord channel <a href="https://discord.gg/G7tWnz9
 
 - https://github.com/microsoft/TaskMatrix
 - https://github.com/invoke-ai/InvokeAI
+- https://github.com/InstantID/InstantID
 - https://github.com/apple/ml-stable-diffusion
 - https://github.com/Sanster/lama-cleaner
 - https://github.com/IDEA-Research/Grounded-Segment-Anything
@@ -209,7 +210,7 @@ Also, say 👋 in our public Discord channel <a href="https://discord.gg/G7tWnz9
 - https://github.com/deep-floyd/IF
 - https://github.com/bentoml/BentoML
 - https://github.com/bmaltais/kohya_ss
-- +12.000 other amazing GitHub repositories 💪
+- +14,000 other amazing GitHub repositories 💪
 
 Thank you for using us ❤️.
 

docker/diffusers-onnxruntime-cuda/Dockerfile

@@ -38,6 +38,7 @@ RUN python3.10 -m pip install --no-cache-dir --upgrade pip uv==0.1.11 && \
         datasets \
         hf-doc-builder \
         huggingface-hub \
+        hf_transfer \
         Jinja2 \
         librosa \
         numpy==1.26.4 \

docker/diffusers-pytorch-compile-cuda/Dockerfile

@@ -38,6 +38,7 @@ RUN python3.10 -m pip install --no-cache-dir --upgrade pip uv==0.1.11 && \
     datasets \
     hf-doc-builder \
     huggingface-hub \
+    hf_transfer \
     Jinja2 \
     librosa \
     numpy==1.26.4 \

docker/diffusers-pytorch-cuda/Dockerfile

@@ -38,6 +38,7 @@ RUN python3.10 -m pip install --no-cache-dir --upgrade pip uv==0.1.11 && \
     datasets \
     hf-doc-builder \
     huggingface-hub \
+    hf_transfer \
     Jinja2 \
     librosa \
     numpy==1.26.4 \

docker/diffusers-pytorch-xformers-cuda/Dockerfile

@@ -38,6 +38,7 @@ RUN python3.10 -m pip install --no-cache-dir --upgrade pip uv==0.1.11 && \
         datasets \
         hf-doc-builder \
         huggingface-hub \
+        hf_transfer \
         Jinja2 \
         librosa \
         numpy==1.26.4 \

docs/source/en/_toctree.yml

@@ -190,6 +190,10 @@
   - local: conceptual/evaluation
     title: Evaluating Diffusion Models
   title: Conceptual Guides
+- sections:
+  - local: community_projects
+    title: Projects built with Diffusers
+  title: Community Projects
 - sections:
   - isExpanded: false
     sections:
@@ -219,54 +223,76 @@
     sections:
     - local: api/models/overview
       title: Overview
-    - local: api/models/unet
-      title: UNet1DModel
-    - local: api/models/unet2d
-      title: UNet2DModel
-    - local: api/models/unet2d-cond
-      title: UNet2DConditionModel
-    - local: api/models/unet3d-cond
-      title: UNet3DConditionModel
-    - local: api/models/unet-motion
-      title: UNetMotionModel
-    - local: api/models/uvit2d
-      title: UViT2DModel
-    - local: api/models/vq
-      title: VQModel
-    - local: api/models/autoencoderkl
-      title: AutoencoderKL
-    - local: api/models/asymmetricautoencoderkl
-      title: AsymmetricAutoencoderKL
-    - local: api/models/autoencoder_tiny
-      title: Tiny AutoEncoder
-    - local: api/models/consistency_decoder_vae
-      title: ConsistencyDecoderVAE
-    - local: api/models/transformer2d
-      title: Transformer2DModel
-    - local: api/models/pixart_transformer2d
-      title: PixArtTransformer2DModel
-    - local: api/models/dit_transformer2d
-      title: DiTTransformer2DModel
-    - local: api/models/hunyuan_transformer2d
-      title: HunyuanDiT2DModel
-    - local: api/models/aura_flow_transformer2d
-      title: AuraFlowTransformer2DModel
-    - local: api/models/latte_transformer3d
-      title: LatteTransformer3DModel
-    - local: api/models/lumina_nextdit2d
-      title: LuminaNextDiT2DModel
-    - local: api/models/transformer_temporal
-      title: TransformerTemporalModel
-    - local: api/models/sd3_transformer2d
-      title: SD3Transformer2DModel
-    - local: api/models/prior_transformer
-      title: PriorTransformer
-    - local: api/models/controlnet
-      title: ControlNetModel
-    - local: api/models/controlnet_hunyuandit
-      title: HunyuanDiT2DControlNetModel
-    - local: api/models/controlnet_sd3
-      title: SD3ControlNetModel
+    - sections:
+      - local: api/models/controlnet
+        title: ControlNetModel
+      - local: api/models/controlnet_hunyuandit
+        title: HunyuanDiT2DControlNetModel
+      - local: api/models/controlnet_sd3
+        title: SD3ControlNetModel
+      - local: api/models/controlnet_sparsectrl
+        title: SparseControlNetModel
+      title: ControlNets
+    - sections:
+      - local: api/models/aura_flow_transformer2d
+        title: AuraFlowTransformer2DModel
+      - local: api/models/cogvideox_transformer3d
+        title: CogVideoXTransformer3DModel
+      - local: api/models/dit_transformer2d
+        title: DiTTransformer2DModel
+      - local: api/models/flux_transformer
+        title: FluxTransformer2DModel
+      - local: api/models/hunyuan_transformer2d
+        title: HunyuanDiT2DModel
+      - local: api/models/latte_transformer3d
+        title: LatteTransformer3DModel
+      - local: api/models/lumina_nextdit2d
+        title: LuminaNextDiT2DModel
+      - local: api/models/pixart_transformer2d
+        title: PixArtTransformer2DModel
+      - local: api/models/prior_transformer
+        title: PriorTransformer
+      - local: api/models/sd3_transformer2d
+        title: SD3Transformer2DModel
+      - local: api/models/stable_audio_transformer
+        title: StableAudioDiTModel
+      - local: api/models/transformer2d
+        title: Transformer2DModel
+      - local: api/models/transformer_temporal
+        title: TransformerTemporalModel
+      title: Transformers
+    - sections:
+      - local: api/models/stable_cascade_unet
+        title: StableCascadeUNet
+      - local: api/models/unet
+        title: UNet1DModel
+      - local: api/models/unet2d
+        title: UNet2DModel
+      - local: api/models/unet2d-cond
+        title: UNet2DConditionModel
+      - local: api/models/unet3d-cond
+        title: UNet3DConditionModel
+      - local: api/models/unet-motion
+        title: UNetMotionModel
+      - local: api/models/uvit2d
+        title: UViT2DModel
+      title: UNets
+    - sections:
+      - local: api/models/autoencoderkl
+        title: AutoencoderKL
+      - local: api/models/autoencoderkl_cogvideox
+        title: AutoencoderKLCogVideoX
+      - local: api/models/asymmetricautoencoderkl
+        title: AsymmetricAutoencoderKL
+      - local: api/models/consistency_decoder_vae
+        title: ConsistencyDecoderVAE
+      - local: api/models/autoencoder_oobleck
+        title: Oobleck AutoEncoder
+      - local: api/models/autoencoder_tiny
+        title: Tiny AutoEncoder
+      - local: api/models/vq
+        title: VQModel
+      title: VAEs
     title: Models
   - isExpanded: false
     sections:
@@ -288,6 +314,8 @@
       title: AutoPipeline
     - local: api/pipelines/blip_diffusion
       title: BLIP-Diffusion
+    - local: api/pipelines/cogvideox
+      title: CogVideoX
     - local: api/pipelines/consistency_models
       title: Consistency Models
     - local: api/pipelines/controlnet
@@ -314,6 +342,8 @@
       title: DiffEdit
     - local: api/pipelines/dit
       title: DiT
+    - local: api/pipelines/flux
+      title: Flux
     - local: api/pipelines/hunyuandit
       title: Hunyuan-DiT
     - local: api/pipelines/i2vgenxl
@@ -332,6 +362,8 @@
       title: Latent Consistency Models
     - local: api/pipelines/latent_diffusion
       title: Latent Diffusion
+    - local: api/pipelines/latte
+      title: Latte
     - local: api/pipelines/ledits_pp
       title: LEDITS++
     - local: api/pipelines/lumina
@@ -358,6 +390,8 @@
       title: Semantic Guidance
     - local: api/pipelines/shap_e
       title: Shap-E
+    - local: api/pipelines/stable_audio
+      title: Stable Audio
     - local: api/pipelines/stable_cascade
       title: Stable Cascade
     - sections:
@@ -421,6 +455,8 @@
       title: CMStochasticIterativeScheduler
     - local: api/schedulers/consistency_decoder
       title: ConsistencyDecoderScheduler
+    - local: api/schedulers/cosine_dpm
+      title: CosineDPMSolverMultistepScheduler
     - local: api/schedulers/ddim_inverse
       title: DDIMInverseScheduler
     - local: api/schedulers/ddim

docs/source/en/api/loaders/lora.md

@@ -12,10 +12,13 @@ specific language governing permissions and limitations under the License.
 
 # LoRA
 
-LoRA is a fast and lightweight training method that inserts and trains a significantly smaller number of parameters instead of all the model parameters. This produces a smaller file (~100 MBs) and makes it easier to quickly train a model to learn a new concept. LoRA weights are typically loaded into the UNet, text encoder or both. There are two classes for loading LoRA weights:
+LoRA is a fast and lightweight training method that inserts and trains a significantly smaller number of parameters instead of all the model parameters. This produces a smaller file (~100 MBs) and makes it easier to quickly train a model to learn a new concept. LoRA weights are typically loaded into the denoiser, text encoder or both. The denoiser usually corresponds to a UNet ([`UNet2DConditionModel`], for example) or a Transformer ([`SD3Transformer2DModel`], for example). There are several classes for loading LoRA weights:
 
-- [`LoraLoaderMixin`] provides functions for loading and unloading, fusing and unfusing, enabling and disabling, and more functions for managing LoRA weights. This class can be used with any model.
-- [`StableDiffusionXLLoraLoaderMixin`] is a [Stable Diffusion (SDXL)](../../api/pipelines/stable_diffusion/stable_diffusion_xl) version of the [`LoraLoaderMixin`] class for loading and saving LoRA weights. It can only be used with the SDXL model.
+- [`StableDiffusionLoraLoaderMixin`] provides functions for loading and unloading, fusing and unfusing, enabling and disabling, and more functions for managing LoRA weights. This class can be used with any model.
+- [`StableDiffusionXLLoraLoaderMixin`] is a [Stable Diffusion (SDXL)](../../api/pipelines/stable_diffusion/stable_diffusion_xl) version of the [`StableDiffusionLoraLoaderMixin`] class for loading and saving LoRA weights. It can only be used with the SDXL model.
+- [`SD3LoraLoaderMixin`] provides similar functions for [Stable Diffusion 3](https://huggingface.co/blog/sd3).
+- [`AmusedLoraLoaderMixin`] is for the [`AmusedPipeline`].
+- [`LoraBaseMixin`] provides a base class with several utility methods to fuse, unfuse, unload, LoRAs and more.
 
 <Tip>
 
@@ -23,10 +26,22 @@ To learn more about how to load LoRA weights, see the [LoRA](../../using-diffuse
 
 </Tip>
 
-## LoraLoaderMixin
+## StableDiffusionLoraLoaderMixin
 
-[[autodoc]] loaders.lora.LoraLoaderMixin
+[[autodoc]] loaders.lora_pipeline.StableDiffusionLoraLoaderMixin
 
 ## StableDiffusionXLLoraLoaderMixin
 
-[[autodoc]] loaders.lora.StableDiffusionXLLoraLoaderMixin
+[[autodoc]] loaders.lora_pipeline.StableDiffusionXLLoraLoaderMixin
+
+## SD3LoraLoaderMixin
+
+[[autodoc]] loaders.lora_pipeline.SD3LoraLoaderMixin
+
+## AmusedLoraLoaderMixin
+
+[[autodoc]] loaders.lora_pipeline.AmusedLoraLoaderMixin
+
+## LoraBaseMixin
+
+[[autodoc]] loaders.lora_base.LoraBaseMixin

docs/source/en/api/loaders/peft.md

@@ -12,7 +12,7 @@ specific language governing permissions and limitations under the License.
 
 # PEFT
 
-Diffusers supports loading adapters such as [LoRA](../../using-diffusers/loading_adapters) with the [PEFT](https://huggingface.co/docs/peft/index) library with the [`~loaders.peft.PeftAdapterMixin`] class. This allows modeling classes in Diffusers like [`UNet2DConditionModel`] to load an adapter.
+Diffusers supports loading adapters such as [LoRA](../../using-diffusers/loading_adapters) with the [PEFT](https://huggingface.co/docs/peft/index) library with the [`~loaders.peft.PeftAdapterMixin`] class. This allows modeling classes in Diffusers like [`UNet2DConditionModel`], [`SD3Transformer2DModel`] to operate with an adapter.
 
 <Tip>
 

docs/source/en/api/loaders/single_file.md

@@ -22,6 +22,7 @@ The [`~loaders.FromSingleFileMixin.from_single_file`] method allows you to load:
 
 ## Supported pipelines
 
+- [`CogVideoXPipeline`]
 - [`StableDiffusionPipeline`]
 - [`StableDiffusionImg2ImgPipeline`]
 - [`StableDiffusionInpaintPipeline`]
@@ -49,8 +50,10 @@ The [`~loaders.FromSingleFileMixin.from_single_file`] method allows you to load:
 - [`UNet2DConditionModel`]
 - [`StableCascadeUNet`]
 - [`AutoencoderKL`]
+- [`AutoencoderKLCogVideoX`]
 - [`ControlNetModel`]
 - [`SD3Transformer2DModel`]
+- [`FluxTransformer2DModel`]
 
 ## FromSingleFileMixin
 

docs/source/en/api/loaders/unet.md

@@ -12,7 +12,7 @@ specific language governing permissions and limitations under the License.
 
 # UNet
 
-Some training methods - like LoRA and Custom Diffusion - typically target the UNet's attention layers, but these training methods can also target other non-attention layers. Instead of training all of a model's parameters, only a subset of the parameters are trained, which is faster and more efficient. This class is useful if you're *only* loading weights into a UNet. If you need to load weights into the text encoder or a text encoder and UNet, try using the [`~loaders.LoraLoaderMixin.load_lora_weights`] function instead.
+Some training methods - like LoRA and Custom Diffusion - typically target the UNet's attention layers, but these training methods can also target other non-attention layers. Instead of training all of a model's parameters, only a subset of the parameters are trained, which is faster and more efficient. This class is useful if you're *only* loading weights into a UNet. If you need to load weights into the text encoder or a text encoder and UNet, try using the [`~loaders.StableDiffusionLoraLoaderMixin.load_lora_weights`] function instead.
 
 The [`UNet2DConditionLoadersMixin`] class provides functions for loading and saving weights, fusing and unfusing LoRAs, disabling and enabling LoRAs, and setting and deleting adapters.
 

docs/source/en/api/models/autoencoder_oobleck.md

@@ -0,0 +1,38 @@
+<!--Copyright 2024 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License.
+-->
+
+# AutoencoderOobleck
+
+The Oobleck variational autoencoder (VAE) model with KL loss was introduced in [Stability-AI/stable-audio-tools](https://github.com/Stability-AI/stable-audio-tools) and [Stable Audio Open](https://huggingface.co/papers/2407.14358) by Stability AI. The model is used in 🤗 Diffusers to encode audio waveforms into latents and to decode latent representations into audio waveforms.
+
+The abstract from the paper is:
+
+*Open generative models are vitally important for the community, allowing for fine-tunes and serving as baselines when presenting new models. However, most current text-to-audio models are private and not accessible for artists and researchers to build upon. Here we describe the architecture and training process of a new open-weights text-to-audio model trained with Creative Commons data. Our evaluation shows that the model's performance is competitive with the state-of-the-art across various metrics. Notably, the reported FDopenl3 results (measuring the realism of the generations) showcase its potential for high-quality stereo sound synthesis at 44.1kHz.*
+
+## AutoencoderOobleck
+
+[[autodoc]] AutoencoderOobleck
+    - decode
+    - encode
+    - all
+
+## OobleckDecoderOutput
+
+[[autodoc]] models.autoencoders.autoencoder_oobleck.OobleckDecoderOutput
+
+## OobleckDecoderOutput
+
+[[autodoc]] models.autoencoders.autoencoder_oobleck.OobleckDecoderOutput
+
+## AutoencoderOobleckOutput
+
+[[autodoc]] models.autoencoders.autoencoder_oobleck.AutoencoderOobleckOutput

docs/source/en/api/models/autoencoderkl_cogvideox.md

@@ -0,0 +1,37 @@
+<!--Copyright 2024 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License. -->
+
+# AutoencoderKLCogVideoX
+
+The 3D variational autoencoder (VAE) model with KL loss used in [CogVideoX](https://github.com/THUDM/CogVideo) was introduced in [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://github.com/THUDM/CogVideo/blob/main/resources/CogVideoX.pdf) by Tsinghua University & ZhipuAI.
+
+The model can be loaded with the following code snippet.
+
+```python
+from diffusers import AutoencoderKLCogVideoX
+
+vae = AutoencoderKLCogVideoX.from_pretrained("THUDM/CogVideoX-2b", subfolder="vae", torch_dtype=torch.float16).to("cuda")
+```
+
+## AutoencoderKLCogVideoX
+
+[[autodoc]] AutoencoderKLCogVideoX
+    - decode
+    - encode
+    - all
+
+## AutoencoderKLOutput
+
+[[autodoc]] models.autoencoders.autoencoder_kl.AutoencoderKLOutput
+
+## DecoderOutput
+
+[[autodoc]] models.autoencoders.vae.DecoderOutput

docs/source/en/api/models/cogvideox_transformer3d.md

@@ -0,0 +1,30 @@
+<!--Copyright 2024 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License. -->
+
+# CogVideoXTransformer3DModel
+
+A Diffusion Transformer model for 3D data from [CogVideoX](https://github.com/THUDM/CogVideo) was introduced in [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://github.com/THUDM/CogVideo/blob/main/resources/CogVideoX.pdf) by Tsinghua University & ZhipuAI.
+
+The model can be loaded with the following code snippet.
+
+```python
+from diffusers import CogVideoXTransformer3DModel
+
+vae = CogVideoXTransformer3DModel.from_pretrained("THUDM/CogVideoX-2b", subfolder="transformer", torch_dtype=torch.float16).to("cuda")
+```
+
+## CogVideoXTransformer3DModel
+
+[[autodoc]] CogVideoXTransformer3DModel
+
+## Transformer2DModelOutput
+
+[[autodoc]] models.modeling_outputs.Transformer2DModelOutput

docs/source/en/api/models/controlnet_sparsectrl.md

@@ -0,0 +1,46 @@
+<!-- Copyright 2024 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License. -->
+
+# SparseControlNetModel
+
+SparseControlNetModel is an implementation of ControlNet for [AnimateDiff](https://arxiv.org/abs/2307.04725).
+
+ControlNet was introduced in [Adding Conditional Control to Text-to-Image Diffusion Models](https://huggingface.co/papers/2302.05543) by Lvmin Zhang, Anyi Rao, and Maneesh Agrawala.
+
+The SparseCtrl version of ControlNet was introduced in [SparseCtrl: Adding Sparse Controls to Text-to-Video Diffusion Models](https://arxiv.org/abs/2311.16933) for achieving controlled generation in text-to-video diffusion models by Yuwei Guo, Ceyuan Yang, Anyi Rao, Maneesh Agrawala, Dahua Lin, and Bo Dai.
+
+The abstract from the paper is:
+
+*The development of text-to-video (T2V), i.e., generating videos with a given text prompt, has been significantly advanced in recent years. However, relying solely on text prompts often results in ambiguous frame composition due to spatial uncertainty. The research community thus leverages the dense structure signals, e.g., per-frame depth/edge sequences, to enhance controllability, whose collection accordingly increases the burden of inference. In this work, we present SparseCtrl to enable flexible structure control with temporally sparse signals, requiring only one or a few inputs, as shown in Figure 1. It incorporates an additional condition encoder to process these sparse signals while leaving the pre-trained T2V model untouched. The proposed approach is compatible with various modalities, including sketches, depth maps, and RGB images, providing more practical control for video generation and promoting applications such as storyboarding, depth rendering, keyframe animation, and interpolation. Extensive experiments demonstrate the generalization of SparseCtrl on both original and personalized T2V generators. Codes and models will be publicly available at [this https URL](https://guoyww.github.io/projects/SparseCtrl).*
+
+## Example for loading SparseControlNetModel
+
+```python
+import torch
+from diffusers import SparseControlNetModel
+
+# fp32 variant in float16
+# 1. Scribble checkpoint
+controlnet = SparseControlNetModel.from_pretrained("guoyww/animatediff-sparsectrl-scribble", torch_dtype=torch.float16)
+
+# 2. RGB checkpoint
+controlnet = SparseControlNetModel.from_pretrained("guoyww/animatediff-sparsectrl-rgb", torch_dtype=torch.float16)
+
+# For loading fp16 variant, pass `variant="fp16"` as an additional parameter
+```
+
+## SparseControlNetModel
+
+[[autodoc]] SparseControlNetModel
+
+## SparseControlNetOutput
+
+[[autodoc]] models.controlnet_sparsectrl.SparseControlNetOutput

docs/source/en/api/models/flux_transformer.md

@@ -0,0 +1,19 @@
+<!--Copyright 2024 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License.
+-->
+
+# FluxTransformer2DModel
+
+A Transformer model for image-like data from [Flux](https://blackforestlabs.ai/announcing-black-forest-labs/).
+
+## FluxTransformer2DModel
+
+[[autodoc]] FluxTransformer2DModel

docs/source/en/api/models/stable_audio_transformer.md

@@ -0,0 +1,19 @@
+<!--Copyright 2024 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License.
+-->
+
+# StableAudioDiTModel
+
+A Transformer model for audio waveforms from [Stable Audio Open](https://huggingface.co/papers/2407.14358).
+
+## StableAudioDiTModel
+
+[[autodoc]] StableAudioDiTModel

docs/source/en/api/models/stable_cascade_unet.md

@@ -0,0 +1,19 @@
+<!--Copyright 2024 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License.
+-->
+
+# StableCascadeUNet
+
+A UNet model from the [Stable Cascade pipeline](../pipelines/stable_cascade.md).
+
+## StableCascadeUNet
+
+[[autodoc]] models.unets.unet_stable_cascade.StableCascadeUNet

docs/source/en/api/pipelines/animatediff.md

@@ -25,6 +25,9 @@ The abstract of the paper is the following:
 | Pipeline | Tasks | Demo
 |---|---|:---:|
 | [AnimateDiffPipeline](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/animatediff/pipeline_animatediff.py) | *Text-to-Video Generation with AnimateDiff* |
+| [AnimateDiffControlNetPipeline](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/animatediff/pipeline_animatediff_controlnet.py) | *Controlled Video-to-Video Generation with AnimateDiff using ControlNet* |
+| [AnimateDiffSparseControlNetPipeline](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/animatediff/pipeline_animatediff_sparsectrl.py) | *Controlled Video-to-Video Generation with AnimateDiff using SparseCtrl* |
+| [AnimateDiffSDXLPipeline](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/animatediff/pipeline_animatediff_sdxl.py) | *Video-to-Video Generation with AnimateDiff* |
 | [AnimateDiffVideoToVideoPipeline](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/animatediff/pipeline_animatediff_video2video.py) | *Video-to-Video Generation with AnimateDiff* |
 
 ## Available checkpoints
@@ -100,6 +103,266 @@ AnimateDiff tends to work better with finetuned Stable Diffusion models. If you
 
 </Tip>
 
+### AnimateDiffControlNetPipeline
+
+AnimateDiff can also be used with ControlNets ControlNet was introduced in [Adding Conditional Control to Text-to-Image Diffusion Models](https://huggingface.co/papers/2302.05543) by Lvmin Zhang, Anyi Rao, and Maneesh Agrawala. With a ControlNet model, you can provide an additional control image to condition and control Stable Diffusion generation. For example, if you provide depth maps, the ControlNet model generates a video that'll preserve the spatial information from the depth maps. It is a more flexible and accurate way to control the video generation process.
+
+```python
+import torch
+from diffusers import AnimateDiffControlNetPipeline, AutoencoderKL, ControlNetModel, MotionAdapter, LCMScheduler
+from diffusers.utils import export_to_gif, load_video
+
+# Additionally, you will need a preprocess videos before they can be used with the ControlNet
+# HF maintains just the right package for it: `pip install controlnet_aux`
+from controlnet_aux.processor import ZoeDetector
+
+# Download controlnets from https://huggingface.co/lllyasviel/ControlNet-v1-1 to use .from_single_file
+# Download Diffusers-format controlnets, such as https://huggingface.co/lllyasviel/sd-controlnet-depth, to use .from_pretrained()
+controlnet = ControlNetModel.from_single_file("control_v11f1p_sd15_depth.pth", torch_dtype=torch.float16)
+
+# We use AnimateLCM for this example but one can use the original motion adapters as well (for example, https://huggingface.co/guoyww/animatediff-motion-adapter-v1-5-3)
+motion_adapter = MotionAdapter.from_pretrained("wangfuyun/AnimateLCM")
+
+vae = AutoencoderKL.from_pretrained("stabilityai/sd-vae-ft-mse", torch_dtype=torch.float16)
+pipe: AnimateDiffControlNetPipeline = AnimateDiffControlNetPipeline.from_pretrained(
+    "SG161222/Realistic_Vision_V5.1_noVAE",
+    motion_adapter=motion_adapter,
+    controlnet=controlnet,
+    vae=vae,
+).to(device="cuda", dtype=torch.float16)
+pipe.scheduler = LCMScheduler.from_config(pipe.scheduler.config, beta_schedule="linear")
+pipe.load_lora_weights("wangfuyun/AnimateLCM", weight_name="AnimateLCM_sd15_t2v_lora.safetensors", adapter_name="lcm-lora")
+pipe.set_adapters(["lcm-lora"], [0.8])
+
+depth_detector = ZoeDetector.from_pretrained("lllyasviel/Annotators").to("cuda")
+video = load_video("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/animatediff-vid2vid-input-1.gif")
+conditioning_frames = []
+
+with pipe.progress_bar(total=len(video)) as progress_bar:
+    for frame in video:
+        conditioning_frames.append(depth_detector(frame))
+        progress_bar.update()
+
+prompt = "a panda, playing a guitar, sitting in a pink boat, in the ocean, mountains in background, realistic, high quality"
+negative_prompt = "bad quality, worst quality"
+
+video = pipe(
+    prompt=prompt,
+    negative_prompt=negative_prompt,
+    num_frames=len(video),
+    num_inference_steps=10,
+    guidance_scale=2.0,
+    conditioning_frames=conditioning_frames,
+    generator=torch.Generator().manual_seed(42),
+).frames[0]
+
+export_to_gif(video, "animatediff_controlnet.gif", fps=8)
+```
+
+Here are some sample outputs:
+
+<table align="center">
+    <tr>
+      <th align="center">Source Video</th>
+      <th align="center">Output Video</th>
+    </tr>
+    <tr>
+        <td align="center">
+          raccoon playing a guitar
+          <br />
+          <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/animatediff-vid2vid-input-1.gif" alt="racoon playing a guitar" />
+        </td>
+        <td align="center">
+          a panda, playing a guitar, sitting in a pink boat, in the ocean, mountains in background, realistic, high quality
+          <br/>
+          <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/animatediff-controlnet-output.gif" alt="a panda, playing a guitar, sitting in a pink boat, in the ocean, mountains in background, realistic, high quality" />
+        </td>
+    </tr>
+</table>
+
+### AnimateDiffSparseControlNetPipeline
+
+[SparseCtrl: Adding Sparse Controls to Text-to-Video Diffusion Models](https://arxiv.org/abs/2311.16933) for achieving controlled generation in text-to-video diffusion models by Yuwei Guo, Ceyuan Yang, Anyi Rao, Maneesh Agrawala, Dahua Lin, and Bo Dai.
+
+The abstract from the paper is:
+
+*The development of text-to-video (T2V), i.e., generating videos with a given text prompt, has been significantly advanced in recent years. However, relying solely on text prompts often results in ambiguous frame composition due to spatial uncertainty. The research community thus leverages the dense structure signals, e.g., per-frame depth/edge sequences, to enhance controllability, whose collection accordingly increases the burden of inference. In this work, we present SparseCtrl to enable flexible structure control with temporally sparse signals, requiring only one or a few inputs, as shown in Figure 1. It incorporates an additional condition encoder to process these sparse signals while leaving the pre-trained T2V model untouched. The proposed approach is compatible with various modalities, including sketches, depth maps, and RGB images, providing more practical control for video generation and promoting applications such as storyboarding, depth rendering, keyframe animation, and interpolation. Extensive experiments demonstrate the generalization of SparseCtrl on both original and personalized T2V generators. Codes and models will be publicly available at [this https URL](https://guoyww.github.io/projects/SparseCtrl).*
+
+SparseCtrl introduces the following checkpoints for controlled text-to-video generation:
+
+- [SparseCtrl Scribble](https://huggingface.co/guoyww/animatediff-sparsectrl-scribble)
+- [SparseCtrl RGB](https://huggingface.co/guoyww/animatediff-sparsectrl-rgb)
+
+#### Using SparseCtrl Scribble
+
+```python
+import torch
+
+from diffusers import AnimateDiffSparseControlNetPipeline
+from diffusers.models import AutoencoderKL, MotionAdapter, SparseControlNetModel
+from diffusers.schedulers import DPMSolverMultistepScheduler
+from diffusers.utils import export_to_gif, load_image
+
+
+model_id = "SG161222/Realistic_Vision_V5.1_noVAE"
+motion_adapter_id = "guoyww/animatediff-motion-adapter-v1-5-3"
+controlnet_id = "guoyww/animatediff-sparsectrl-scribble"
+lora_adapter_id = "guoyww/animatediff-motion-lora-v1-5-3"
+vae_id = "stabilityai/sd-vae-ft-mse"
+device = "cuda"
+
+motion_adapter = MotionAdapter.from_pretrained(motion_adapter_id, torch_dtype=torch.float16).to(device)
+controlnet = SparseControlNetModel.from_pretrained(controlnet_id, torch_dtype=torch.float16).to(device)
+vae = AutoencoderKL.from_pretrained(vae_id, torch_dtype=torch.float16).to(device)
+scheduler = DPMSolverMultistepScheduler.from_pretrained(
+    model_id,
+    subfolder="scheduler",
+    beta_schedule="linear",
+    algorithm_type="dpmsolver++",
+    use_karras_sigmas=True,
+)
+pipe = AnimateDiffSparseControlNetPipeline.from_pretrained(
+    model_id,
+    motion_adapter=motion_adapter,
+    controlnet=controlnet,
+    vae=vae,
+    scheduler=scheduler,
+    torch_dtype=torch.float16,
+).to(device)
+pipe.load_lora_weights(lora_adapter_id, adapter_name="motion_lora")
+pipe.fuse_lora(lora_scale=1.0)
+
+prompt = "an aerial view of a cyberpunk city, night time, neon lights, masterpiece, high quality"
+negative_prompt = "low quality, worst quality, letterboxed"
+
+image_files = [
+    "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/animatediff-scribble-1.png",
+    "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/animatediff-scribble-2.png",
+    "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/animatediff-scribble-3.png"
+]
+condition_frame_indices = [0, 8, 15]
+conditioning_frames = [load_image(img_file) for img_file in image_files]
+
+video = pipe(
+    prompt=prompt,
+    negative_prompt=negative_prompt,
+    num_inference_steps=25,
+    conditioning_frames=conditioning_frames,
+    controlnet_conditioning_scale=1.0,
+    controlnet_frame_indices=condition_frame_indices,
+    generator=torch.Generator().manual_seed(1337),
+).frames[0]
+export_to_gif(video, "output.gif")
+```
+
+Here are some sample outputs:
+
+<table align="center">
+    <tr>
+        <center>
+          <b>an aerial view of a cyberpunk city, night time, neon lights, masterpiece, high quality</b>
+        </center>
+    </tr>
+    <tr>
+        <td>
+          <center>
+            <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/animatediff-scribble-1.png" alt="scribble-1" />
+          </center>
+        </td>
+        <td>
+          <center>
+            <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/animatediff-scribble-2.png" alt="scribble-2" />
+          </center>
+        </td>
+        <td>
+          <center>
+            <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/animatediff-scribble-3.png" alt="scribble-3" />
+          </center>
+        </td>
+    </tr>
+    <tr>
+        <td colspan=3>
+          <center>
+            <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/animatediff-sparsectrl-scribble-results.gif" alt="an aerial view of a cyberpunk city, night time, neon lights, masterpiece, high quality" />
+          </center>
+        </td>
+    </tr>
+</table>
+
+#### Using SparseCtrl RGB
+
+```python
+import torch
+
+from diffusers import AnimateDiffSparseControlNetPipeline
+from diffusers.models import AutoencoderKL, MotionAdapter, SparseControlNetModel
+from diffusers.schedulers import DPMSolverMultistepScheduler
+from diffusers.utils import export_to_gif, load_image
+
+
+model_id = "SG161222/Realistic_Vision_V5.1_noVAE"
+motion_adapter_id = "guoyww/animatediff-motion-adapter-v1-5-3"
+controlnet_id = "guoyww/animatediff-sparsectrl-rgb"
+lora_adapter_id = "guoyww/animatediff-motion-lora-v1-5-3"
+vae_id = "stabilityai/sd-vae-ft-mse"
+device = "cuda"
+
+motion_adapter = MotionAdapter.from_pretrained(motion_adapter_id, torch_dtype=torch.float16).to(device)
+controlnet = SparseControlNetModel.from_pretrained(controlnet_id, torch_dtype=torch.float16).to(device)
+vae = AutoencoderKL.from_pretrained(vae_id, torch_dtype=torch.float16).to(device)
+scheduler = DPMSolverMultistepScheduler.from_pretrained(
+    model_id,
+    subfolder="scheduler",
+    beta_schedule="linear",
+    algorithm_type="dpmsolver++",
+    use_karras_sigmas=True,
+)
+pipe = AnimateDiffSparseControlNetPipeline.from_pretrained(
+    model_id,
+    motion_adapter=motion_adapter,
+    controlnet=controlnet,
+    vae=vae,
+    scheduler=scheduler,
+    torch_dtype=torch.float16,
+).to(device)
+pipe.load_lora_weights(lora_adapter_id, adapter_name="motion_lora")
+
+image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/animatediff-firework.png")
+
+video = pipe(
+    prompt="closeup face photo of man in black clothes, night city street, bokeh, fireworks in background",
+    negative_prompt="low quality, worst quality",
+    num_inference_steps=25,
+    conditioning_frames=image,
+    controlnet_frame_indices=[0],
+    controlnet_conditioning_scale=1.0,
+    generator=torch.Generator().manual_seed(42),
+).frames[0]
+export_to_gif(video, "output.gif")
+```
+
+Here are some sample outputs:
+
+<table align="center">
+    <tr>
+        <center>
+          <b>closeup face photo of man in black clothes, night city street, bokeh, fireworks in background</b>
+        </center>
+    </tr>
+    <tr>
+        <td>
+          <center>
+            <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/animatediff-firework.png" alt="closeup face photo of man in black clothes, night city street, bokeh, fireworks in background" />
+          </center>
+        </td>
+        <td>
+          <center>
+            <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/animatediff-sparsectrl-rgb-result.gif" alt="closeup face photo of man in black clothes, night city street, bokeh, fireworks in background" />
+          </center>
+        </td>
+    </tr>
+</table>
+
 ### AnimateDiffSDXLPipeline
 
 AnimateDiff can also be used with SDXL models. This is currently an experimental feature as only a beta release of the motion adapter checkpoint is available.
@@ -571,7 +834,6 @@ ckpt_path = "https://huggingface.co/Lightricks/LongAnimateDiff/blob/main/lt_long
 
 adapter = MotionAdapter.from_single_file(ckpt_path, torch_dtype=torch.float16)
 pipe = AnimateDiffPipeline.from_pretrained("emilianJR/epiCRealism", motion_adapter=adapter)
-
 ```
 
 ## AnimateDiffPipeline
@@ -580,6 +842,18 @@ pipe = AnimateDiffPipeline.from_pretrained("emilianJR/epiCRealism", motion_adapt
   - all
   - __call__
 
+## AnimateDiffControlNetPipeline
+
+[[autodoc]] AnimateDiffControlNetPipeline
+  - all
+  - __call__
+
+## AnimateDiffSparseControlNetPipeline
+
+[[autodoc]] AnimateDiffSparseControlNetPipeline
+  - all
+  - __call__
+
 ## AnimateDiffSDXLPipeline
 
 [[autodoc]] AnimateDiffSDXLPipeline

docs/source/en/api/pipelines/aura_flow.md

@@ -18,7 +18,7 @@ It was developed by the Fal team and more details about it can be found in [this
 
 <Tip>
 
-AuraFlow can be quite expensive to run on consumer hardware devices. However, you can perform a suite of optimizations to run it faster and in a more memory-friendly manner. Check out [this section](https://huggingface.co/blog/sd3#memory-optimizations-for-sd3) for more details. 
+AuraFlow can be quite expensive to run on consumer hardware devices. However, you can perform a suite of optimizations to run it faster and in a more memory-friendly manner. Check out [this section](https://huggingface.co/blog/sd3#memory-optimizations-for-sd3) for more details.
 
 </Tip>
 

docs/source/en/api/pipelines/cogvideox.md

@@ -0,0 +1,91 @@
+<!--Copyright 2024 The HuggingFace Team. All rights reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+-->
+
+# CogVideoX
+
+<!-- TODO: update paper with ArXiv link when ready. -->
+
+[CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://github.com/THUDM/CogVideo/blob/main/resources/CogVideoX.pdf) from Tsinghua University & ZhipuAI.
+
+The abstract from the paper is:
+
+*We introduce CogVideoX, a large-scale diffusion transformer model designed for generating videos based on text prompts. To efficently model video data, we propose to levearge a 3D Variational Autoencoder (VAE) to compresses videos along both spatial and temporal dimensions. To improve the text-video alignment, we propose an expert transformer with the expert adaptive LayerNorm to facilitate the deep fusion between the two modalities. By employing a progressive training technique, CogVideoX is adept at producing coherent, long-duration videos characterized by significant motion. In addition, we develop an effectively text-video data processing pipeline that includes various data preprocessing strategies and a video captioning method. It significantly helps enhance the performance of CogVideoX, improving both generation quality and semantic alignment. Results show that CogVideoX demonstrates state-of-the-art performance across both multiple machine metrics and human evaluations. The model weight of CogVideoX-2B is publicly available at https://github.com/THUDM/CogVideo.*
+
+<Tip>
+
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers.md) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading.md#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+
+</Tip>
+
+This pipeline was contributed by [zRzRzRzRzRzRzR](https://github.com/zRzRzRzRzRzRzR). The original codebase can be found [here](https://huggingface.co/THUDM). The original weights can be found under [hf.co/THUDM](https://huggingface.co/THUDM).
+
+## Inference
+
+Use [`torch.compile`](https://huggingface.co/docs/diffusers/main/en/tutorials/fast_diffusion#torchcompile) to reduce the inference latency.
+
+First, load the pipeline:
+
+```python
+import torch
+from diffusers import CogVideoXPipeline
+from diffusers.utils import export_to_video
+
+pipe = CogVideoXPipeline.from_pretrained("THUDM/CogVideoX-2b").to("cuda")
+prompt = (
+    "A panda, dressed in a small, red jacket and a tiny hat, sits on a wooden stool in a serene bamboo forest. "
+    "The panda's fluffy paws strum a miniature acoustic guitar, producing soft, melodic tunes. Nearby, a few other "
+    "pandas gather, watching curiously and some clapping in rhythm. Sunlight filters through the tall bamboo, "
+    "casting a gentle glow on the scene. The panda's face is expressive, showing concentration and joy as it plays. "
+    "The background includes a small, flowing stream and vibrant green foliage, enhancing the peaceful and magical "
+    "atmosphere of this unique musical performance."
+)
+video = pipe(prompt=prompt, guidance_scale=6, num_inference_steps=50).frames[0]
+export_to_video(video, "output.mp4", fps=8)
+```
+
+Then change the memory layout of the pipelines `transformer` and `vae` components to `torch.channels-last`:
+
+```python
+pipeline.transformer.to(memory_format=torch.channels_last)
+pipeline.vae.to(memory_format=torch.channels_last)
+```
+
+Finally, compile the components and run inference:
+
+```python
+pipeline.transformer = torch.compile(pipeline.transformer)
+pipeline.vae.decode = torch.compile(pipeline.vae.decode)
+
+# CogVideoX works very well with long and well-described prompts
+prompt = "A panda, dressed in a small, red jacket and a tiny hat, sits on a wooden stool in a serene bamboo forest. The panda's fluffy paws strum a miniature acoustic guitar, producing soft, melodic tunes. Nearby, a few other pandas gather, watching curiously and some clapping in rhythm. Sunlight filters through the tall bamboo, casting a gentle glow on the scene. The panda's face is expressive, showing concentration and joy as it plays. The background includes a small, flowing stream and vibrant green foliage, enhancing the peaceful and magical atmosphere of this unique musical performance."
+video = pipeline(prompt=prompt, guidance_scale=6, num_inference_steps=50).frames[0]
+```
+
+The [benchmark](TODO: link) results on an 80GB A100 machine are:
+
+```
+Without torch.compile(): Average inference time: TODO seconds.
+With torch.compile(): Average inference time: TODO seconds.
+```
+
+## CogVideoXPipeline
+
+[[autodoc]] CogVideoXPipeline
+  - all
+  - __call__
+
+## CogVideoXPipelineOutput
+
+[[autodoc]] pipelines.cogvideo.pipeline_cogvideox.CogVideoXPipelineOutput

docs/source/en/api/pipelines/flux.md

@@ -0,0 +1,165 @@
+<!--Copyright 2024 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License.
+-->
+
+# Flux
+
+Flux is a series of text-to-image generation models based on diffusion transformers. To know more about Flux, check out the original [blog post](https://blackforestlabs.ai/announcing-black-forest-labs/) by the creators of Flux, Black Forest Labs.
+
+Original model checkpoints for Flux can be found [here](https://huggingface.co/black-forest-labs). Original inference code can be found [here](https://github.com/black-forest-labs/flux).
+
+<Tip>
+
+Flux can be quite expensive to run on consumer hardware devices. However, you can perform a suite of optimizations to run it faster and in a more memory-friendly manner. Check out [this section](https://huggingface.co/blog/sd3#memory-optimizations-for-sd3) for more details. Additionally, Flux can benefit from quantization for memory efficiency with a trade-off in inference latency. Refer to [this blog post](https://huggingface.co/blog/quanto-diffusers) to learn more.  For an exhaustive list of resources, check out [this gist](https://gist.github.com/sayakpaul/b664605caf0aa3bf8585ab109dd5ac9c).
+
+</Tip>
+
+Flux comes in two variants:
+
+* Timestep-distilled (`black-forest-labs/FLUX.1-schnell`)
+* Guidance-distilled (`black-forest-labs/FLUX.1-dev`)
+
+Both checkpoints have slightly difference usage which we detail below.
+
+### Timestep-distilled
+
+* `max_sequence_length` cannot be more than 256.
+* `guidance_scale` needs to be 0.
+* As this is a timestep-distilled model, it benefits from fewer sampling steps.
+
+```python
+import torch
+from diffusers import FluxPipeline
+
+pipe = FluxPipeline.from_pretrained("black-forest-labs/FLUX.1-schnell", torch_dtype=torch.bfloat16)
+pipe.enable_model_cpu_offload()
+
+prompt = "A cat holding a sign that says hello world"
+out = pipe(
+    prompt=prompt,
+    guidance_scale=0.,
+    height=768,
+    width=1360,
+    num_inference_steps=4,
+    max_sequence_length=256,
+).images[0]
+out.save("image.png")
+```
+
+### Guidance-distilled
+
+* The guidance-distilled variant takes about 50 sampling steps for good-quality generation.
+* It doesn't have any limitations around the `max_sequence_length`.
+
+```python
+import torch
+from diffusers import FluxPipeline
+
+pipe = FluxPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16)
+pipe.enable_model_cpu_offload()
+
+prompt = "a tiny astronaut hatching from an egg on the moon"
+out = pipe(
+    prompt=prompt,
+    guidance_scale=3.5,
+    height=768,
+    width=1360,
+    num_inference_steps=50,
+).images[0]
+out.save("image.png")
+```
+
+## Running FP16 inference
+Flux can generate high-quality images with FP16 (i.e. to accelerate inference on Turing/Volta GPUs) but produces different outputs compared to FP32/BF16. The issue is that some activations in the text encoders have to be clipped when running in FP16, which affects the overall image. Forcing text encoders to run with FP32 inference thus removes this output difference. See [here](https://github.com/huggingface/diffusers/pull/9097#issuecomment-2272292516) for details.
+
+FP16 inference code:
+```python
+import torch
+from diffusers import FluxPipeline
+
+pipe = FluxPipeline.from_pretrained("black-forest-labs/FLUX.1-schnell", torch_dtype=torch.bfloat16) # can replace schnell with dev
+# to run on low vram GPUs (i.e. between 4 and 32 GB VRAM)
+pipe.enable_sequential_cpu_offload()
+pipe.vae.enable_slicing()
+pipe.vae.enable_tiling()
+
+pipe.to(torch.float16) # casting here instead of in the pipeline constructor because doing so in the constructor loads all models into CPU memory at once
+
+prompt = "A cat holding a sign that says hello world"
+out = pipe(
+    prompt=prompt,
+    guidance_scale=0.,
+    height=768,
+    width=1360,
+    num_inference_steps=4,
+    max_sequence_length=256,
+).images[0]
+out.save("image.png")
+```
+
+## Single File Loading for the `FluxTransformer2DModel`
+
+The `FluxTransformer2DModel` supports loading checkpoints in the original format shipped by Black Forest Labs. This is also useful when trying to load finetunes or quantized versions of the models that have been published by the community.
+
+<Tip>
+`FP8` inference can be brittle depending on the GPU type, CUDA version, and `torch` version that you are using. It is recommended that you use the `optimum-quanto` library in order to run FP8 inference on your machine.
+</Tip>
+
+The following example demonstrates how to run Flux with less than 16GB of VRAM.
+
+First install `optimum-quanto`
+
+```shell
+pip install optimum-quanto
+```
+
+Then run the following example
+
+```python
+import torch
+from diffusers import FluxTransformer2DModel, FluxPipeline
+from transformers import T5EncoderModel, CLIPTextModel
+from optimum.quanto import freeze, qfloat8, quantize
+
+bfl_repo = "black-forest-labs/FLUX.1-dev"
+dtype = torch.bfloat16
+
+transformer = FluxTransformer2DModel.from_single_file("https://huggingface.co/Kijai/flux-fp8/blob/main/flux1-dev-fp8.safetensors", torch_dtype=dtype)
+quantize(transformer, weights=qfloat8)
+freeze(transformer)
+
+text_encoder_2 = T5EncoderModel.from_pretrained(bfl_repo, subfolder="text_encoder_2", torch_dtype=dtype)
+quantize(text_encoder_2, weights=qfloat8)
+freeze(text_encoder_2)
+
+pipe = FluxPipeline.from_pretrained(bfl_repo, transformer=None, text_encoder_2=None, torch_dtype=dtype)
+pipe.transformer = transformer
+pipe.text_encoder_2 = text_encoder_2
+
+pipe.enable_model_cpu_offload()
+
+prompt = "A cat holding a sign that says hello world"
+image = pipe(
+    prompt,
+    guidance_scale=3.5,
+    output_type="pil",
+    num_inference_steps=20,
+    generator=torch.Generator("cpu").manual_seed(0)
+).images[0]
+
+image.save("flux-fp8-dev.png")
+```
+
+## FluxPipeline
+
+[[autodoc]] FluxPipeline
+	- all
+	- __call__

docs/source/en/api/pipelines/kolors.md

@@ -41,6 +41,64 @@ image = pipe(
 image.save("kolors_sample.png")
 ```
 
+### IP Adapter
+
+Kolors needs a different IP Adapter to work, and it uses [Openai-CLIP-336](https://huggingface.co/openai/clip-vit-large-patch14-336) as an image encoder.
+
+<Tip>
+
+Using an IP Adapter with Kolors requires more than 24GB of VRAM. To use it, we recommend using [`~DiffusionPipeline.enable_model_cpu_offload`] on consumer GPUs.
+
+</Tip>
+
+<Tip>
+
+While Kolors is integrated in Diffusers, you need to load the image encoder from a revision to use the safetensor files. You can still use the main branch of the original repository if you're comfortable loading pickle checkpoints.
+
+</Tip>
+
+```python
+import torch
+from transformers import CLIPVisionModelWithProjection
+
+from diffusers import DPMSolverMultistepScheduler, KolorsPipeline
+from diffusers.utils import load_image
+
+image_encoder = CLIPVisionModelWithProjection.from_pretrained(
+    "Kwai-Kolors/Kolors-IP-Adapter-Plus",
+    subfolder="image_encoder",
+    low_cpu_mem_usage=True,
+    torch_dtype=torch.float16,
+    revision="refs/pr/4",
+)
+
+pipe = KolorsPipeline.from_pretrained(
+    "Kwai-Kolors/Kolors-diffusers", image_encoder=image_encoder, torch_dtype=torch.float16, variant="fp16"
+).to("cuda")
+pipe.scheduler = DPMSolverMultistepScheduler.from_config(pipe.scheduler.config, use_karras_sigmas=True)
+
+pipe.load_ip_adapter(
+    "Kwai-Kolors/Kolors-IP-Adapter-Plus",
+    subfolder="",
+    weight_name="ip_adapter_plus_general.safetensors",
+    revision="refs/pr/4",
+    image_encoder_folder=None,
+)
+pipe.enable_model_cpu_offload()
+
+ipa_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/kolors/cat_square.png")
+
+image = pipe(
+    prompt="best quality, high quality",
+    negative_prompt="",
+    guidance_scale=6.5,
+    num_inference_steps=25,
+    ip_adapter_image=ipa_image,
+).images[0]
+
+image.save("kolors_ipa_sample.png")
+```
+
 ## KolorsPipeline
 
 [[autodoc]] KolorsPipeline

docs/source/en/api/pipelines/latte.md

@@ -0,0 +1,77 @@
+<!-- # Copyright 2024 The HuggingFace Team. All rights reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License. -->
+
+# Latte
+
+![latte text-to-video](https://github.com/Vchitect/Latte/blob/52bc0029899babbd6e9250384c83d8ed2670ff7a/visuals/latte.gif?raw=true)
+
+[Latte: Latent Diffusion Transformer for Video Generation](https://arxiv.org/abs/2401.03048) from Monash University, Shanghai AI Lab, Nanjing University, and Nanyang Technological University.
+
+The abstract from the paper is:
+
+*We propose a novel Latent Diffusion Transformer, namely Latte, for video generation. Latte first extracts spatio-temporal tokens from input videos and then adopts a series of Transformer blocks to model video distribution in the latent space. In order to model a substantial number of tokens extracted from videos, four efficient variants are introduced from the perspective of decomposing the spatial and temporal dimensions of input videos. To improve the quality of generated videos, we determine the best practices of Latte through rigorous experimental analysis, including video clip patch embedding, model variants, timestep-class information injection, temporal positional embedding, and learning strategies. Our comprehensive evaluation demonstrates that Latte achieves state-of-the-art performance across four standard video generation datasets, i.e., FaceForensics, SkyTimelapse, UCF101, and Taichi-HD. In addition, we extend Latte to text-to-video generation (T2V) task, where Latte achieves comparable results compared to recent T2V models. We strongly believe that Latte provides valuable insights for future research on incorporating Transformers into diffusion models for video generation.*
+
+**Highlights**: Latte is a latent diffusion transformer proposed as a backbone for modeling different modalities (trained for text-to-video generation here). It achieves state-of-the-art performance across four standard video benchmarks - [FaceForensics](https://arxiv.org/abs/1803.09179), [SkyTimelapse](https://arxiv.org/abs/1709.07592), [UCF101](https://arxiv.org/abs/1212.0402) and [Taichi-HD](https://arxiv.org/abs/2003.00196). To prepare and download the datasets for evaluation, please refer to [this https URL](https://github.com/Vchitect/Latte/blob/main/docs/datasets_evaluation.md).
+
+This pipeline was contributed by [maxin-cn](https://github.com/maxin-cn). The original codebase can be found [here](https://github.com/Vchitect/Latte). The original weights can be found under [hf.co/maxin-cn](https://huggingface.co/maxin-cn).
+
+<Tip>
+
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers.md) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading.md#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+
+</Tip>
+
+### Inference
+
+Use [`torch.compile`](https://huggingface.co/docs/diffusers/main/en/tutorials/fast_diffusion#torchcompile) to reduce the inference latency.
+
+First, load the pipeline:
+
+```python
+import torch
+from diffusers import LattePipeline
+
+pipeline = LattePipeline.from_pretrained(
+	"maxin-cn/Latte-1", torch_dtype=torch.float16
+).to("cuda")
+```
+
+Then change the memory layout of the pipelines `transformer` and `vae` components to `torch.channels-last`:
+
+```python
+pipeline.transformer.to(memory_format=torch.channels_last)
+pipeline.vae.to(memory_format=torch.channels_last)
+```
+
+Finally, compile the components and run inference:
+
+```python
+pipeline.transformer = torch.compile(pipeline.transformer)
+pipeline.vae.decode = torch.compile(pipeline.vae.decode)
+
+video = pipeline(prompt="A dog wearing sunglasses floating in space, surreal, nebulae in background").frames[0]
+```
+
+The [benchmark](https://gist.github.com/a-r-r-o-w/4e1694ca46374793c0361d740a99ff19) results on an 80GB A100 machine are:
+
+```
+Without torch.compile(): Average inference time: 16.246 seconds.
+With torch.compile(): Average inference time: 14.573 seconds.
+```
+
+## LattePipeline
+
+[[autodoc]] LattePipeline
+  - all
+  - __call__

docs/source/en/api/pipelines/lumina.md

@@ -43,6 +43,8 @@ Lumina-T2X has the following components:
 * It uses a Flow-based Large Diffusion Transformer as the backbone
 * It supports different any modalities with one backbone and corresponding encoder, decoder.
 
+This pipeline was contributed by [PommesPeter](https://github.com/PommesPeter). The original codebase can be found [here](https://github.com/Alpha-VLLM/Lumina-T2X). The original weights can be found under [hf.co/Alpha-VLLM](https://huggingface.co/Alpha-VLLM).
+
 <Tip>
 
 Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers.md) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading.md#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
@@ -57,7 +59,7 @@ First, load the pipeline:
 
 ```python
 from diffusers import LuminaText2ImgPipeline
-import torch 
+import torch
 
 pipeline = LuminaText2ImgPipeline.from_pretrained(
 	"Alpha-VLLM/Lumina-Next-SFT-diffusers", torch_dtype=torch.bfloat16
@@ -85,4 +87,4 @@ image = pipeline(prompt="Upper body of a young woman in a Victorian-era outfit w
 [[autodoc]] LuminaText2ImgPipeline
 	- all
 	- __call__
-	
+

docs/source/en/api/pipelines/overview.md

@@ -71,6 +71,7 @@ The table below lists all the pipelines currently available in 🤗 Diffusers an
 | [Semantic Guidance](semantic_stable_diffusion) | text2image |
 | [Shap-E](shap_e) | text-to-3D, image-to-3D |
 | [Spectrogram Diffusion](spectrogram_diffusion) |  |
+| [Stable Audio](stable_audio) | text2audio |
 | [Stable Diffusion](stable_diffusion/overview) | text2image, image2image, depth2image, inpainting, image variation, latent upscaler, super-resolution |
 | [Stable Diffusion Model Editing](model_editing) | model editing |
 | [Stable Diffusion XL](stable_diffusion/stable_diffusion_xl) | text2image, image2image, inpainting |

docs/source/en/api/pipelines/pag.md

@@ -20,6 +20,34 @@ The abstract from the paper is:
 
 *Recent studies have demonstrated that diffusion models are capable of generating high-quality samples, but their quality heavily depends on sampling guidance techniques, such as classifier guidance (CG) and classifier-free guidance (CFG). These techniques are often not applicable in unconditional generation or in various downstream tasks such as image restoration. In this paper, we propose a novel sampling guidance, called Perturbed-Attention Guidance (PAG), which improves diffusion sample quality across both unconditional and conditional settings, achieving this without requiring additional training or the integration of external modules. PAG is designed to progressively enhance the structure of samples throughout the denoising process. It involves generating intermediate samples with degraded structure by substituting selected self-attention maps in diffusion U-Net with an identity matrix, by considering the self-attention mechanisms' ability to capture structural information, and guiding the denoising process away from these degraded samples. In both ADM and Stable Diffusion, PAG surprisingly improves sample quality in conditional and even unconditional scenarios. Moreover, PAG significantly improves the baseline performance in various downstream tasks where existing guidances such as CG or CFG cannot be fully utilized, including ControlNet with empty prompts and image restoration such as inpainting and deblurring.*
 
+PAG can be used by specifying the `pag_applied_layers` as a parameter when instantiating a PAG pipeline. It can be a single string or a list of strings. Each string can be a unique layer identifier or a regular expression to identify one or more layers. 
+
+- Full identifier as a normal string: `down_blocks.2.attentions.0.transformer_blocks.0.attn1.processor`
+- Full identifier as a RegEx: `down_blocks.2.(attentions|motion_modules).0.transformer_blocks.0.attn1.processor`
+- Partial identifier as a RegEx: `down_blocks.2`, or `attn1`
+- List of identifiers (can be combo of strings and ReGex): `["blocks.1", "blocks.(14|20)", r"down_blocks\.(2,3)"]`
+
+<Tip warning={true}>
+
+Since RegEx is supported as a way for matching layer identifiers, it is crucial to use it correctly otherwise there might be unexpected behaviour. The recommended way to use PAG is by specifying layers as `blocks.{layer_index}` and `blocks.({layer_index_1|layer_index_2|...})`. Using it in any other way, while doable, may bypass our basic validation checks and give you unexpected results.
+
+</Tip>
+
+## AnimateDiffPAGPipeline
+[[autodoc]] AnimateDiffPAGPipeline
+  - all
+  - __call__
+
+## HunyuanDiTPAGPipeline
+[[autodoc]] HunyuanDiTPAGPipeline
+  - all
+  - __call__
+
+## KolorsPAGPipeline
+[[autodoc]] KolorsPAGPipeline
+  - all
+  - __call__  
+
 ## StableDiffusionPAGPipeline
 [[autodoc]] StableDiffusionPAGPipeline
 	- all
@@ -49,3 +77,15 @@ The abstract from the paper is:
 [[autodoc]] StableDiffusionXLControlNetPAGPipeline
 	- all
 	- __call__
+
+
+## StableDiffusion3PAGPipeline
+[[autodoc]] StableDiffusion3PAGPipeline
+	- all
+	- __call__
+
+
+## PixArtSigmaPAGPipeline
+[[autodoc]] PixArtSigmaPAGPipeline
+	- all
+	- __call__

docs/source/en/api/pipelines/stable_audio.md

@@ -0,0 +1,42 @@
+<!--Copyright 2024 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License.
+-->
+
+# Stable Audio
+
+Stable Audio was proposed in [Stable Audio Open](https://arxiv.org/abs/2407.14358) by Zach Evans et al. . it takes a text prompt as input and predicts the corresponding sound or music sample.
+
+Stable Audio Open generates variable-length (up to 47s) stereo audio at 44.1kHz from text prompts. It comprises three components: an autoencoder that compresses waveforms into a manageable sequence length, a T5-based text embedding for text conditioning, and a transformer-based diffusion (DiT) model that operates in the latent space of the autoencoder.
+
+Stable Audio is trained on a corpus of around 48k audio recordings, where around 47k are from Freesound and the rest are from the Free Music Archive (FMA). All audio files are licensed under CC0, CC BY, or CC Sampling+. This data is used to train the autoencoder and the DiT.
+
+The abstract of the paper is the following:
+*Open generative models are vitally important for the community, allowing for fine-tunes and serving as baselines when presenting new models. However, most current text-to-audio models are private and not accessible for artists and researchers to build upon. Here we describe the architecture and training process of a new open-weights text-to-audio model trained with Creative Commons data. Our evaluation shows that the model's performance is competitive with the state-of-the-art across various metrics. Notably, the reported FDopenl3 results (measuring the realism of the generations) showcase its potential for high-quality stereo sound synthesis at 44.1kHz.*
+
+This pipeline was contributed by [Yoach Lacombe](https://huggingface.co/ylacombe). The original codebase can be found at [Stability-AI/stable-audio-tools](https://github.com/Stability-AI/stable-audio-tools).
+
+## Tips
+
+When constructing a prompt, keep in mind:
+
+* Descriptive prompt inputs work best; use adjectives to describe the sound (for example, "high quality" or "clear") and make the prompt context specific where possible (e.g. "melodic techno with a fast beat and synths" works better than "techno").
+* Using a *negative prompt* can significantly improve the quality of the generated audio. Try using a negative prompt of "low quality, average quality".
+
+During inference:
+
+* The _quality_ of the generated audio sample can be controlled by the `num_inference_steps` argument; higher steps give higher quality audio at the expense of slower inference.
+* Multiple waveforms can be generated in one go: set `num_waveforms_per_prompt` to a value greater than 1 to enable. Automatic scoring will be performed between the generated waveforms and prompt text, and the audios ranked from best to worst accordingly.
+
+
+## StableAudioPipeline
+[[autodoc]] StableAudioPipeline
+	- all
+	- __call__

docs/source/en/api/schedulers/cosine_dpm.md

@@ -0,0 +1,24 @@
+<!--Copyright 2024 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License.
+-->
+
+# CosineDPMSolverMultistepScheduler
+
+The [`CosineDPMSolverMultistepScheduler`] is a variant of [`DPMSolverMultistepScheduler`] with cosine schedule, proposed by Nichol and Dhariwal (2021).
+It is being used in the [Stable Audio Open](https://arxiv.org/abs/2407.14358) paper and the [Stability-AI/stable-audio-tool](https://github.com/Stability-AI/stable-audio-tool) codebase.
+
+This scheduler was contributed by [Yoach Lacombe](https://huggingface.co/ylacombe).
+
+## CosineDPMSolverMultistepScheduler
+[[autodoc]] CosineDPMSolverMultistepScheduler
+
+## SchedulerOutput
+[[autodoc]] schedulers.scheduling_utils.SchedulerOutput

docs/source/en/community_projects.md

@@ -0,0 +1,78 @@
+<!--Copyright 2024 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License.
+-->
+
+# Community Projects
+
+Welcome to Community Projects. This space is dedicated to showcasing the incredible work and innovative applications created by our vibrant community using the `diffusers` library.
+
+This section aims to:
+
+- Highlight diverse and inspiring projects built with `diffusers`
+- Foster knowledge sharing within our community
+- Provide real-world examples of how `diffusers` can be leveraged
+
+Happy exploring, and thank you for being part of the Diffusers community!
+
+<table>
+    <tr>
+        <th>Project Name</th>
+        <th>Description</th>
+    </tr>
+  <tr style="border-top: 2px solid black">
+    <td><a href="https://github.com/carson-katri/dream-textures"> dream-textures </a></td>
+    <td>Stable Diffusion built-in to Blender</td>
+  </tr>
+  <tr style="border-top: 2px solid black">
+    <td><a href="https://github.com/megvii-research/HiDiffusion"> HiDiffusion </a></td>
+    <td>Increases the resolution and speed of your diffusion model by only adding a single line of code</td>
+  </tr>
+  <tr style="border-top: 2px solid black">
+    <td><a href="https://github.com/lllyasviel/IC-Light"> IC-Light </a></td>
+    <td>IC-Light is a project to manipulate the illumination of images</td>
+  </tr>
+  <tr style="border-top: 2px solid black">
+    <td><a href="https://github.com/InstantID/InstantID"> InstantID </a></td>
+    <td>InstantID : Zero-shot Identity-Preserving Generation in Seconds</td>
+  </tr>
+  <tr style="border-top: 2px solid black">
+    <td><a href="https://github.com/Sanster/IOPaint"> IOPaint </a></td>
+    <td>Image inpainting tool powered by SOTA AI Model. Remove any unwanted object, defect, people from your pictures or erase and replace(powered by stable diffusion) any thing on your pictures.</td>
+  </tr>
+  <tr style="border-top: 2px solid black">
+    <td><a href="https://github.com/bmaltais/kohya_ss"> Kohya </a></td>
+    <td>Gradio GUI for Kohya's Stable Diffusion trainers</td>
+  </tr>
+  <tr style="border-top: 2px solid black">
+    <td><a href="https://github.com/magic-research/magic-animate"> MagicAnimate </a></td>
+    <td>MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model</td>
+  </tr>
+  <tr style="border-top: 2px solid black">
+    <td><a href="https://github.com/levihsu/OOTDiffusion"> OOTDiffusion </a></td>
+    <td>Outfitting Fusion based Latent Diffusion for Controllable Virtual Try-on</td>
+  </tr>
+  <tr style="border-top: 2px solid black">
+    <td><a href="https://github.com/vladmandic/automatic"> SD.Next </a></td>
+    <td>SD.Next: Advanced Implementation of Stable Diffusion and other Diffusion-based generative image models</td>
+  </tr>
+  <tr style="border-top: 2px solid black">
+    <td><a href="https://github.com/ashawkey/stable-dreamfusion"> stable-dreamfusion </a></td>
+    <td>Text-to-3D & Image-to-3D & Mesh Exportation with NeRF + Diffusion</td>
+  </tr>
+  <tr style="border-top: 2px solid black">
+    <td><a href="https://github.com/HVision-NKU/StoryDiffusion"> StoryDiffusion </a></td>
+    <td>StoryDiffusion can create a magic story by generating consistent images and videos.</td>
+  </tr>
+  <tr style="border-top: 2px solid black">
+    <td><a href="https://github.com/cumulo-autumn/StreamDiffusion"> StreamDiffusion </a></td>
+    <td>A Pipeline-Level Solution for Real-Time Interactive Generation</td>
+  </tr>
+</table>

docs/source/en/optimization/fp16.md

@@ -125,3 +125,5 @@ image
     <figcaption class="mt-2 text-center text-sm text-gray-500">distilled Stable Diffusion + Tiny AutoEncoder</figcaption>
   </div>
 </div>
+
+More tiny autoencoder models for other Stable Diffusion models, like Stable Diffusion 3, are available from [madebyollin](https://huggingface.co/madebyollin).

docs/source/en/training/instructpix2pix.md

@@ -14,7 +14,7 @@ specific language governing permissions and limitations under the License.
 
 [InstructPix2Pix](https://hf.co/papers/2211.09800) is a Stable Diffusion model trained to edit images from human-provided instructions. For example, your prompt can be "turn the clouds rainy" and the model will edit the input image accordingly. This model is conditioned on the text prompt (or editing instruction) and the input image.
 
-This guide will explore the [train_instruct_pix2pix.py](https://github.com/huggingface/diffusers/blob/main/examples/instruct_pix2pix/train_instruct_pix2pix.py) training script to help you become familiar with it, and how you can adapt it for your own use-case.
+This guide will explore the [train_instruct_pix2pix.py](https://github.com/huggingface/diffusers/blob/main/examples/instruct_pix2pix/train_instruct_pix2pix.py) training script to help you become familiar with it, and how you can adapt it for your own use case.
 
 Before running the script, make sure you install the library from source:
 
@@ -117,7 +117,7 @@ optimizer = optimizer_cls(
 )
 ```
 
-Next, the edited images and and edit instructions are [preprocessed](https://github.com/huggingface/diffusers/blob/64603389da01082055a901f2883c4810d1144edb/examples/instruct_pix2pix/train_instruct_pix2pix.py#L624) and [tokenized](https://github.com/huggingface/diffusers/blob/64603389da01082055a901f2883c4810d1144edb/examples/instruct_pix2pix/train_instruct_pix2pix.py#L610C24-L610C24). It is important the same image transformations are applied to the original and edited images.
+Next, the edited images and edit instructions are [preprocessed](https://github.com/huggingface/diffusers/blob/64603389da01082055a901f2883c4810d1144edb/examples/instruct_pix2pix/train_instruct_pix2pix.py#L624) and [tokenized](https://github.com/huggingface/diffusers/blob/64603389da01082055a901f2883c4810d1144edb/examples/instruct_pix2pix/train_instruct_pix2pix.py#L610C24-L610C24). It is important the same image transformations are applied to the original and edited images.
 
 ```py
 def preprocess_train(examples):
@@ -249,4 +249,4 @@ The SDXL training script is discussed in more detail in the [SDXL training](sdxl
 
 Congratulations on training your own InstructPix2Pix model! 🥳 To learn more about the model, it may be helpful to:
 
-- Read the [Instruction-tuning Stable Diffusion with InstructPix2Pix](https://huggingface.co/blog/instruction-tuning-sd) blog post to learn more about some experiments we've done with InstructPix2Pix, dataset preparation, and results for different instructions.
+- Read the [Instruction-tuning Stable Diffusion with InstructPix2Pix](https://huggingface.co/blog/instruction-tuning-sd) blog post to learn more about some experiments we've done with InstructPix2Pix, dataset preparation, and results for different instructions.

docs/source/en/tutorials/basic_training.md

@@ -340,7 +340,8 @@ Now you can wrap all these components together in a training loop with 🤗 Acce
 ...                 loss = F.mse_loss(noise_pred, noise)
 ...                 accelerator.backward(loss)
 
-...                 accelerator.clip_grad_norm_(model.parameters(), 1.0)
+...                 if accelerator.sync_gradients:
+...                     accelerator.clip_grad_norm_(model.parameters(), 1.0)
 ...                 optimizer.step()
 ...                 lr_scheduler.step()
 ...                 optimizer.zero_grad()

docs/source/en/tutorials/fast_diffusion.md

@@ -35,7 +35,7 @@ pip3 install --pre torch --index-url https://download.pytorch.org/whl/nightly/cu
 ```
 
 > [!TIP]
-> The results reported below are from a 80GB 400W A100 with its clock rate set to the maximum. 
+> The results reported below are from a 80GB 400W A100 with its clock rate set to the maximum.
 > If you're interested in the full benchmarking code, take a look at [huggingface/diffusion-fast](https://github.com/huggingface/diffusion-fast).
 
 
@@ -168,7 +168,7 @@ Using SDPA attention and compiling both the UNet and VAE cuts the latency from 3
 </div>
 
 > [!TIP]
-> From PyTorch 2.3.1, you can control the caching behavior of `torch.compile()`. This is particularly beneficial for compilation modes like `"max-autotune"` which performs a grid-search over several compilation flags to find the optimal configuration. Learn more in the [Compile Time Caching in torch.compile](https://pytorch.org/tutorials/recipes/torch_compile_caching_tutorial.html) tutorial. 
+> From PyTorch 2.3.1, you can control the caching behavior of `torch.compile()`. This is particularly beneficial for compilation modes like `"max-autotune"` which performs a grid-search over several compilation flags to find the optimal configuration. Learn more in the [Compile Time Caching in torch.compile](https://pytorch.org/tutorials/recipes/torch_compile_caching_tutorial.html) tutorial.
 
 ### Prevent graph breaks
 

docs/source/en/tutorials/inference_with_big_models.md

@@ -18,13 +18,13 @@ A modern diffusion model, like [Stable Diffusion XL (SDXL)](../using-diffusers/s
 * Two text encoders
 * A UNet for denoising
 
-Usually, the text encoders and the denoiser are much larger compared to the VAE. 
+Usually, the text encoders and the denoiser are much larger compared to the VAE.
 
 As models get bigger and better, it’s possible your model is so big that even a single copy won’t fit in memory. But that doesn’t mean it can’t be loaded. If you have more than one GPU, there is more memory available to store your model. In this case, it’s better to split your model checkpoint into several smaller *checkpoint shards*.
 
 When a text encoder checkpoint has multiple shards, like [T5-xxl for SD3](https://huggingface.co/stabilityai/stable-diffusion-3-medium-diffusers/tree/main/text_encoder_3), it is automatically handled by the [Transformers](https://huggingface.co/docs/transformers/index) library as it is a required dependency of Diffusers when using the [`StableDiffusion3Pipeline`]. More specifically, Transformers will automatically handle the loading of multiple shards within the requested model class and get it ready so that inference can be performed.
 
-The denoiser checkpoint can also have multiple shards and supports inference thanks to the [Accelerate](https://huggingface.co/docs/accelerate/index) library. 
+The denoiser checkpoint can also have multiple shards and supports inference thanks to the [Accelerate](https://huggingface.co/docs/accelerate/index) library.
 
 > [!TIP]
 > Refer to the [Handling big models for inference](https://huggingface.co/docs/accelerate/main/en/concept_guides/big_model_inference) guide for general guidance when working with big models that are hard to fit into memory.
@@ -43,7 +43,7 @@ unet.save_pretrained("sdxl-unet-sharded", max_shard_size="5GB")
 The size of the fp32 variant of the SDXL UNet checkpoint is ~10.4GB. Set the `max_shard_size` parameter to 5GB to create 3 shards. After saving, you can load them in [`StableDiffusionXLPipeline`]:
 
 ```python
-from diffusers import UNet2DConditionModel, StableDiffusionXLPipeline 
+from diffusers import UNet2DConditionModel, StableDiffusionXLPipeline
 import torch
 
 unet = UNet2DConditionModel.from_pretrained(
@@ -57,14 +57,14 @@ image = pipeline("a cute dog running on the grass", num_inference_steps=30).imag
 image.save("dog.png")
 ```
 
-If placing all the model-level components on the GPU at once is not feasible, use [`~DiffusionPipeline.enable_model_cpu_offload`] to help you: 
+If placing all the model-level components on the GPU at once is not feasible, use [`~DiffusionPipeline.enable_model_cpu_offload`] to help you:
 
 ```diff
 - pipeline.to("cuda")
 + pipeline.enable_model_cpu_offload()
 ```
 
-In general, we recommend sharding when a checkpoint is more than 5GB (in fp32). 
+In general, we recommend sharding when a checkpoint is more than 5GB (in fp32).
 
 ## Device placement
 

docs/source/en/tutorials/using_peft_for_inference.md

@@ -34,7 +34,7 @@ pipe_id = "stabilityai/stable-diffusion-xl-base-1.0"
 pipe = DiffusionPipeline.from_pretrained(pipe_id, torch_dtype=torch.float16).to("cuda")
 ```
 
-Next, load a [CiroN2022/toy-face](https://huggingface.co/CiroN2022/toy-face) adapter with the [`~diffusers.loaders.StableDiffusionXLLoraLoaderMixin.load_lora_weights`] method. With the 🤗 PEFT integration, you can assign a specific `adapter_name` to the checkpoint, which let's you easily switch between different LoRA checkpoints. Let's call this adapter `"toy"`.
+Next, load a [CiroN2022/toy-face](https://huggingface.co/CiroN2022/toy-face) adapter with the [`~diffusers.loaders.StableDiffusionXLLoraLoaderMixin.load_lora_weights`] method. With the 🤗 PEFT integration, you can assign a specific `adapter_name` to the checkpoint, which lets you easily switch between different LoRA checkpoints. Let's call this adapter `"toy"`.
 
 ```python
 pipe.load_lora_weights("CiroN2022/toy-face", weight_name="toy_face_sdxl.safetensors", adapter_name="toy")
@@ -191,7 +191,7 @@ image
 
 ## Manage active adapters
 
-You have attached multiple adapters in this tutorial, and if you're feeling a bit lost on what adapters have been attached to the pipeline's components, use the [`~diffusers.loaders.LoraLoaderMixin.get_active_adapters`] method to check the list of active adapters:
+You have attached multiple adapters in this tutorial, and if you're feeling a bit lost on what adapters have been attached to the pipeline's components, use the [`~diffusers.loaders.StableDiffusionLoraLoaderMixin.get_active_adapters`] method to check the list of active adapters:
 
 ```py
 active_adapters = pipe.get_active_adapters()
@@ -199,7 +199,7 @@ active_adapters
 ["toy", "pixel"]
 ```
 
-You can also get the active adapters of each pipeline component with [`~diffusers.loaders.LoraLoaderMixin.get_list_adapters`]:
+You can also get the active adapters of each pipeline component with [`~diffusers.loaders.StableDiffusionLoraLoaderMixin.get_list_adapters`]:
 
 ```py
 list_adapters_component_wise = pipe.get_list_adapters()

docs/source/en/using-diffusers/callback.md

@@ -12,7 +12,7 @@ specific language governing permissions and limitations under the License.
 
 # Pipeline callbacks
 
-The denoising loop of a pipeline can be modified with custom defined functions using the `callback_on_step_end` parameter. The callback function is executed at the end of each step, and modifies the pipeline attributes and variables for the next step. This is really useful for *dynamically* adjusting certain pipeline attributes or modifying tensor variables. This versatility allows for interesting use-cases such as changing the prompt embeddings at each timestep, assigning different weights to the prompt embeddings, and editing the guidance scale. With callbacks, you can implement new features without modifying the underlying code!
+The denoising loop of a pipeline can be modified with custom defined functions using the `callback_on_step_end` parameter. The callback function is executed at the end of each step, and modifies the pipeline attributes and variables for the next step. This is really useful for *dynamically* adjusting certain pipeline attributes or modifying tensor variables. This versatility allows for interesting use cases such as changing the prompt embeddings at each timestep, assigning different weights to the prompt embeddings, and editing the guidance scale. With callbacks, you can implement new features without modifying the underlying code!
 
 > [!TIP]
 > 🤗 Diffusers currently only supports `callback_on_step_end`, but feel free to open a [feature request](https://github.com/huggingface/diffusers/issues/new/choose) if you have a cool use-case and require a callback function with a different execution point!
@@ -75,7 +75,7 @@ out.images[0].save("official_callback.png")
     <figcaption class="mt-2 text-center text-sm text-gray-500">without SDXLCFGCutoffCallback</figcaption>
   </div>
   <div>
-    <img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/with_cfg_callback.png" alt="generated image of a a sports car at the road with cfg callback" />
+    <img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/with_cfg_callback.png" alt="generated image of a sports car at the road with cfg callback" />
     <figcaption class="mt-2 text-center text-sm text-gray-500">with SDXLCFGCutoffCallback</figcaption>
   </div>
 </div>

docs/source/en/using-diffusers/controlnet.md

@@ -256,7 +256,7 @@ make_image_grid([init_image, mask_image, output], rows=1, cols=3)
 
 ## Guess mode
 
-[Guess mode](https://github.com/lllyasviel/ControlNet/discussions/188) does not require supplying a prompt to a ControlNet at all! This forces the ControlNet encoder to do it's best to "guess" the contents of the input control map (depth map, pose estimation, canny edge, etc.).
+[Guess mode](https://github.com/lllyasviel/ControlNet/discussions/188) does not require supplying a prompt to a ControlNet at all! This forces the ControlNet encoder to do its best to "guess" the contents of the input control map (depth map, pose estimation, canny edge, etc.).
 
 Guess mode adjusts the scale of the output residuals from a ControlNet by a fixed ratio depending on the block depth. The shallowest `DownBlock` corresponds to 0.1, and as the blocks get deeper, the scale increases exponentially such that the scale of the `MidBlock` output becomes 1.0.
 

docs/source/en/using-diffusers/custom_pipeline_overview.md

@@ -289,9 +289,9 @@ scheduler = DPMSolverMultistepScheduler.from_pretrained(pipe_id, subfolder="sche
 3. Load an image processor:
 
 ```python
-from transformers import CLIPFeatureExtractor
+from transformers import CLIPImageProcessor
 
-feature_extractor = CLIPFeatureExtractor.from_pretrained(pipe_id, subfolder="feature_extractor")
+feature_extractor = CLIPImageProcessor.from_pretrained(pipe_id, subfolder="feature_extractor")
 ```
 
 <Tip warning={true}>

docs/source/en/using-diffusers/inference_with_lcm.md

@@ -64,7 +64,7 @@ image
 </hfoption>
 <hfoption id="LCM-LoRA">
 
-To use LCM-LoRAs, you need to replace the scheduler with the [`LCMScheduler`] and load the LCM-LoRA weights with the [`~loaders.LoraLoaderMixin.load_lora_weights`] method. Then you can use the pipeline as usual, and pass a text prompt to generate an image in just 4 steps.
+To use LCM-LoRAs, you need to replace the scheduler with the [`LCMScheduler`] and load the LCM-LoRA weights with the [`~loaders.StableDiffusionLoraLoaderMixin.load_lora_weights`] method. Then you can use the pipeline as usual, and pass a text prompt to generate an image in just 4 steps.
 
 A couple of notes to keep in mind when using LCM-LoRAs are:
 
@@ -156,7 +156,7 @@ image
 </hfoption>
 <hfoption id="LCM-LoRA">
 
-To use LCM-LoRAs for image-to-image, you need to replace the scheduler with the [`LCMScheduler`] and load the LCM-LoRA weights with the [`~loaders.LoraLoaderMixin.load_lora_weights`] method. Then you can use the pipeline as usual, and pass a text prompt and initial image to generate an image in just 4 steps.
+To use LCM-LoRAs for image-to-image, you need to replace the scheduler with the [`LCMScheduler`] and load the LCM-LoRA weights with the [`~loaders.StableDiffusionLoraLoaderMixin.load_lora_weights`] method. Then you can use the pipeline as usual, and pass a text prompt and initial image to generate an image in just 4 steps.
 
 > [!TIP]
 > Experiment with different values for `num_inference_steps`, `strength`, and `guidance_scale` to get the best results.
@@ -207,7 +207,7 @@ image
 
 ## Inpainting
 
-To use LCM-LoRAs for inpainting, you need to replace the scheduler with the [`LCMScheduler`] and load the LCM-LoRA weights with the [`~loaders.LoraLoaderMixin.load_lora_weights`] method. Then you can use the pipeline as usual, and pass a text prompt, initial image, and mask image to generate an image in just 4 steps.
+To use LCM-LoRAs for inpainting, you need to replace the scheduler with the [`LCMScheduler`] and load the LCM-LoRA weights with the [`~loaders.StableDiffusionLoraLoaderMixin.load_lora_weights`] method. Then you can use the pipeline as usual, and pass a text prompt, initial image, and mask image to generate an image in just 4 steps.
 
 ```py
 import torch
@@ -262,7 +262,7 @@ LCMs are compatible with adapters like LoRA, ControlNet, T2I-Adapter, and Animat
 <hfoptions id="lcm-lora">
 <hfoption id="LCM">
 
-Load the LCM checkpoint for your supported model into [`UNet2DConditionModel`] and replace the scheduler with the [`LCMScheduler`]. Then you can use the [`~loaders.LoraLoaderMixin.load_lora_weights`] method to load the LoRA weights into the LCM and generate a styled image in a few steps.
+Load the LCM checkpoint for your supported model into [`UNet2DConditionModel`] and replace the scheduler with the [`LCMScheduler`]. Then you can use the [`~loaders.StableDiffusionLoraLoaderMixin.load_lora_weights`] method to load the LoRA weights into the LCM and generate a styled image in a few steps.
 
 ```python
 from diffusers import StableDiffusionXLPipeline, UNet2DConditionModel, LCMScheduler
@@ -294,7 +294,7 @@ image
 </hfoption>
 <hfoption id="LCM-LoRA">
 
-Replace the scheduler with the [`LCMScheduler`]. Then you can use the [`~loaders.LoraLoaderMixin.load_lora_weights`] method to load the LCM-LoRA weights and the style LoRA you want to use. Combine both LoRA adapters with the [`~loaders.UNet2DConditionLoadersMixin.set_adapters`] method and generate a styled image in a few steps.
+Replace the scheduler with the [`LCMScheduler`]. Then you can use the [`~loaders.StableDiffusionLoraLoaderMixin.load_lora_weights`] method to load the LCM-LoRA weights and the style LoRA you want to use. Combine both LoRA adapters with the [`~loaders.UNet2DConditionLoadersMixin.set_adapters`] method and generate a styled image in a few steps.
 
 ```py
 import torch
@@ -389,7 +389,7 @@ make_image_grid([canny_image, image], rows=1, cols=2)
 </hfoption>
 <hfoption id="LCM-LoRA">
 
-Load a ControlNet model trained on canny images and pass it to the [`ControlNetModel`]. Then you can load a Stable Diffusion v1.5 model into [`StableDiffusionControlNetPipeline`] and replace the scheduler with the [`LCMScheduler`]. Use the [`~loaders.LoraLoaderMixin.load_lora_weights`] method to load the LCM-LoRA weights, and pass the canny image to the pipeline and generate an image.
+Load a ControlNet model trained on canny images and pass it to the [`ControlNetModel`]. Then you can load a Stable Diffusion v1.5 model into [`StableDiffusionControlNetPipeline`] and replace the scheduler with the [`LCMScheduler`]. Use the [`~loaders.StableDiffusionLoraLoaderMixin.load_lora_weights`] method to load the LCM-LoRA weights, and pass the canny image to the pipeline and generate an image.
 
 > [!TIP]
 > Experiment with different values for `num_inference_steps`, `controlnet_conditioning_scale`, `cross_attention_kwargs`, and `guidance_scale` to get the best results.
@@ -525,7 +525,7 @@ image = pipe(
 </hfoption>
 <hfoption id="LCM-LoRA">
 
-Load a T2IAdapter trained on canny images and pass it to the [`StableDiffusionXLAdapterPipeline`]. Replace the scheduler with the [`LCMScheduler`], and use the [`~loaders.LoraLoaderMixin.load_lora_weights`] method to load the LCM-LoRA weights. Pass the canny image to the pipeline and generate an image.
+Load a T2IAdapter trained on canny images and pass it to the [`StableDiffusionXLAdapterPipeline`]. Replace the scheduler with the [`LCMScheduler`], and use the [`~loaders.StableDiffusionLoraLoaderMixin.load_lora_weights`] method to load the LCM-LoRA weights. Pass the canny image to the pipeline and generate an image.
 
 ```py
 import torch

docs/source/en/using-diffusers/inference_with_tcd_lora.md

@@ -212,14 +212,14 @@ TCD-LoRA is very versatile, and it can be combined with other adapter types like
 import torch
 import numpy as np
 from PIL import Image
-from transformers import DPTFeatureExtractor, DPTForDepthEstimation
+from transformers import DPTImageProcessor, DPTForDepthEstimation
 from diffusers import ControlNetModel, StableDiffusionXLControlNetPipeline
 from diffusers.utils import load_image, make_image_grid
 from scheduling_tcd import TCDScheduler
 
 device = "cuda"
 depth_estimator = DPTForDepthEstimation.from_pretrained("Intel/dpt-hybrid-midas").to(device)
-feature_extractor = DPTFeatureExtractor.from_pretrained("Intel/dpt-hybrid-midas")
+feature_extractor = DPTImageProcessor.from_pretrained("Intel/dpt-hybrid-midas")
 
 def get_depth_map(image):
     image = feature_extractor(images=image, return_tensors="pt").pixel_values.to(device)

docs/source/en/using-diffusers/loading_adapters.md

@@ -116,7 +116,7 @@ import torch
 pipeline = AutoPipelineForText2Image.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.float16).to("cuda")
 ```
 
-Then use the [`~loaders.LoraLoaderMixin.load_lora_weights`] method to load the [ostris/super-cereal-sdxl-lora](https://huggingface.co/ostris/super-cereal-sdxl-lora) weights and specify the weights filename from the repository:
+Then use the [`~loaders.StableDiffusionLoraLoaderMixin.load_lora_weights`] method to load the [ostris/super-cereal-sdxl-lora](https://huggingface.co/ostris/super-cereal-sdxl-lora) weights and specify the weights filename from the repository:
 
 ```py
 pipeline.load_lora_weights("ostris/super-cereal-sdxl-lora", weight_name="cereal_box_sdxl_v1.safetensors")
@@ -129,7 +129,7 @@ image
     <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/load_lora.png" />
 </div>
 
-The [`~loaders.LoraLoaderMixin.load_lora_weights`] method loads LoRA weights into both the UNet and text encoder. It is the preferred way for loading LoRAs because it can handle cases where:
+The [`~loaders.StableDiffusionLoraLoaderMixin.load_lora_weights`] method loads LoRA weights into both the UNet and text encoder. It is the preferred way for loading LoRAs because it can handle cases where:
 
 - the LoRA weights don't have separate identifiers for the UNet and text encoder
 - the LoRA weights have separate identifiers for the UNet and text encoder
@@ -153,7 +153,7 @@ image
     <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/load_attn_proc.png" />
 </div>
 
-To unload the LoRA weights, use the [`~loaders.LoraLoaderMixin.unload_lora_weights`] method to discard the LoRA weights and restore the model to its original weights:
+To unload the LoRA weights, use the [`~loaders.StableDiffusionLoraLoaderMixin.unload_lora_weights`] method to discard the LoRA weights and restore the model to its original weights:
 
 ```py
 pipeline.unload_lora_weights()
@@ -161,9 +161,9 @@ pipeline.unload_lora_weights()
 
 ### Adjust LoRA weight scale
 
-For both [`~loaders.LoraLoaderMixin.load_lora_weights`] and [`~loaders.UNet2DConditionLoadersMixin.load_attn_procs`], you can pass the `cross_attention_kwargs={"scale": 0.5}` parameter to adjust how much of the LoRA weights to use. A value of `0` is the same as only using the base model weights, and a value of `1` is equivalent to using the fully finetuned LoRA.
+For both [`~loaders.StableDiffusionLoraLoaderMixin.load_lora_weights`] and [`~loaders.UNet2DConditionLoadersMixin.load_attn_procs`], you can pass the `cross_attention_kwargs={"scale": 0.5}` parameter to adjust how much of the LoRA weights to use. A value of `0` is the same as only using the base model weights, and a value of `1` is equivalent to using the fully finetuned LoRA.
 
-For more granular control on the amount of LoRA weights used per layer, you can use [`~loaders.LoraLoaderMixin.set_adapters`] and pass a dictionary specifying by how much to scale the weights in each layer by.
+For more granular control on the amount of LoRA weights used per layer, you can use [`~loaders.StableDiffusionLoraLoaderMixin.set_adapters`] and pass a dictionary specifying by how much to scale the weights in each layer by.
 ```python
 pipe = ... # create pipeline
 pipe.load_lora_weights(..., adapter_name="my_adapter")
@@ -186,7 +186,7 @@ This also works with multiple adapters - see [this guide](https://huggingface.co
 
 <Tip warning={true}>
 
-Currently, [`~loaders.LoraLoaderMixin.set_adapters`] only supports scaling attention weights. If a LoRA has other parts (e.g., resnets or down-/upsamplers), they will keep a scale of 1.0.
+Currently, [`~loaders.StableDiffusionLoraLoaderMixin.set_adapters`] only supports scaling attention weights. If a LoRA has other parts (e.g., resnets or down-/upsamplers), they will keep a scale of 1.0.
 
 </Tip>
 
@@ -203,7 +203,7 @@ To load a Kohya LoRA, let's download the [Blueprintify SD XL 1.0](https://civita
 !wget https://civitai.com/api/download/models/168776 -O blueprintify-sd-xl-10.safetensors
 ```
 
-Load the LoRA checkpoint with the [`~loaders.LoraLoaderMixin.load_lora_weights`] method, and specify the filename in the `weight_name` parameter:
+Load the LoRA checkpoint with the [`~loaders.StableDiffusionLoraLoaderMixin.load_lora_weights`] method, and specify the filename in the `weight_name` parameter:
 
 ```py
 from diffusers import AutoPipelineForText2Image
@@ -227,7 +227,7 @@ image
 Some limitations of using Kohya LoRAs with 🤗 Diffusers include:
 
 - Images may not look like those generated by UIs - like ComfyUI - for multiple reasons, which are explained [here](https://github.com/huggingface/diffusers/pull/4287/#issuecomment-1655110736).
-- [LyCORIS checkpoints](https://github.com/KohakuBlueleaf/LyCORIS) aren't fully supported. The [`~loaders.LoraLoaderMixin.load_lora_weights`] method loads LyCORIS checkpoints with LoRA and LoCon modules, but Hada and LoKR are not supported.
+- [LyCORIS checkpoints](https://github.com/KohakuBlueleaf/LyCORIS) aren't fully supported. The [`~loaders.StableDiffusionLoraLoaderMixin.load_lora_weights`] method loads LyCORIS checkpoints with LoRA and LoCon modules, but Hada and LoKR are not supported.
 
 </Tip>
 

docs/source/en/using-diffusers/merge_loras.md

@@ -14,9 +14,9 @@ specific language governing permissions and limitations under the License.
 
 It can be fun and creative to use multiple [LoRAs]((https://huggingface.co/docs/peft/conceptual_guides/adapter#low-rank-adaptation-lora)) together to generate something entirely new and unique. This works by merging multiple LoRA weights together to produce images that are a blend of different styles. Diffusers provides a few methods to merge LoRAs depending on *how* you want to merge their weights, which can affect image quality.
 
-This guide will show you how to merge LoRAs using the [`~loaders.UNet2DConditionLoadersMixin.set_adapters`] and [`~peft.LoraModel.add_weighted_adapter`] methods. To improve inference speed and reduce memory-usage of merged LoRAs, you'll also see how to use the [`~loaders.LoraLoaderMixin.fuse_lora`] method to fuse the LoRA weights with the original weights of the underlying model.
+This guide will show you how to merge LoRAs using the [`~loaders.PeftAdapterMixin.set_adapters`] and [add_weighted_adapter](https://huggingface.co/docs/peft/package_reference/lora#peft.LoraModel.add_weighted_adapter) methods. To improve inference speed and reduce memory-usage of merged LoRAs, you'll also see how to use the [`~loaders.StableDiffusionLoraLoaderMixin.fuse_lora`] method to fuse the LoRA weights with the original weights of the underlying model.
 
-For this guide, load a Stable Diffusion XL (SDXL) checkpoint and the [KappaNeuro/studio-ghibli-style]() and [Norod78/sdxl-chalkboarddrawing-lora]() LoRAs with the [`~loaders.LoraLoaderMixin.load_lora_weights`] method. You'll need to assign each LoRA an `adapter_name` to combine them later.
+For this guide, load a Stable Diffusion XL (SDXL) checkpoint and the [KappaNeuro/studio-ghibli-style](https://huggingface.co/KappaNeuro/studio-ghibli-style) and [Norod78/sdxl-chalkboarddrawing-lora](https://huggingface.co/Norod78/sdxl-chalkboarddrawing-lora) LoRAs with the [`~loaders.StableDiffusionLoraLoaderMixin.load_lora_weights`] method. You'll need to assign each LoRA an `adapter_name` to combine them later.
 
 ```py
 from diffusers import DiffusionPipeline
@@ -29,7 +29,7 @@ pipeline.load_lora_weights("lordjia/by-feng-zikai", weight_name="fengzikai_v1.0_
 
 ## set_adapters
 
-The [`~loaders.UNet2DConditionLoadersMixin.set_adapters`] method merges LoRA adapters by concatenating their weighted matrices. Use the adapter name to specify which LoRAs to merge, and the `adapter_weights` parameter to control the scaling for each LoRA. For example, if `adapter_weights=[0.5, 0.5]`, then the merged LoRA output is an average of both LoRAs. Try adjusting the adapter weights to see how it affects the generated image!
+The [`~loaders.PeftAdapterMixin.set_adapters`] method merges LoRA adapters by concatenating their weighted matrices. Use the adapter name to specify which LoRAs to merge, and the `adapter_weights` parameter to control the scaling for each LoRA. For example, if `adapter_weights=[0.5, 0.5]`, then the merged LoRA output is an average of both LoRAs. Try adjusting the adapter weights to see how it affects the generated image!
 
 ```py
 pipeline.set_adapters(["ikea", "feng"], adapter_weights=[0.7, 0.8])
@@ -47,19 +47,19 @@ image
 ## add_weighted_adapter
 
 > [!WARNING]
-> This is an experimental method that adds PEFTs [`~peft.LoraModel.add_weighted_adapter`] method to Diffusers to enable more efficient merging methods. Check out this [issue](https://github.com/huggingface/diffusers/issues/6892) if you're interested in learning more about the motivation and design behind this integration.
+> This is an experimental method that adds PEFTs [add_weighted_adapter](https://huggingface.co/docs/peft/package_reference/lora#peft.LoraModel.add_weighted_adapter) method to Diffusers to enable more efficient merging methods. Check out this [issue](https://github.com/huggingface/diffusers/issues/6892) if you're interested in learning more about the motivation and design behind this integration.
 
-The [`~peft.LoraModel.add_weighted_adapter`] method provides access to more efficient merging method such as [TIES and DARE](https://huggingface.co/docs/peft/developer_guides/model_merging). To use these merging methods, make sure you have the latest stable version of Diffusers and PEFT installed.
+The [add_weighted_adapter](https://huggingface.co/docs/peft/package_reference/lora#peft.LoraModel.add_weighted_adapter) method provides access to more efficient merging method such as [TIES and DARE](https://huggingface.co/docs/peft/developer_guides/model_merging). To use these merging methods, make sure you have the latest stable version of Diffusers and PEFT installed.
 
 ```bash
 pip install -U diffusers peft
 ```
 
-There are three steps to merge LoRAs with the [`~peft.LoraModel.add_weighted_adapter`] method:
+There are three steps to merge LoRAs with the [add_weighted_adapter](https://huggingface.co/docs/peft/package_reference/lora#peft.LoraModel.add_weighted_adapter) method:
 
-1. Create a [`~peft.PeftModel`] from the underlying model and LoRA checkpoint.
+1. Create a [PeftModel](https://huggingface.co/docs/peft/package_reference/peft_model#peft.PeftModel) from the underlying model and LoRA checkpoint.
 2. Load a base UNet model and the LoRA adapters.
-3. Merge the adapters using the [`~peft.LoraModel.add_weighted_adapter`] method and the merging method of your choice.
+3. Merge the adapters using the [add_weighted_adapter](https://huggingface.co/docs/peft/package_reference/lora#peft.LoraModel.add_weighted_adapter) method and the merging method of your choice.
 
 Let's dive deeper into what these steps entail.
 
@@ -92,7 +92,7 @@ pipeline = DiffusionPipeline.from_pretrained(
 pipeline.load_lora_weights("ostris/ikea-instructions-lora-sdxl", weight_name="ikea_instructions_xl_v1_5.safetensors", adapter_name="ikea")
 ```
 
-Now you'll create a [`~peft.PeftModel`] from the loaded LoRA checkpoint by combining the SDXL UNet and the LoRA UNet from the pipeline.
+Now you'll create a [PeftModel](https://huggingface.co/docs/peft/package_reference/peft_model#peft.PeftModel) from the loaded LoRA checkpoint by combining the SDXL UNet and the LoRA UNet from the pipeline.
 
 ```python
 from peft import get_peft_model, LoraConfig
@@ -112,7 +112,7 @@ ikea_peft_model.load_state_dict(original_state_dict, strict=True)
 > [!TIP]
 > You can optionally push the ikea_peft_model to the Hub by calling `ikea_peft_model.push_to_hub("ikea_peft_model", token=TOKEN)`.
 
-Repeat this process to create a [`~peft.PeftModel`] from the [lordjia/by-feng-zikai](https://huggingface.co/lordjia/by-feng-zikai) LoRA.
+Repeat this process to create a [PeftModel](https://huggingface.co/docs/peft/package_reference/peft_model#peft.PeftModel) from the [lordjia/by-feng-zikai](https://huggingface.co/lordjia/by-feng-zikai) LoRA.
 
 ```python
 pipeline.delete_adapters("ikea")
@@ -148,7 +148,7 @@ model = PeftModel.from_pretrained(base_unet, "stevhliu/ikea_peft_model", use_saf
 model.load_adapter("stevhliu/feng_peft_model", use_safetensors=True, subfolder="feng", adapter_name="feng")
 ```
 
-3. Merge the adapters using the [`~peft.LoraModel.add_weighted_adapter`] method and the merging method of your choice (learn more about other merging methods in this [blog post](https://huggingface.co/blog/peft_merging)). For this example, let's use the `"dare_linear"` method to merge the LoRAs.
+3. Merge the adapters using the [add_weighted_adapter](https://huggingface.co/docs/peft/package_reference/lora#peft.LoraModel.add_weighted_adapter) method and the merging method of your choice (learn more about other merging methods in this [blog post](https://huggingface.co/blog/peft_merging)). For this example, let's use the `"dare_linear"` method to merge the LoRAs.
 
 > [!WARNING]
 > Keep in mind the LoRAs need to have the same rank to be merged!
@@ -182,9 +182,9 @@ image
 
 ## fuse_lora
 
-Both the [`~loaders.UNet2DConditionLoadersMixin.set_adapters`] and [`~peft.LoraModel.add_weighted_adapter`] methods require loading the base model and the LoRA adapters separately which incurs some overhead. The [`~loaders.LoraLoaderMixin.fuse_lora`] method allows you to fuse the LoRA weights directly with the original weights of the underlying model. This way, you're only loading the model once which can increase inference and lower memory-usage.
+Both the [`~loaders.PeftAdapterMixin.set_adapters`] and [add_weighted_adapter](https://huggingface.co/docs/peft/package_reference/lora#peft.LoraModel.add_weighted_adapter) methods require loading the base model and the LoRA adapters separately which incurs some overhead. The [`~loaders.lora_base.LoraBaseMixin.fuse_lora`] method allows you to fuse the LoRA weights directly with the original weights of the underlying model. This way, you're only loading the model once which can increase inference and lower memory-usage.
 
-You can use PEFT to easily fuse/unfuse multiple adapters directly into the model weights (both UNet and text encoder) using the [`~loaders.LoraLoaderMixin.fuse_lora`] method, which can lead to a speed-up in inference and lower VRAM usage.
+You can use PEFT to easily fuse/unfuse multiple adapters directly into the model weights (both UNet and text encoder) using the [`~loaders.lora_base.LoraBaseMixin.fuse_lora`] method, which can lead to a speed-up in inference and lower VRAM usage.
 
 For example, if you have a base model and adapters loaded and set as active with the following adapter weights:
 
@@ -199,13 +199,13 @@ pipeline.load_lora_weights("lordjia/by-feng-zikai", weight_name="fengzikai_v1.0_
 pipeline.set_adapters(["ikea", "feng"], adapter_weights=[0.7, 0.8])
 ```
 
-Fuse these LoRAs into the UNet with the [`~loaders.LoraLoaderMixin.fuse_lora`] method. The `lora_scale` parameter controls how much to scale the output by with the LoRA weights. It is important to make the `lora_scale` adjustments in the [`~loaders.LoraLoaderMixin.fuse_lora`] method because it won’t work if you try to pass `scale` to the `cross_attention_kwargs` in the pipeline.
+Fuse these LoRAs into the UNet with the [`~loaders.lora_base.LoraBaseMixin.fuse_lora`] method. The `lora_scale` parameter controls how much to scale the output by with the LoRA weights. It is important to make the `lora_scale` adjustments in the [`~loaders.lora_base.LoraBaseMixin.fuse_lora`] method because it won’t work if you try to pass `scale` to the `cross_attention_kwargs` in the pipeline.
 
 ```py
 pipeline.fuse_lora(adapter_names=["ikea", "feng"], lora_scale=1.0)
 ```
 
-Then you should use [`~loaders.LoraLoaderMixin.unload_lora_weights`] to unload the LoRA weights since they've already been fused with the underlying base model. Finally, call [`~DiffusionPipeline.save_pretrained`] to save the fused pipeline locally or you could call [`~DiffusionPipeline.push_to_hub`] to push the fused pipeline to the Hub.
+Then you should use [`~loaders.StableDiffusionLoraLoaderMixin.unload_lora_weights`] to unload the LoRA weights since they've already been fused with the underlying base model. Finally, call [`~DiffusionPipeline.save_pretrained`] to save the fused pipeline locally or you could call [`~DiffusionPipeline.push_to_hub`] to push the fused pipeline to the Hub.
 
 ```py
 pipeline.unload_lora_weights()
@@ -226,7 +226,7 @@ image = pipeline("A bowl of ramen shaped like a cute kawaii bear, by Feng Zikai"
 image
 ```
 
-You can call [`~loaders.LoraLoaderMixin.unfuse_lora`] to restore the original model's weights (for example, if you want to use a different `lora_scale` value). However, this only works if you've only fused one LoRA adapter to the original model. If you've fused multiple LoRAs, you'll need to reload the model.
+You can call [`~~loaders.lora_base.LoraBaseMixin.unfuse_lora`] to restore the original model's weights (for example, if you want to use a different `lora_scale` value). However, this only works if you've only fused one LoRA adapter to the original model. If you've fused multiple LoRAs, you'll need to reload the model.
 
 ```py
 pipeline.unfuse_lora()

docs/source/en/using-diffusers/other-formats.md

@@ -74,7 +74,7 @@ pipeline = StableDiffusionPipeline.from_single_file(
 
 [LoRA](https://hf.co/docs/peft/conceptual_guides/adapter#low-rank-adaptation-lora) is a lightweight adapter that is fast and easy to train, making them especially popular for generating images in a certain way or style. These adapters are commonly stored in a safetensors file, and are widely popular on model sharing platforms like [civitai](https://civitai.com/).
 
-LoRAs are loaded into a base model with the [`~loaders.LoraLoaderMixin.load_lora_weights`] method.
+LoRAs are loaded into a base model with the [`~loaders.StableDiffusionLoraLoaderMixin.load_lora_weights`] method.
 
 ```py
 from diffusers import StableDiffusionXLPipeline

docs/source/en/using-diffusers/pag.md

@@ -22,7 +22,7 @@ This guide will show you how to use PAG for various tasks and use cases.
 You can apply PAG to the [`StableDiffusionXLPipeline`] for tasks such as text-to-image, image-to-image, and inpainting. To enable PAG for a specific task, load the pipeline using the [AutoPipeline](../api/pipelines/auto_pipeline) API with the `enable_pag=True` flag and the `pag_applied_layers` argument.
 
 > [!TIP]
-> 🤗 Diffusers currently only supports using PAG with selected SDXL pipelines, but feel free to open a [feature request](https://github.com/huggingface/diffusers/issues/new/choose) if you want to add PAG support to a new pipeline!
+> 🤗 Diffusers currently only supports using PAG with selected SDXL pipelines and [`PixArtSigmaPAGPipeline`]. But feel free to open a [feature request](https://github.com/huggingface/diffusers/issues/new/choose) if you want to add PAG support to a new pipeline!
 
 <hfoptions id="tasks">
 <hfoption id="Text-to-image">
@@ -44,10 +44,10 @@ pipeline.enable_model_cpu_offload()
 > [!TIP]
 > The `pag_applied_layers` argument allows you to specify which layers PAG is applied to. Additionally, you can use `set_pag_applied_layers` method to update these layers after the pipeline has been created. Check out the [pag_applied_layers](#pag_applied_layers) section to learn more about applying PAG to other layers.
 
-If you already have a pipeline created and loaded, you can enable PAG on it using the `from_pipe` API with the `enable_pag` flag. Internally, a PAG pipeline is created based on the pipeline and task you specified. In the example below, since we used `AutoPipelineForText2Image` and passed a `StableDiffusionXLPipeline`, a `StableDiffusionXLPAGPipeline` is created accordingly. Note that this does not require additional memory, and you will have both `StableDiffusionXLPipeline` and  `StableDiffusionXLPAGPipeline` loaded and ready to use. You can read more about the `from_pipe` API and how to reuse pipelines in diffuser[here](https://huggingface.co/docs/diffusers/using-diffusers/loading#reuse-a-pipeline)
+If you already have a pipeline created and loaded, you can enable PAG on it using the `from_pipe` API with the `enable_pag` flag. Internally, a PAG pipeline is created based on the pipeline and task you specified. In the example below, since we used `AutoPipelineForText2Image` and passed a `StableDiffusionXLPipeline`, a `StableDiffusionXLPAGPipeline` is created accordingly. Note that this does not require additional memory, and you will have both `StableDiffusionXLPipeline` and  `StableDiffusionXLPAGPipeline` loaded and ready to use. You can read more about the `from_pipe` API and how to reuse pipelines in diffuser [here](https://huggingface.co/docs/diffusers/using-diffusers/loading#reuse-a-pipeline).
 
 ```py
-pipeline_sdxl = AutoPipelineForText2Image.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0, torch_dtype=torch.float16")
+pipeline_sdxl = AutoPipelineForText2Image.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.float16)
 pipeline = AutoPipelineForText2Image.from_pipe(pipeline_sdxl, enable_pag=True)
 ```
 
@@ -130,10 +130,10 @@ prompt = "a dog catching a frisbee in the jungle"
 
 generator = torch.Generator(device="cpu").manual_seed(0)
 image = pipeline(
-    prompt, 
-    image=init_image, 
-    strength=0.8, 
-    guidance_scale=guidance_scale, 
+    prompt,
+    image=init_image,
+    strength=0.8,
+    guidance_scale=guidance_scale,
     pag_scale=pag_scale,
     generator=generator).images[0]
 ```
@@ -161,14 +161,14 @@ pipeline_inpaint = AutoPipelineForInpaiting.from_pretrained("stabilityai/stable-
 pipeline = AutoPipelineForInpaiting.from_pipe(pipeline_inpaint, enable_pag=True)
 ```
 
-This still works when your pipeline has a different task: 
+This still works when your pipeline has a different task:
 
 ```py
 pipeline_t2i = AutoPipelineForText2Image.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.float16)
 pipeline = AutoPipelineForInpaiting.from_pipe(pipeline_t2i, enable_pag=True)
 ```
 
-Let's generate an image! 
+Let's generate an image!
 
 ```py
 img_url = "https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo.png"
@@ -258,7 +258,7 @@ for pag_scale in [0.0, 3.0]:
   </div>
 </div>
 
-## PAG with IP-Adapter 
+## PAG with IP-Adapter
 
 [IP-Adapter](https://hf.co/papers/2308.06721) is a popular model that can be plugged into diffusion models to enable image prompting without any changes to the underlying model. You can enable PAG on a pipeline with IP-Adapter loaded.
 
@@ -317,7 +317,7 @@ PAG reduces artifacts and improves the overall compposition.
 </div>
 
 
-## Configure parameters 
+## Configure parameters
 
 ### pag_applied_layers
 

docs/source/en/using-diffusers/shap-e.md

@@ -52,7 +52,7 @@ images = pipe(
 ).images
 ```
 
-Now use the [`~utils.export_to_gif`] function to turn the list of image frames into a gif of the 3D object.
+이제 [`~utils.export_to_gif`] 함수를 사용해 이미지 프레임 리스트를 3D 오브젝트의 gif로 변환합니다.
 
 ```py
 from diffusers.utils import export_to_gif

docs/source/en/using-diffusers/svd.md

@@ -21,6 +21,7 @@ This guide will show you how to use SVD to generate short videos from images.
 Before you begin, make sure you have the following libraries installed:
 
 ```py
+# Colab에서 필요한 라이브러리를 설치하기 위해 주석을 제외하세요
 !pip install -q -U diffusers transformers accelerate
 ```
 

docs/source/ko/_toctree.yml

@@ -1,121 +1,183 @@
 - sections:
   - local: index
-    title: "🧨 Diffusers"
+    title: 🧨 Diffusers
   - local: quicktour
     title: "훑어보기"
   - local: stable_diffusion
     title: Stable Diffusion
   - local: installation
-    title: "설치"
-  title: "시작하기"
+    title: 설치
+  title: 시작하기
 - sections:
   - local: tutorials/tutorial_overview
     title: 개요
   - local: using-diffusers/write_own_pipeline
     title: 모델과 스케줄러 이해하기
-  - local: in_translation
-    title: AutoPipeline
+  - local: in_translation # tutorials/autopipeline
+    title: (번역중) AutoPipeline
   - local: tutorials/basic_training
     title: Diffusion 모델 학습하기
-  title: Tutorials
+  - local: in_translation # tutorials/using_peft_for_inference
+    title: (번역중) 추론을 위한 LoRAs 불러오기
+  - local: in_translation # tutorials/fast_diffusion
+    title: (번역중) Text-to-image diffusion 모델 추론 가속화하기
+  - local: in_translation  # tutorials/inference_with_big_models
+    title: (번역중) 큰 모델로 작업하기
+  title: 튜토리얼
 - sections:
-  - sections:
-    - local: using-diffusers/loading_overview
-      title: 개요
-    - local: using-diffusers/loading
-      title: 파이프라인, 모델, 스케줄러 불러오기
-    - local: using-diffusers/schedulers
-      title: 다른 스케줄러들을 가져오고 비교하기
-    - local: using-diffusers/custom_pipeline_overview
-      title: 커뮤니티 파이프라인 불러오기
-    - local: using-diffusers/using_safetensors
-      title: 세이프텐서 불러오기
-    - local: using-diffusers/other-formats
-      title: 다른 형식의 Stable Diffusion 불러오기
-    - local: in_translation
-      title: Hub에 파일 push하기
-    title: 불러오기 & 허브
-  - sections:
-    - local: using-diffusers/pipeline_overview
-      title: 개요
-    - local: using-diffusers/unconditional_image_generation
-      title: Unconditional 이미지 생성
-    - local: using-diffusers/conditional_image_generation
-      title: Text-to-image 생성
-    - local: using-diffusers/img2img
-      title: Text-guided image-to-image
-    - local: using-diffusers/inpaint
-      title: Text-guided 이미지 인페인팅
-    - local: using-diffusers/depth2img
-      title: Text-guided depth-to-image
-    - local: using-diffusers/textual_inversion_inference
-      title: Textual inversion
-    - local: training/distributed_inference
-      title: 여러 GPU를 사용한 분산 추론
-    - local: in_translation
-      title: Distilled Stable Diffusion 추론
-    - local: using-diffusers/reusing_seeds
-      title: Deterministic 생성으로 이미지 퀄리티 높이기
-    - local: using-diffusers/control_brightness
-      title: 이미지 밝기 조정하기
-    - local: using-diffusers/reproducibility
-      title: 재현 가능한 파이프라인 생성하기
-    - local: using-diffusers/custom_pipeline_examples
-      title: 커뮤니티 파이프라인들
-    - local: using-diffusers/contribute_pipeline
-      title: 커뮤티니 파이프라인에 기여하는 방법
-    - local: using-diffusers/stable_diffusion_jax_how_to
-      title: JAX/Flax에서의 Stable Diffusion
-    - local: using-diffusers/weighted_prompts
-      title: Weighting Prompts
-    title: 추론을 위한 파이프라인
-  - sections:
-    - local: training/overview
-      title: 개요
-    - local: training/create_dataset
-      title: 학습을 위한 데이터셋 생성하기
-    - local: training/adapt_a_model
-      title: 새로운 태스크에 모델 적용하기
+  - local: using-diffusers/loading
+    title: 파이프라인 불러오기
+  - local: using-diffusers/custom_pipeline_overview
+    title: 커뮤니티 파이프라인과 컴포넌트 불러오기
+  - local: using-diffusers/schedulers
+    title: 스케줄러와 모델 불러오기
+  - local: using-diffusers/other-formats
+    title: 모델 파일과 레이아웃
+  - local: using-diffusers/loading_adapters
+    title: 어댑터 불러오기
+  - local: using-diffusers/push_to_hub
+    title: 파일들을 Hub로 푸시하기
+  title: 파이프라인과 어댑터 불러오기
+- sections:
+  - local: using-diffusers/unconditional_image_generation
+    title: Unconditional 이미지 생성
+  - local: using-diffusers/conditional_image_generation
+    title: Text-to-image
+  - local: using-diffusers/img2img
+    title: Image-to-image
+  - local: using-diffusers/inpaint
+    title: 인페인팅
+  - local: in_translation # using-diffusers/text-img2vid
+    title: (번역중) Text 또는 image-to-video
+  - local: using-diffusers/depth2img
+    title: Depth-to-image
+  title: 생성 태스크
+- sections:
+  - local: in_translation # using-diffusers/overview_techniques
+    title: (번역중) 개요
+  - local: training/distributed_inference
+    title: 여러 GPU를 사용한 분산 추론
+  - local: in_translation # using-diffusers/merge_loras
+    title: (번역중) LoRA 병합
+  - local: in_translation # using-diffusers/scheduler_features
+    title: (번역중) 스케줄러 기능
+  - local: in_translation # using-diffusers/callback
+    title: (번역중) 파이프라인 콜백
+  - local: in_translation # using-diffusers/reusing_seeds
+    title: (번역중) 재현 가능한 파이프라인
+  - local: in_translation # using-diffusers/image_quality
+    title: (번역중) 이미지 퀄리티 조절하기
+  - local: using-diffusers/weighted_prompts
+    title: 프롬프트 기술
+  title: 추론 테크닉
+- sections:
+  - local: in_translation # advanced_inference/outpaint
+    title: (번역중) Outpainting
+  title: 추론 심화
+- sections:
+  - local: in_translation # using-diffusers/sdxl
+    title: (번역중) Stable Diffusion XL
+  - local: using-diffusers/sdxl_turbo
+    title: SDXL Turbo
+  - local: using-diffusers/kandinsky
+    title: Kandinsky
+  - local: in_translation # using-diffusers/ip_adapter
+    title: (번역중) IP-Adapter
+  - local: in_translation # using-diffusers/pag
+    title: (번역중) PAG
+  - local: in_translation # using-diffusers/controlnet
+    title: (번역중) ControlNet
+  - local: in_translation # using-diffusers/t2i_adapter
+    title: (번역중) T2I-Adapter
+  - local: in_translation # using-diffusers/inference_with_lcm
+    title: (번역중) Latent Consistency Model
+  - local: using-diffusers/textual_inversion_inference
+    title: Textual inversion
+  - local: using-diffusers/shap-e
+    title: Shap-E
+  - local: using-diffusers/diffedit
+    title: DiffEdit
+  - local: in_translation # using-diffusers/inference_with_tcd_lora
+    title: (번역중) Trajectory Consistency Distillation-LoRA
+  - local: using-diffusers/svd
+    title: Stable Video Diffusion
+  - local: in_translation # using-diffusers/marigold_usage
+    title: (번역중) Marigold 컴퓨터 비전
+  title: 특정 파이프라인 예시
+- sections:
+  - local: training/overview
+    title: 개요
+  - local: training/create_dataset
+    title: 학습을 위한 데이터셋 생성하기
+  - local: training/adapt_a_model
+    title: 새로운 태스크에 모델 적용하기
+  - isExpanded: false
+    sections:
     - local: training/unconditional_training
       title: Unconditional 이미지 생성
+    - local: training/text2image
+      title: Text-to-image
+    - local: in_translation # training/sdxl
+      title: (번역중) Stable Diffusion XL
+    - local: in_translation # training/kandinsky
+      title: (번역중) Kandinsky 2.2
+    - local: in_translation # training/wuerstchen
+      title: (번역중) Wuerstchen
+    - local: training/controlnet
+      title: ControlNet
+    - local: in_translation # training/t2i_adapters
+      title: (번역중) T2I-Adapters
+    - local: training/instructpix2pix
+      title: InstructPix2Pix
+    title: 모델
+  - isExpanded: false
+    sections:
     - local: training/text_inversion
       title: Textual Inversion
     - local: training/dreambooth
       title: DreamBooth
-    - local: training/text2image
-      title: Text-to-image
     - local: training/lora
-      title: Low-Rank Adaptation of Large Language Models (LoRA)
-    - local: training/controlnet
-      title: ControlNet
-    - local: training/instructpix2pix
-      title: InstructPix2Pix 학습
+      title: LoRA
     - local: training/custom_diffusion
       title: Custom Diffusion
-    title: Training
-  title: Diffusers 사용하기
+    - local: in_translation # training/lcm_distill
+      title: (번역중) Latent Consistency Distillation
+    - local: in_translation # training/ddpo
+      title: (번역중) DDPO 강화학습 훈련
+    title: 메서드
+  title: 학습
 - sections:
-  - local: optimization/opt_overview
-    title: 개요
   - local: optimization/fp16
-    title: 메모리와 속도
+    title: 추론 스피드업
+  - local: in_translation # optimization/memory
+    title: (번역중) 메모리 사용량 줄이기
   - local: optimization/torch2.0
-    title: Torch2.0 지원
+    title: PyTorch 2.0
   - local: optimization/xformers
     title: xFormers
-  - local: optimization/onnx
-    title: ONNX
-  - local: optimization/open_vino
-    title: OpenVINO
-  - local: optimization/coreml
-    title: Core ML
-  - local: optimization/mps
-    title: MPS
-  - local: optimization/habana
-    title: Habana Gaudi
   - local: optimization/tome
-    title: Token Merging
-  title: 최적화/특수 하드웨어
+    title: Token merging
+  - local: in_translation # optimization/deepcache
+    title: (번역중) DeepCache
+  - local: in_translation # optimization/tgate
+    title: (번역중) TGATE
+  - sections:
+    - local: using-diffusers/stable_diffusion_jax_how_to
+      title: JAX/Flax
+    - local: optimization/onnx
+      title: ONNX
+    - local: optimization/open_vino
+      title: OpenVINO
+    - local: optimization/coreml
+      title: Core ML
+    title: 최적화된 모델 형식
+  - sections:
+    - local: optimization/mps
+      title: Metal Performance Shaders (MPS)
+    - local: optimization/habana
+      title: Habana Gaudi
+    title: 최적화된 하드웨어
+  title: 추론 가속화와 메모리 줄이기
 - sections:
   - local: conceptual/philosophy
     title: 철학

docs/source/ko/conceptual/ethical_guidelines.md

@@ -10,26 +10,27 @@ an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express o
 specific language governing permissions and limitations under the License.
 -->
 
-# 🧨 Diffusers의 윤리 지침
+# 🧨 Diffusers의 윤리 지침 [[-diffusers-ethical-guidelines]]
 
-## 서문
+## 서문 [[preamble]]
 
 [Diffusers](https://huggingface.co/docs/diffusers/index)는 사전 훈련된 diffusion 모델을 제공하며 추론 및 훈련을 위한 모듈식 툴박스로 사용됩니다.
 
 이 기술의 실제 적용과 사회에 미칠 수 있는 부정적인 영향을 고려하여 Diffusers 라이브러리의 개발, 사용자 기여 및 사용에 윤리 지침을 제공하는 것이 중요하다고 생각합니다.
 
-이 기술을 사용하는 데 연관된 위험은 아직 조사 중이지만, 몇 가지 예를 들면: 예술가들에 대한 저작권 문제; 딥 페이크의 악용; 부적절한 맥락에서의 성적 콘텐츠 생성; 동의 없는 impersonation; 사회적인 편견으로 인해 억압되는 그룹들에 대한 해로운 영향입니다.
+이이 기술을 사용함에 따른 위험은 여전히 검토 중이지만, 몇 가지 예를 들면: 예술가들에 대한 저작권 문제; 딥 페이크의 악용; 부적절한 맥락에서의 성적 콘텐츠 생성; 동의 없는 사칭; 소수자 집단의 억압을 영속화하는 유해한 사회적 편견 등이 있습니다.
+
 우리는 위험을 지속적으로 추적하고 커뮤니티의 응답과 소중한 피드백에 따라 다음 지침을 조정할 것입니다.
 
 
-## 범위
+## 범위 [[scope]]
 
 Diffusers 커뮤니티는 프로젝트의 개발에 다음과 같은 윤리 지침을 적용하며, 특히 윤리적 문제와 관련된 민감한 주제에 대한 커뮤니티의 기여를 조정하는 데 도움을 줄 것입니다.
 
 
-## 윤리 지침
+## 윤리 지침 [[ethical-guidelines]]
 
-다음 윤리 지침은 일반적으로 적용되지만, 기술적 선택을 할 때 윤리적으로 민감한 문제를 다룰 때 주로 적용할 것입니다. 또한, 해당 기술의 최신 동향과 관련된 신규 위험에 따라 시간이 지남에 따라 이러한 윤리 원칙을 조정할 것을 약속합니다.
+다음 윤리 지침은 일반적으로 적용되지만, 민감한 윤리적 문제와 관련하여 기술적 선택을 할 때 이를 우선적으로 적용할 것입니다. 나아가, 해당 기술의 최신 동향과 관련된 새로운 위험이 발생함에 따라 이러한 윤리 원칙을 조정할 것을 약속드립니다.
 
 - **투명성**: 우리는 PR을 관리하고, 사용자에게 우리의 선택을 설명하며, 기술적 의사결정을 내릴 때 투명성을 유지할 것을 약속합니다.
 
@@ -44,7 +45,7 @@ Diffusers 커뮤니티는 프로젝트의 개발에 다음과 같은 윤리 지
 - **책임**: 우리는 커뮤니티와 팀워크를 통해, 이 기술의 잠재적인 위험과 위험을 예측하고 완화하는 데 대한 공동 책임을 가지고 있습니다.
 
 
-## 구현 사례: 안전 기능과 메커니즘
+## 구현 사례: 안전 기능과 메커니즘 [[examples-of-implementations-safety-features-and-mechanisms]]
 
 팀은 diffusion 기술과 관련된 잠재적인 윤리 및 사회적 위험에 대처하기 위한 기술적 및 비기술적 도구를 제공하고자 하고 있습니다. 또한, 커뮤니티의 참여는 이러한 기능의 구현하고 우리와 함께 인식을 높이는 데 매우 중요합니다.
 

docs/source/ko/conceptual/philosophy.md

@@ -10,7 +10,7 @@ an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express o
 specific language governing permissions and limitations under the License.
 -->
 
-# 철학 [[philosophy]] 
+# 철학 [[philosophy]]
 
 🧨 Diffusers는 다양한 모달리티에서 **최신의** 사전 훈련된 diffusion 모델을 제공합니다.
 그 목적은 추론과 훈련을 위한 **모듈식 툴박스**로 사용되는 것입니다.

docs/source/ko/index.md

@@ -46,52 +46,4 @@ specific language governing permissions and limitations under the License.
       <p class="text-gray-700">🤗 Diffusers 클래스 및 메서드의 작동 방식에 대한 기술 설명.</p>
     </a>
   </div>
-</div>
-
-## Supported pipelines
-
-| Pipeline | Paper/Repository | Tasks |
-|---|---|:---:|
-| [alt_diffusion](./api/pipelines/alt_diffusion) | [AltCLIP: Altering the Language Encoder in CLIP for Extended Language Capabilities](https://arxiv.org/abs/2211.06679) | Image-to-Image Text-Guided Generation |
-| [audio_diffusion](./api/pipelines/audio_diffusion) | [Audio Diffusion](https://github.com/teticio/audio-diffusion.git) | Unconditional Audio Generation |
-| [controlnet](./api/pipelines/stable_diffusion/controlnet) | [Adding Conditional Control to Text-to-Image Diffusion Models](https://arxiv.org/abs/2302.05543) | Image-to-Image Text-Guided Generation |
-| [cycle_diffusion](./api/pipelines/cycle_diffusion) | [Unifying Diffusion Models' Latent Space, with Applications to CycleDiffusion and Guidance](https://arxiv.org/abs/2210.05559) | Image-to-Image Text-Guided Generation |
-| [dance_diffusion](./api/pipelines/dance_diffusion) | [Dance Diffusion](https://github.com/williamberman/diffusers.git) | Unconditional Audio Generation |
-| [ddpm](./api/pipelines/ddpm) | [Denoising Diffusion Probabilistic Models](https://arxiv.org/abs/2006.11239) | Unconditional Image Generation |
-| [ddim](./api/pipelines/ddim) | [Denoising Diffusion Implicit Models](https://arxiv.org/abs/2010.02502) | Unconditional Image Generation |
-| [if](./if) | [**IF**](./api/pipelines/if) | Image Generation |
-| [if_img2img](./if) | [**IF**](./api/pipelines/if) | Image-to-Image Generation |
-| [if_inpainting](./if) | [**IF**](./api/pipelines/if) | Image-to-Image Generation |
-| [latent_diffusion](./api/pipelines/latent_diffusion) | [High-Resolution Image Synthesis with Latent Diffusion Models](https://arxiv.org/abs/2112.10752)| Text-to-Image Generation |
-| [latent_diffusion](./api/pipelines/latent_diffusion) | [High-Resolution Image Synthesis with Latent Diffusion Models](https://arxiv.org/abs/2112.10752)| Super Resolution Image-to-Image |
-| [latent_diffusion_uncond](./api/pipelines/latent_diffusion_uncond) | [High-Resolution Image Synthesis with Latent Diffusion Models](https://arxiv.org/abs/2112.10752) | Unconditional Image Generation |
-| [paint_by_example](./api/pipelines/paint_by_example) | [Paint by Example: Exemplar-based Image Editing with Diffusion Models](https://arxiv.org/abs/2211.13227) | Image-Guided Image Inpainting |
-| [pndm](./api/pipelines/pndm) | [Pseudo Numerical Methods for Diffusion Models on Manifolds](https://arxiv.org/abs/2202.09778) | Unconditional Image Generation |
-| [score_sde_ve](./api/pipelines/score_sde_ve) | [Score-Based Generative Modeling through Stochastic Differential Equations](https://openreview.net/forum?id=PxTIG12RRHS) | Unconditional Image Generation |
-| [score_sde_vp](./api/pipelines/score_sde_vp) | [Score-Based Generative Modeling through Stochastic Differential Equations](https://openreview.net/forum?id=PxTIG12RRHS) | Unconditional Image Generation |
-| [semantic_stable_diffusion](./api/pipelines/semantic_stable_diffusion) | [Semantic Guidance](https://arxiv.org/abs/2301.12247) | Text-Guided Generation |
-| [stable_diffusion_text2img](./api/pipelines/stable_diffusion/text2img) | [Stable Diffusion](https://stability.ai/blog/stable-diffusion-public-release) | Text-to-Image Generation |
-| [stable_diffusion_img2img](./api/pipelines/stable_diffusion/img2img) | [Stable Diffusion](https://stability.ai/blog/stable-diffusion-public-release) | Image-to-Image Text-Guided Generation |
-| [stable_diffusion_inpaint](./api/pipelines/stable_diffusion/inpaint) | [Stable Diffusion](https://stability.ai/blog/stable-diffusion-public-release) | Text-Guided Image Inpainting |
-| [stable_diffusion_panorama](./api/pipelines/stable_diffusion/panorama) | [MultiDiffusion](https://multidiffusion.github.io/) | Text-to-Panorama Generation |
-| [stable_diffusion_pix2pix](./api/pipelines/stable_diffusion/pix2pix) | [InstructPix2Pix: Learning to Follow Image Editing Instructions](https://arxiv.org/abs/2211.09800)  | Text-Guided Image Editing|
-| [stable_diffusion_pix2pix_zero](./api/pipelines/stable_diffusion/pix2pix_zero) | [Zero-shot Image-to-Image Translation](https://pix2pixzero.github.io/) | Text-Guided Image Editing |
-| [stable_diffusion_attend_and_excite](./api/pipelines/stable_diffusion/attend_and_excite) | [Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models](https://arxiv.org/abs/2301.13826) | Text-to-Image Generation |
-| [stable_diffusion_self_attention_guidance](./api/pipelines/stable_diffusion/self_attention_guidance) | [Improving Sample Quality of Diffusion Models Using Self-Attention Guidance](https://arxiv.org/abs/2210.00939) | Text-to-Image Generation Unconditional Image Generation |
-| [stable_diffusion_image_variation](./stable_diffusion/image_variation) | [Stable Diffusion Image Variations](https://github.com/LambdaLabsML/lambda-diffusers#stable-diffusion-image-variations) | Image-to-Image Generation |
-| [stable_diffusion_latent_upscale](./stable_diffusion/latent_upscale) | [Stable Diffusion Latent Upscaler](https://twitter.com/StabilityAI/status/1590531958815064065) | Text-Guided Super Resolution Image-to-Image |
-| [stable_diffusion_model_editing](./api/pipelines/stable_diffusion/model_editing) | [Editing Implicit Assumptions in Text-to-Image Diffusion Models](https://time-diffusion.github.io/) | Text-to-Image Model Editing |
-| [stable_diffusion_2](./api/pipelines/stable_diffusion_2) | [Stable Diffusion 2](https://stability.ai/blog/stable-diffusion-v2-release) | Text-to-Image Generation |
-| [stable_diffusion_2](./api/pipelines/stable_diffusion_2) | [Stable Diffusion 2](https://stability.ai/blog/stable-diffusion-v2-release) | Text-Guided Image Inpainting |
-| [stable_diffusion_2](./api/pipelines/stable_diffusion_2) | [Depth-Conditional Stable Diffusion](https://github.com/Stability-AI/stablediffusion#depth-conditional-stable-diffusion) | Depth-to-Image Generation |
-| [stable_diffusion_2](./api/pipelines/stable_diffusion_2) | [Stable Diffusion 2](https://stability.ai/blog/stable-diffusion-v2-release) | Text-Guided Super Resolution Image-to-Image |
-| [stable_diffusion_safe](./api/pipelines/stable_diffusion_safe) | [Safe Stable Diffusion](https://arxiv.org/abs/2211.05105) | Text-Guided Generation |
-| [stable_unclip](./stable_unclip) | Stable unCLIP | Text-to-Image Generation |
-| [stable_unclip](./stable_unclip) | Stable unCLIP | Image-to-Image Text-Guided Generation |
-| [stochastic_karras_ve](./api/pipelines/stochastic_karras_ve) | [Elucidating the Design Space of Diffusion-Based Generative Models](https://arxiv.org/abs/2206.00364) | Unconditional Image Generation |
-| [text_to_video_sd](./api/pipelines/text_to_video) | [Modelscope's Text-to-video-synthesis Model in Open Domain](https://modelscope.cn/models/damo/text-to-video-synthesis/summary) | Text-to-Video Generation |
-| [unclip](./api/pipelines/unclip) | [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://arxiv.org/abs/2204.06125)(implementation by [kakaobrain](https://github.com/kakaobrain/karlo)) | Text-to-Image Generation |
-| [versatile_diffusion](./api/pipelines/versatile_diffusion) | [Versatile Diffusion: Text, Images and Variations All in One Diffusion Model](https://arxiv.org/abs/2211.08332) | Text-to-Image Generation |
-| [versatile_diffusion](./api/pipelines/versatile_diffusion) | [Versatile Diffusion: Text, Images and Variations All in One Diffusion Model](https://arxiv.org/abs/2211.08332) | Image Variations Generation |
-| [versatile_diffusion](./api/pipelines/versatile_diffusion) | [Versatile Diffusion: Text, Images and Variations All in One Diffusion Model](https://arxiv.org/abs/2211.08332) | Dual Image and Text Guided Generation |
-| [vq_diffusion](./api/pipelines/vq_diffusion) | [Vector Quantized Diffusion Model for Text-to-Image Synthesis](https://arxiv.org/abs/2111.14822) | Text-to-Image Generation |
+</div>

docs/source/ko/optimization/opt_overview.md

@@ -1,17 +0,0 @@
-<!--Copyright 2024 The HuggingFace Team. All rights reserved.
-
-Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
-the License. You may obtain a copy of the License at
-
-http://www.apache.org/licenses/LICENSE-2.0
-
-Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
-an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
-specific language governing permissions and limitations under the License.
--->
-
-# 개요
-
-노이즈가 많은 출력에서 적은 출력으로 만드는 과정으로 고품질 생성 모델의 출력을 만드는 각각의 반복되는 스텝은 많은 계산이 필요합니다. 🧨 Diffuser의 목표 중 하나는 모든 사람이 이 기술을 널리 이용할 수 있도록 하는 것이며, 여기에는 소비자 및 특수 하드웨어에서 빠른 추론을 가능하게 하는 것을 포함합니다.
-
-이 섹션에서는 추론 속도를 최적화하고 메모리 소비를 줄이기 위한 반정밀(half-precision) 가중치 및 sliced attention과 같은 팁과 요령을 다룹니다. 또한 [`torch.compile`](https://pytorch.org/tutorials/intermediate/torch_compile_tutorial.html) 또는 [ONNX Runtime](https://onnxruntime.ai/docs/)을 사용하여 PyTorch 코드의 속도를 높이고, [xFormers](https://facebookresearch.github.io/xformers/)를 사용하여 memory-efficient attention을 활성화하는 방법을 배울 수 있습니다. Apple Silicon, Intel 또는 Habana 프로세서와 같은 특정 하드웨어에서 추론을 실행하기 위한 가이드도 있습니다.

docs/source/ko/quicktour.md

@@ -15,7 +15,7 @@ specific language governing permissions and limitations under the License.
 
 Diffusion 모델은 이미지나 오디오와 같은 관심 샘플들을 생성하기 위해 랜덤 가우시안 노이즈를 단계별로 제거하도록 학습됩니다. 이로 인해 생성 AI에 대한 관심이 매우 높아졌으며, 인터넷에서 diffusion 생성 이미지의 예를 본 적이 있을 것입니다. 🧨 Diffusers는 누구나 diffusion 모델들을 널리 이용할 수 있도록 하기 위한 라이브러리입니다.
 
-개발자든 일반 사용자든 이 훑어보기를 통해 🧨 diffusers를 소개하고 빠르게 생성할 수 있도록 도와드립니다! 알아야 할 라이브러리의 주요 구성 요소는 크게 세 가지입니다:
+개발자든 일반 사용자든 이 훑어보기를 통해 🧨 Diffusers를 소개하고 빠르게 생성할 수 있도록 도와드립니다! 알아야 할 라이브러리의 주요 구성 요소는 크게 세 가지입니다:
 
 * [`DiffusionPipeline`]은 추론을 위해 사전 학습된 diffusion 모델에서 샘플을 빠르게 생성하도록 설계된 높은 수준의 엔드투엔드 클래스입니다.
 * Diffusion 시스템 생성을 위한 빌딩 블록으로 사용할 수 있는 널리 사용되는 사전 학습된 [model](./api/models) 아키텍처 및 모듈.

docs/source/ko/using-diffusers/contribute_pipeline.md

@@ -1,182 +0,0 @@
-<!--Copyright 2024 The HuggingFace Team. All rights reserved.
-
-Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
-the License. You may obtain a copy of the License at
-
-http://www.apache.org/licenses/LICENSE-2.0
-
-Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
-an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
-specific language governing permissions and limitations under the License.
--->
-
-# 커뮤니티 파이프라인에 기여하는 방법
-
-<Tip>
-
-💡 모든 사람이 속도 저하 없이 쉽게 작업을 공유할 수 있도록 커뮤니티 파이프라인을 추가하는 이유에 대한 자세한 내용은 GitHub 이슈 [#841](https://github.com/huggingface/diffusers/issues/841)를 참조하세요.
-
-</Tip>
-
-커뮤니티 파이프라인을 사용하면 [`DiffusionPipeline`] 위에 원하는 추가 기능을 추가할 수 있습니다. `DiffusionPipeline` 위에 구축할 때의 가장 큰 장점은 누구나 인수를 하나만 추가하면 파이프라인을 로드하고 사용할 수 있어 커뮤니티가 매우 쉽게 접근할 수 있다는 것입니다.
-
-이번 가이드에서는 커뮤니티 파이프라인을 생성하는 방법과 작동 원리를 설명합니다.
-간단하게 설명하기 위해 `UNet`이 단일 forward pass를 수행하고 스케줄러를 한 번 호출하는 "one-step" 파이프라인을 만들겠습니다.
-
-## 파이프라인 초기화
-
-커뮤니티 파이프라인을 위한 `one_step_unet.py` 파일을 생성하는 것으로 시작합니다. 이 파일에서, Hub에서 모델 가중치와 스케줄러 구성을 로드할 수 있도록 [`DiffusionPipeline`]을 상속하는 파이프라인 클래스를 생성합니다. one-step 파이프라인에는 `UNet`과 스케줄러가 필요하므로 이를 `__init__` 함수에 인수로 추가해야합니다:
-
-```python
-from diffusers import DiffusionPipeline
-import torch
-
-
-class UnetSchedulerOneForwardPipeline(DiffusionPipeline):
-    def __init__(self, unet, scheduler):
-        super().__init__()
-```
-
-파이프라인과 그 구성요소(`unet` and `scheduler`)를 [`~DiffusionPipeline.save_pretrained`]으로 저장할 수 있도록 하려면 `register_modules` 함수에 추가하세요:
-
-```diff
-  from diffusers import DiffusionPipeline
-  import torch
-
-  class UnetSchedulerOneForwardPipeline(DiffusionPipeline):
-      def __init__(self, unet, scheduler):
-          super().__init__()
-
-+         self.register_modules(unet=unet, scheduler=scheduler)
-```
-
-이제 '초기화' 단계가 완료되었으니 forward pass로 이동할 수 있습니다! 🔥
-
-## Forward pass 정의
-
-Forward pass 에서는(`__call__`로 정의하는 것이 좋습니다) 원하는 기능을 추가할 수 있는 완전한 창작 자유가 있습니다. 우리의 놀라운 one-step 파이프라인의 경우, 임의의 이미지를 생성하고 `timestep=1`을 설정하여 `unet`과 `scheduler`를 한 번만 호출합니다:
-
-```diff
-  from diffusers import DiffusionPipeline
-  import torch
-
-
-  class UnetSchedulerOneForwardPipeline(DiffusionPipeline):
-      def __init__(self, unet, scheduler):
-          super().__init__()
-
-          self.register_modules(unet=unet, scheduler=scheduler)
-
-+     def __call__(self):
-+         image = torch.randn(
-+             (1, self.unet.config.in_channels, self.unet.config.sample_size, self.unet.config.sample_size),
-+         )
-+         timestep = 1
-
-+         model_output = self.unet(image, timestep).sample
-+         scheduler_output = self.scheduler.step(model_output, timestep, image).prev_sample
-
-+         return scheduler_output
-```
-
-끝났습니다! 🚀 이제 이 파이프라인에 `unet`과 `scheduler`를 전달하여 실행할 수 있습니다:
-
-```python
-from diffusers import DDPMScheduler, UNet2DModel
-
-scheduler = DDPMScheduler()
-unet = UNet2DModel()
-
-pipeline = UnetSchedulerOneForwardPipeline(unet=unet, scheduler=scheduler)
-
-output = pipeline()
-```
-
-하지만 파이프라인 구조가 동일한 경우 기존 가중치를 파이프라인에 로드할 수 있다는 장점이 있습니다. 예를 들어 one-step 파이프라인에 [`google/ddpm-cifar10-32`](https://huggingface.co/google/ddpm-cifar10-32) 가중치를 로드할 수 있습니다:
-
-```python
-pipeline = UnetSchedulerOneForwardPipeline.from_pretrained("google/ddpm-cifar10-32")
-
-output = pipeline()
-```
-
-## 파이프라인 공유
-
-🧨Diffusers [리포지토리](https://github.com/huggingface/diffusers)에서 Pull Request를 열어 [examples/community](https://github.com/huggingface/diffusers/tree/main/examples/community) 하위 폴더에 `one_step_unet.py`의 멋진 파이프라인을 추가하세요.
-
-병합이 되면, `diffusers >= 0.4.0`이 설치된 사용자라면 누구나 `custom_pipeline` 인수에 지정하여 이 파이프라인을 마술처럼 🪄 사용할 수 있습니다:
-
-```python
-from diffusers import DiffusionPipeline
-
-pipe = DiffusionPipeline.from_pretrained("google/ddpm-cifar10-32", custom_pipeline="one_step_unet")
-pipe()
-```
-
-커뮤니티 파이프라인을 공유하는 또 다른 방법은 Hub 에서 선호하는 [모델 리포지토리](https://huggingface.co/docs/hub/models-uploading)에 직접  `one_step_unet.py` 파일을 업로드하는 것입니다. `one_step_unet.py` 파일을 지정하는 대신 모델 저장소 id를 `custom_pipeline` 인수에 전달하세요:
-
-```python
-from diffusers import DiffusionPipeline
-
-pipeline = DiffusionPipeline.from_pretrained("google/ddpm-cifar10-32", custom_pipeline="stevhliu/one_step_unet")
-```
-
-다음 표에서 두 가지 공유 워크플로우를 비교하여 자신에게 가장 적합한 옵션을 결정하는 데 도움이 되는 정보를 확인하세요:
-
-|                | GitHub 커뮤니티 파이프라인                                                                                        | HF Hub 커뮤니티 파이프라인                                                                 |
-|----------------|------------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------|
-| 사용법          | 동일                                                                                                             | 동일                                                                                      |
-| 리뷰 과정 | 병합하기 전에 GitHub에서 Pull Request를 열고 Diffusers 팀의 검토 과정을 거칩니다. 속도가 느릴 수 있습니다. | 검토 없이 Hub 저장소에 바로 업로드합니다. 가장 빠른 워크플로우 입니다. |
-| 가시성     | 공식 Diffusers 저장소 및 문서에 포함되어 있습니다.                                                  | HF 허브 프로필에 포함되며 가시성을 확보하기 위해 자신의 사용량/프로모션에 의존합니다. |
-
-<Tip>
-
-💡 커뮤니티 파이프라인 파일에 원하는 패키지를 사용할 수 있습니다. 사용자가 패키지를 설치하기만 하면 모든 것이 정상적으로 작동합니다. 파이프라인이 자동으로 감지되므로 `DiffusionPipeline`에서 상속하는 파이프라인 클래스가 하나만 있는지 확인하세요.
-
-</Tip>
-
-## 커뮤니티 파이프라인은 어떻게 작동하나요?
-
-커뮤니티 파이프라인은 [`DiffusionPipeline`]을 상속하는 클래스입니다:
-
-- [`custom_pipeline`] 인수로 로드할 수 있습니다.
-- 모델 가중치 및 스케줄러 구성은 [`pretrained_model_name_or_path`]에서 로드됩니다.
-- 커뮤니티 파이프라인에서 기능을 구현하는 코드는 `pipeline.py` 파일에 정의되어 있습니다.
-
-공식 저장소에서 모든 파이프라인 구성 요소 가중치를 로드할 수 없는 경우가 있습니다. 이 경우 다른 구성 요소는 파이프라인에 직접 전달해야 합니다:
-
-```python
-from diffusers import DiffusionPipeline
-from transformers import CLIPFeatureExtractor, CLIPModel
-
-model_id = "CompVis/stable-diffusion-v1-4"
-clip_model_id = "laion/CLIP-ViT-B-32-laion2B-s34B-b79K"
-
-feature_extractor = CLIPFeatureExtractor.from_pretrained(clip_model_id)
-clip_model = CLIPModel.from_pretrained(clip_model_id, torch_dtype=torch.float16)
-
-pipeline = DiffusionPipeline.from_pretrained(
-    model_id,
-    custom_pipeline="clip_guided_stable_diffusion",
-    clip_model=clip_model,
-    feature_extractor=feature_extractor,
-    scheduler=scheduler,
-    torch_dtype=torch.float16,
-)
-```
-
-커뮤니티 파이프라인의 마법은 다음 코드에 담겨 있습니다. 이 코드를 통해 커뮤니티 파이프라인을 GitHub 또는 Hub에서 로드할 수 있으며, 모든 🧨 Diffusers 패키지에서 사용할 수 있습니다.
-
-```python
-# 2. 파이프라인 클래스를 로드합니다. 사용자 지정 모듈을 사용하는 경우 Hub에서 로드합니다
-# 명시적 클래스에서 로드하는 경우, 이를 사용해 보겠습니다.
-if custom_pipeline is not None:
-    pipeline_class = get_class_from_dynamic_module(
-        custom_pipeline, module_file=CUSTOM_PIPELINE_FILE_NAME, cache_dir=custom_pipeline
-    )
-elif cls != DiffusionPipeline:
-    pipeline_class = cls
-else:
-    diffusers_module = importlib.import_module(cls.__module__.split(".")[0])
-    pipeline_class = getattr(diffusers_module, config_dict["_class_name"])
-```

docs/source/ko/using-diffusers/control_brightness.md

@@ -1,45 +0,0 @@
-# 이미지 밝기 조절하기
-
-Stable Diffusion 파이프라인은 [일반적인 디퓨전 노이즈 스케줄과 샘플 단계에 결함이 있음](https://huggingface.co/papers/2305.08891) 논문에서 설명한 것처럼 매우 밝거나 어두운 이미지를 생성하는 데는 성능이 평범합니다. 이 논문에서 제안한 솔루션은 현재 [`DDIMScheduler`]에 구현되어 있으며 이미지의 밝기를 개선하는 데 사용할 수 있습니다.
-
-<Tip>
-
-💡 제안된 솔루션에 대한 자세한 내용은 위에 링크된 논문을 참고하세요!
-
-</Tip>
-
-해결책 중 하나는 *v 예측값*과 *v 로스*로 모델을 훈련하는 것입니다. 다음 flag를 [`train_text_to_image.py`](https://github.com/huggingface/diffusers/blob/main/examples/text_to_image/train_text_to_image.py) 또는 [`train_text_to_image_lora.py`](https://github.com/huggingface/diffusers/blob/main/examples/text_to_image/train_text_to_image_lora.py) 스크립트에 추가하여 `v_prediction`을 활성화합니다:
-
-```bash
---prediction_type="v_prediction"
-```
-
-예를 들어, `v_prediction`으로 미세 조정된 [`ptx0/pseudo-journey-v2`](https://huggingface.co/ptx0/pseudo-journey-v2) 체크포인트를 사용해 보겠습니다.
-
-다음으로 [`DDIMScheduler`]에서 다음 파라미터를 설정합니다:
-
-1. rescale_betas_zero_snr=True`, 노이즈 스케줄을 제로 터미널 신호 대 잡음비(SNR)로 재조정합니다.
-2. `timestep_spacing="trailing"`, 마지막 타임스텝부터 샘플링 시작
-
-```py
->>> from diffusers import DiffusionPipeline, DDIMScheduler
-
->>> pipeline = DiffusionPipeline.from_pretrained("ptx0/pseudo-journey-v2")
-# switch the scheduler in the pipeline to use the DDIMScheduler
-
->>> pipeline.scheduler = DDIMScheduler.from_config(
-...     pipeline.scheduler.config, rescale_betas_zero_snr=True, timestep_spacing="trailing"
-... )
->>> pipeline.to("cuda")
-```
-
-마지막으로 파이프라인에 대한 호출에서 `guidance_rescale`을 설정하여 과다 노출을 방지합니다:
-
-```py
-prompt = "A lion in galaxies, spirals, nebulae, stars, smoke, iridescent, intricate detail, octane render, 8k"
-image = pipeline(prompt, guidance_rescale=0.7).images[0]
-```
-
-<div class="flex justify-center">
-    <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/zero_snr.png"/>
-</div>

docs/source/ko/using-diffusers/custom_pipeline_examples.md

@@ -1,275 +0,0 @@
-<!--Copyright 2024 The HuggingFace Team. All rights reserved.
-
-Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
-the License. You may obtain a copy of the License at
-
-http://www.apache.org/licenses/LICENSE-2.0
-
-Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
-an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
-specific language governing permissions and limitations under the License.
--->
-
-# 커뮤니티 파이프라인
-
-> **커뮤니티 파이프라인에 대한 자세한 내용은 [이 이슈](https://github.com/huggingface/diffusers/issues/841)를 참조하세요.
-
-**커뮤니티** 예제는 커뮤니티에서 추가한 추론 및 훈련 예제로 구성되어 있습니다.
-다음 표를 참조하여 모든 커뮤니티 예제에 대한 개요를 확인하시기 바랍니다. **코드 예제**를 클릭하면 복사하여 붙여넣기할 수 있는 코드 예제를 확인할 수 있습니다.
-커뮤니티가 예상대로 작동하지 않는 경우 이슈를 개설하고 작성자에게 핑을 보내주세요.
-
-| 예                                     | 설명                                                                                                                                                                                                                                                                                                                                                                                                                                                                                             | 코드 예제                                                                         | 콜랩                                                                                                                                                                                                              |저자                                                         |
-|:---------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-----------------------------------------------------------:|
-| CLIP Guided Stable Diffusion           | CLIP 가이드 기반의 Stable Diffusion으로 텍스트에서 이미지로 생성하기                                                                                                                                                                                                                                                                                                                                                                                                                                | [CLIP Guided Stable Diffusion](#clip-guided-stable-diffusion)                    | [![콜랩에서 열기](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/CLIP_Guided_Stable_diffusion_with_diffusers.ipynb)  | [Suraj Patil](https://github.com/patil-suraj/)             |
-| One Step U-Net (Dummy)                 | 커뮤니티 파이프라인을 어떻게 사용해야 하는지에 대한 예시(참고 https://github.com/huggingface/diffusers/issues/841)                                                                                                                                                                                                                                                                                                                                                                                   | [One Step U-Net](#one-step-unet)                                                 | -                                                                                                                                                                                                                  | [Patrick von Platen](https://github.com/patrickvonplaten/) |
-| Stable Diffusion Interpolation         | 서로 다른 프롬프트/시드 간 Stable Diffusion의 latent space 보간                                                                                                                                                                                                                                                                                                                                                                                                                                    | [Stable Diffusion Interpolation](#stable-diffusion-interpolation)                | -                                                                                                                                                                                                                  | [Nate Raw](https://github.com/nateraw/)                    |
-| Stable Diffusion Mega                  | 모든 기능을 갖춘 **하나의** Stable Diffusion 파이프라인 [Text2Image](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion.py), [Image2Image](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_img2img.py) and [Inpainting](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_inpaint.py) | [Stable Diffusion Mega](#stable-diffusion-mega)                                  | -                                                                                                                                                                                                                  | [Patrick von Platen](https://github.com/patrickvonplaten/) |
-| Long Prompt Weighting Stable Diffusion | 토큰 길이 제한이 없고 프롬프트에서 파싱 가중치 지원을 하는 **하나의** Stable Diffusion 파이프라인,                                                                                                                                                                                                                                                                                                                                                                                                    | [Long Prompt Weighting Stable Diffusion](#long-prompt-weighting-stable-diffusion) |-                                                                                                                                                                                                                  | [SkyTNT](https://github.com/SkyTNT)                        |
-| Speech to Image                        | 자동 음성 인식을 사용하여 텍스트를 작성하고 Stable Diffusion을 사용하여 이미지를 생성합니다.                                                                                                                                                                                                                                                                                                                                                                                                          | [Speech to Image](#speech-to-image)                                               | -                                                                                                                                                                                                                 | [Mikail Duzenli](https://github.com/MikailINTech)          |
-
-커스텀 파이프라인을 불러오려면 `diffusers/examples/community`에 있는 파일 중 하나로서 `custom_pipeline` 인수를 `DiffusionPipeline`에 전달하기만 하면 됩니다. 자신만의 파이프라인이 있는 PR을 보내주시면 빠르게 병합해드리겠습니다.
-```py
-pipe = DiffusionPipeline.from_pretrained(
-    "CompVis/stable-diffusion-v1-4", custom_pipeline="filename_in_the_community_folder"
-)
-```
-
-## 사용 예시
-
-### CLIP 가이드 기반의 Stable Diffusion
-
-모든 노이즈 제거 단계에서 추가 CLIP 모델을 통해 Stable Diffusion을 가이드함으로써 CLIP 모델 기반의 Stable Diffusion은 보다 더 사실적인 이미지를 생성을 할 수 있습니다.
-
-다음 코드는 약 12GB의 GPU RAM이 필요합니다.
-
-```python
-from diffusers import DiffusionPipeline
-from transformers import CLIPImageProcessor, CLIPModel
-import torch
-
-
-feature_extractor = CLIPImageProcessor.from_pretrained("laion/CLIP-ViT-B-32-laion2B-s34B-b79K")
-clip_model = CLIPModel.from_pretrained("laion/CLIP-ViT-B-32-laion2B-s34B-b79K", torch_dtype=torch.float16)
-
-
-guided_pipeline = DiffusionPipeline.from_pretrained(
-    "CompVis/stable-diffusion-v1-4",
-    custom_pipeline="clip_guided_stable_diffusion",
-    clip_model=clip_model,
-    feature_extractor=feature_extractor,
-    torch_dtype=torch.float16,
-)
-guided_pipeline.enable_attention_slicing()
-guided_pipeline = guided_pipeline.to("cuda")
-
-prompt = "fantasy book cover, full moon, fantasy forest landscape, golden vector elements, fantasy magic, dark light night, intricate, elegant, sharp focus, illustration, highly detailed, digital painting, concept art, matte, art by WLOP and Artgerm and Albert Bierstadt, masterpiece"
-
-generator = torch.Generator(device="cuda").manual_seed(0)
-images = []
-for i in range(4):
-    image = guided_pipeline(
-        prompt,
-        num_inference_steps=50,
-        guidance_scale=7.5,
-        clip_guidance_scale=100,
-        num_cutouts=4,
-        use_cutouts=False,
-        generator=generator,
-    ).images[0]
-    images.append(image)
-
-# 이미지 로컬에 저장하기
-for i, img in enumerate(images):
-    img.save(f"./clip_guided_sd/image_{i}.png")
-```
-
-이미지` 목록에는 로컬에 저장하거나 구글 콜랩에 직접 표시할 수 있는 PIL 이미지 목록이 포함되어 있습니다. 생성된 이미지는 기본적으로 안정적인 확산을 사용하는 것보다 품질이 높은 경향이 있습니다. 예를 들어 위의 스크립트는 다음과 같은 이미지를 생성합니다:
-
-![clip_guidance](https://huggingface.co/datasets/patrickvonplaten/images/resolve/main/clip_guidance/merged_clip_guidance.jpg).
-
-### One Step Unet
-
-예시 "one-step-unet"는 다음과 같이 실행할 수 있습니다.
-
-```python
-from diffusers import DiffusionPipeline
-
-pipe = DiffusionPipeline.from_pretrained("google/ddpm-cifar10-32", custom_pipeline="one_step_unet")
-pipe()
-```
-
-**참고**: 이 커뮤니티 파이프라인은 기능으로 유용하지 않으며 커뮤니티 파이프라인을 추가할 수 있는 방법의 예시일 뿐입니다(https://github.com/huggingface/diffusers/issues/841 참조).
-
-### Stable Diffusion Interpolation
-
-다음 코드는 최소 8GB VRAM의 GPU에서 실행할 수 있으며 약 5분 정도 소요됩니다.
-
-```python
-from diffusers import DiffusionPipeline
-import torch
-
-pipe = DiffusionPipeline.from_pretrained(
-    "CompVis/stable-diffusion-v1-4",
-    torch_dtype=torch.float16,
-    safety_checker=None,  # Very important for videos...lots of false positives while interpolating
-    custom_pipeline="interpolate_stable_diffusion",
-).to("cuda")
-pipe.enable_attention_slicing()
-
-frame_filepaths = pipe.walk(
-    prompts=["a dog", "a cat", "a horse"],
-    seeds=[42, 1337, 1234],
-    num_interpolation_steps=16,
-    output_dir="./dreams",
-    batch_size=4,
-    height=512,
-    width=512,
-    guidance_scale=8.5,
-    num_inference_steps=50,
-)
-```
-
-walk(...)` 함수의 출력은 `output_dir`에 정의된 대로 폴더에 저장된 이미지 목록을 반환합니다. 이 이미지를 사용하여 안정적으로 확산되는 동영상을 만들 수 있습니다.
-
-> 안정된 확산을 이용한 동영상 제작 방법과 더 많은 기능에 대한 자세한 내용은 https://github.com/nateraw/stable-diffusion-videos 에서 확인하시기 바랍니다.
-
-### Stable Diffusion Mega
-
-The Stable Diffusion Mega 파이프라인을 사용하면 Stable Diffusion 파이프라인의 주요 사용 사례를 단일 클래스에서 사용할 수 있습니다.
-```python
-#!/usr/bin/env python3
-from diffusers import DiffusionPipeline
-import PIL
-import requests
-from io import BytesIO
-import torch
-
-
-def download_image(url):
-    response = requests.get(url)
-    return PIL.Image.open(BytesIO(response.content)).convert("RGB")
-
-
-pipe = DiffusionPipeline.from_pretrained(
-    "CompVis/stable-diffusion-v1-4",
-    custom_pipeline="stable_diffusion_mega",
-    torch_dtype=torch.float16,
-)
-pipe.to("cuda")
-pipe.enable_attention_slicing()
-
-
-### Text-to-Image
-
-images = pipe.text2img("An astronaut riding a horse").images
-
-### Image-to-Image
-
-init_image = download_image(
-    "https://raw.githubusercontent.com/CompVis/stable-diffusion/main/assets/stable-samples/img2img/sketch-mountains-input.jpg"
-)
-
-prompt = "A fantasy landscape, trending on artstation"
-
-images = pipe.img2img(prompt=prompt, image=init_image, strength=0.75, guidance_scale=7.5).images
-
-### Inpainting
-
-img_url = "https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo.png"
-mask_url = "https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo_mask.png"
-init_image = download_image(img_url).resize((512, 512))
-mask_image = download_image(mask_url).resize((512, 512))
-
-prompt = "a cat sitting on a bench"
-images = pipe.inpaint(prompt=prompt, image=init_image, mask_image=mask_image, strength=0.75).images
-```
-
-위에 표시된 것처럼 하나의 파이프라인에서 '텍스트-이미지 변환', '이미지-이미지 변환', '인페인팅'을 모두 실행할 수 있습니다.
-
-### Long Prompt Weighting Stable Diffusion
-
-파이프라인을 사용하면 77개의 토큰 길이 제한 없이 프롬프트를 입력할 수 있습니다. 또한 "()"를 사용하여 단어 가중치를 높이거나 "[]"를 사용하여 단어 가중치를 낮출 수 있습니다.
-또한 파이프라인을 사용하면 단일 클래스에서 Stable Diffusion 파이프라인의 주요 사용 사례를 사용할 수 있습니다.
-
-#### pytorch
-
-```python
-from diffusers import DiffusionPipeline
-import torch
-
-pipe = DiffusionPipeline.from_pretrained(
-    "hakurei/waifu-diffusion", custom_pipeline="lpw_stable_diffusion", torch_dtype=torch.float16
-)
-pipe = pipe.to("cuda")
-
-prompt = "best_quality (1girl:1.3) bow bride brown_hair closed_mouth frilled_bow frilled_hair_tubes frills (full_body:1.3) fox_ear hair_bow hair_tubes happy hood japanese_clothes kimono long_sleeves red_bow smile solo tabi uchikake white_kimono wide_sleeves cherry_blossoms"
-neg_prompt = "lowres, bad_anatomy, error_body, error_hair, error_arm, error_hands, bad_hands, error_fingers, bad_fingers, missing_fingers, error_legs, bad_legs, multiple_legs, missing_legs, error_lighting, error_shadow, error_reflection, text, error, extra_digit, fewer_digits, cropped, worst_quality, low_quality, normal_quality, jpeg_artifacts, signature, watermark, username, blurry"
-
-pipe.text2img(prompt, negative_prompt=neg_prompt, width=512, height=512, max_embeddings_multiples=3).images[0]
-```
-
-#### onnxruntime
-
-```python
-from diffusers import DiffusionPipeline
-import torch
-
-pipe = DiffusionPipeline.from_pretrained(
-    "CompVis/stable-diffusion-v1-4",
-    custom_pipeline="lpw_stable_diffusion_onnx",
-    revision="onnx",
-    provider="CUDAExecutionProvider",
-)
-
-prompt = "a photo of an astronaut riding a horse on mars, best quality"
-neg_prompt = "lowres, bad anatomy, error body, error hair, error arm, error hands, bad hands, error fingers, bad fingers, missing fingers, error legs, bad legs, multiple legs, missing legs, error lighting, error shadow, error reflection, text, error, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry"
-
-pipe.text2img(prompt, negative_prompt=neg_prompt, width=512, height=512, max_embeddings_multiples=3).images[0]
-```
-
-토큰 인덱스 시퀀스 길이가 이 모델에 지정된 최대 시퀀스 길이보다 길면(*** > 77). 이 시퀀스를 모델에서 실행하면 인덱싱 오류가 발생합니다`. 정상적인 현상이니 걱정하지 마세요.
-### Speech to Image
-
-다음 코드는 사전학습된 OpenAI whisper-small과 Stable Diffusion을 사용하여 오디오 샘플에서 이미지를 생성할 수 있습니다.
-```Python
-import torch
-
-import matplotlib.pyplot as plt
-from datasets import load_dataset
-from diffusers import DiffusionPipeline
-from transformers import (
-    WhisperForConditionalGeneration,
-    WhisperProcessor,
-)
-
-
-device = "cuda" if torch.cuda.is_available() else "cpu"
-
-ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
-
-audio_sample = ds[3]
-
-text = audio_sample["text"].lower()
-speech_data = audio_sample["audio"]["array"]
-
-model = WhisperForConditionalGeneration.from_pretrained("openai/whisper-small").to(device)
-processor = WhisperProcessor.from_pretrained("openai/whisper-small")
-
-diffuser_pipeline = DiffusionPipeline.from_pretrained(
-    "CompVis/stable-diffusion-v1-4",
-    custom_pipeline="speech_to_image_diffusion",
-    speech_model=model,
-    speech_processor=processor,
-
-    torch_dtype=torch.float16,
-)
-
-diffuser_pipeline.enable_attention_slicing()
-diffuser_pipeline = diffuser_pipeline.to(device)
-
-output = diffuser_pipeline(speech_data)
-plt.imshow(output.images[0])
-```
-위 예시는 다음의 결과 이미지를 보입니다.
-
-![image](https://user-images.githubusercontent.com/45072645/196901736-77d9c6fc-63ee-4072-90b0-dc8b903d63e3.png)

docs/source/ko/using-diffusers/diffedit.md

@@ -0,0 +1,285 @@
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License.
+-->
+
+# DiffEdit
+
+[[open-in-colab]]
+
+이미지 편집을 하려면 일반적으로 편집할 영역의 마스크를 제공해야 합니다. DiffEdit는 텍스트 쿼리를 기반으로 마스크를 자동으로 생성하므로 이미지 편집 소프트웨어 없이도 마스크를 만들기가 전반적으로 더 쉬워집니다. DiffEdit 알고리즘은 세 단계로 작동합니다:
+
+1. Diffusion 모델이 일부 쿼리 텍스트와 참조 텍스트를 조건부로 이미지의 노이즈를 제거하여 이미지의 여러 영역에 대해 서로 다른 노이즈 추정치를 생성하고, 그 차이를 사용하여 쿼리 텍스트와 일치하도록 이미지의 어느 영역을 변경해야 하는지 식별하기 위한 마스크를 추론합니다.
+2. 입력 이미지가 DDIM을 사용하여 잠재 공간으로 인코딩됩니다.
+3. 마스크 외부의 픽셀이 입력 이미지와 동일하게 유지되도록 마스크를 가이드로 사용하여 텍스트 쿼리에 조건이 지정된 diffusion 모델로 latents를 디코딩합니다.
+
+이 가이드에서는 마스크를 수동으로 만들지 않고 DiffEdit를 사용하여 이미지를 편집하는 방법을 설명합니다.
+
+시작하기 전에 다음 라이브러리가 설치되어 있는지 확인하세요:
+
+```py
+# Colab에서 필요한 라이브러리를 설치하기 위해 주석을 제외하세요
+#!pip install -q diffusers transformers accelerate
+```
+
+[`StableDiffusionDiffEditPipeline`]에는 이미지 마스크와 부분적으로 반전된 latents 집합이 필요합니다. 이미지 마스크는 [`~StableDiffusionDiffEditPipeline.generate_mask`] 함수에서 생성되며, 두 개의 파라미터인 `source_prompt`와 `target_prompt`가 포함됩니다. 이 매개변수는 이미지에서 무엇을 편집할지 결정합니다. 예를 들어, *과일* 한 그릇을 *배* 한 그릇으로 변경하려면 다음과 같이 하세요:
+
+```py
+source_prompt = "a bowl of fruits"
+target_prompt = "a bowl of pears"
+```
+
+부분적으로 반전된 latents는 [`~StableDiffusionDiffEditPipeline.invert`] 함수에서 생성되며, 일반적으로 이미지를 설명하는 `prompt` 또는 *캡션*을 포함하는 것이 inverse latent sampling 프로세스를 가이드하는 데 도움이 됩니다. 캡션은 종종 `source_prompt`가 될 수 있지만, 다른 텍스트 설명으로 자유롭게 실험해 보세요!
+
+파이프라인, 스케줄러, 역 스케줄러를 불러오고 메모리 사용량을 줄이기 위해 몇 가지 최적화를 활성화해 보겠습니다:
+
+```py
+import torch
+from diffusers import DDIMScheduler, DDIMInverseScheduler, StableDiffusionDiffEditPipeline
+
+pipeline = StableDiffusionDiffEditPipeline.from_pretrained(
+    "stabilityai/stable-diffusion-2-1",
+    torch_dtype=torch.float16,
+    safety_checker=None,
+    use_safetensors=True,
+)
+pipeline.scheduler = DDIMScheduler.from_config(pipeline.scheduler.config)
+pipeline.inverse_scheduler = DDIMInverseScheduler.from_config(pipeline.scheduler.config)
+pipeline.enable_model_cpu_offload()
+pipeline.enable_vae_slicing()
+```
+
+수정하기 위한 이미지를 불러옵니다:
+
+```py
+from diffusers.utils import load_image, make_image_grid
+
+img_url = "https://github.com/Xiang-cd/DiffEdit-stable-diffusion/raw/main/assets/origin.png"
+raw_image = load_image(img_url).resize((768, 768))
+raw_image
+```
+
+이미지 마스크를 생성하기 위해 [`~StableDiffusionDiffEditPipeline.generate_mask`] 함수를 사용합니다. 이미지에서 편집할 내용을 지정하기 위해 `source_prompt`와 `target_prompt`를 전달해야 합니다:
+
+```py
+from PIL import Image
+
+source_prompt = "a bowl of fruits"
+target_prompt = "a basket of pears"
+mask_image = pipeline.generate_mask(
+    image=raw_image,
+    source_prompt=source_prompt,
+    target_prompt=target_prompt,
+)
+Image.fromarray((mask_image.squeeze()*255).astype("uint8"), "L").resize((768, 768))
+```
+
+다음으로, 반전된 latents를 생성하고 이미지를 묘사하는 캡션에 전달합니다:
+
+```py
+inv_latents = pipeline.invert(prompt=source_prompt, image=raw_image).latents
+```
+
+마지막으로, 이미지 마스크와 반전된 latents를 파이프라인에 전달합니다. `target_prompt`는 이제 `prompt`가 되며, `source_prompt`는 `negative_prompt`로 사용됩니다.
+
+```py
+output_image = pipeline(
+    prompt=target_prompt,
+    mask_image=mask_image,
+    image_latents=inv_latents,
+    negative_prompt=source_prompt,
+).images[0]
+mask_image = Image.fromarray((mask_image.squeeze()*255).astype("uint8"), "L").resize((768, 768))
+make_image_grid([raw_image, mask_image, output_image], rows=1, cols=3)
+```
+
+<div class="flex gap-4">
+  <div>
+    <img class="rounded-xl" src="https://github.com/Xiang-cd/DiffEdit-stable-diffusion/raw/main/assets/origin.png"/>
+    <figcaption class="mt-2 text-center text-sm text-gray-500">original image</figcaption>
+  </div>
+  <div>
+    <img class="rounded-xl" src="https://github.com/Xiang-cd/DiffEdit-stable-diffusion/blob/main/assets/target.png?raw=true"/>
+    <figcaption class="mt-2 text-center text-sm text-gray-500">edited image</figcaption>
+  </div>
+</div>
+
+## Source와 target 임베딩 생성하기
+
+Source와 target 임베딩은 수동으로 생성하는 대신 [Flan-T5](https://huggingface.co/docs/transformers/model_doc/flan-t5) 모델을 사용하여 자동으로 생성할 수 있습니다.
+
+Flan-T5 모델과 토크나이저를 🤗 Transformers 라이브러리에서 불러옵니다:
+
+```py
+import torch
+from transformers import AutoTokenizer, T5ForConditionalGeneration
+
+tokenizer = AutoTokenizer.from_pretrained("google/flan-t5-large")
+model = T5ForConditionalGeneration.from_pretrained("google/flan-t5-large", device_map="auto", torch_dtype=torch.float16)
+```
+
+모델에 프롬프트할 source와 target 프롬프트를 생성하기 위해 초기 텍스트들을 제공합니다.
+
+```py
+source_concept = "bowl"
+target_concept = "basket"
+
+source_text = f"Provide a caption for images containing a {source_concept}. "
+"The captions should be in English and should be no longer than 150 characters."
+
+target_text = f"Provide a caption for images containing a {target_concept}. "
+"The captions should be in English and should be no longer than 150 characters."
+```
+
+다음으로, 프롬프트들을 생성하기 위해 유틸리티 함수를 생성합니다.
+
+```py
+@torch.no_grad()
+def generate_prompts(input_prompt):
+    input_ids = tokenizer(input_prompt, return_tensors="pt").input_ids.to("cuda")
+
+    outputs = model.generate(
+        input_ids, temperature=0.8, num_return_sequences=16, do_sample=True, max_new_tokens=128, top_k=10
+    )
+    return tokenizer.batch_decode(outputs, skip_special_tokens=True)
+
+source_prompts = generate_prompts(source_text)
+target_prompts = generate_prompts(target_text)
+print(source_prompts)
+print(target_prompts)
+```
+
+<Tip>
+
+다양한 품질의 텍스트를 생성하는 전략에 대해 자세히 알아보려면 [생성 전략](https://huggingface.co/docs/transformers/main/en/generation_strategies) 가이드를 참조하세요.
+
+</Tip>
+
+텍스트 인코딩을 위해 [`StableDiffusionDiffEditPipeline`]에서 사용하는 텍스트 인코더 모델을 불러옵니다. 텍스트 인코더를 사용하여 텍스트 임베딩을 계산합니다:
+
+```py
+import torch
+from diffusers import StableDiffusionDiffEditPipeline
+
+pipeline = StableDiffusionDiffEditPipeline.from_pretrained(
+    "stabilityai/stable-diffusion-2-1", torch_dtype=torch.float16, use_safetensors=True
+)
+pipeline.enable_model_cpu_offload()
+pipeline.enable_vae_slicing()
+
+@torch.no_grad()
+def embed_prompts(sentences, tokenizer, text_encoder, device="cuda"):
+    embeddings = []
+    for sent in sentences:
+        text_inputs = tokenizer(
+            sent,
+            padding="max_length",
+            max_length=tokenizer.model_max_length,
+            truncation=True,
+            return_tensors="pt",
+        )
+        text_input_ids = text_inputs.input_ids
+        prompt_embeds = text_encoder(text_input_ids.to(device), attention_mask=None)[0]
+        embeddings.append(prompt_embeds)
+    return torch.concatenate(embeddings, dim=0).mean(dim=0).unsqueeze(0)
+
+source_embeds = embed_prompts(source_prompts, pipeline.tokenizer, pipeline.text_encoder)
+target_embeds = embed_prompts(target_prompts, pipeline.tokenizer, pipeline.text_encoder)
+```
+
+마지막으로, 임베딩을 [`~StableDiffusionDiffEditPipeline.generate_mask`] 및 [`~StableDiffusionDiffEditPipeline.invert`] 함수와 파이프라인에 전달하여 이미지를 생성합니다:
+
+```diff
+  from diffusers import DDIMInverseScheduler, DDIMScheduler
+  from diffusers.utils import load_image, make_image_grid
+  from PIL import Image
+
+  pipeline.scheduler = DDIMScheduler.from_config(pipeline.scheduler.config)
+  pipeline.inverse_scheduler = DDIMInverseScheduler.from_config(pipeline.scheduler.config)
+
+  img_url = "https://github.com/Xiang-cd/DiffEdit-stable-diffusion/raw/main/assets/origin.png"
+  raw_image = load_image(img_url).resize((768, 768))
+
+  mask_image = pipeline.generate_mask(
+      image=raw_image,
+-     source_prompt=source_prompt,
+-     target_prompt=target_prompt,
++     source_prompt_embeds=source_embeds,
++     target_prompt_embeds=target_embeds,
+  )
+
+  inv_latents = pipeline.invert(
+-     prompt=source_prompt,
++     prompt_embeds=source_embeds,
+      image=raw_image,
+  ).latents
+
+  output_image = pipeline(
+      mask_image=mask_image,
+      image_latents=inv_latents,
+-     prompt=target_prompt,
+-     negative_prompt=source_prompt,
++     prompt_embeds=target_embeds,
++     negative_prompt_embeds=source_embeds,
+  ).images[0]
+  mask_image = Image.fromarray((mask_image.squeeze()*255).astype("uint8"), "L")
+  make_image_grid([raw_image, mask_image, output_image], rows=1, cols=3)
+```
+
+## 반전을 위한 캡션 생성하기
+
+`source_prompt`를 캡션으로 사용하여 부분적으로 반전된 latents를 생성할 수 있지만, [BLIP](https://huggingface.co/docs/transformers/model_doc/blip) 모델을 사용하여 캡션을 자동으로 생성할 수도 있습니다.
+
+🤗 Transformers 라이브러리에서 BLIP 모델과 프로세서를 불러옵니다:
+
+```py
+import torch
+from transformers import BlipForConditionalGeneration, BlipProcessor
+
+processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
+model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-base", torch_dtype=torch.float16, low_cpu_mem_usage=True)
+```
+
+입력 이미지에서 캡션을 생성하는 유틸리티 함수를 만듭니다:
+
+```py
+@torch.no_grad()
+def generate_caption(images, caption_generator, caption_processor):
+    text = "a photograph of"
+
+    inputs = caption_processor(images, text, return_tensors="pt").to(device="cuda", dtype=caption_generator.dtype)
+    caption_generator.to("cuda")
+    outputs = caption_generator.generate(**inputs, max_new_tokens=128)
+
+    # 캡션 generator 오프로드
+    caption_generator.to("cpu")
+
+    caption = caption_processor.batch_decode(outputs, skip_special_tokens=True)[0]
+    return caption
+```
+
+입력 이미지를 불러오고 `generate_caption` 함수를 사용하여 해당 이미지에 대한 캡션을 생성합니다:
+
+```py
+from diffusers.utils import load_image
+
+img_url = "https://github.com/Xiang-cd/DiffEdit-stable-diffusion/raw/main/assets/origin.png"
+raw_image = load_image(img_url).resize((768, 768))
+caption = generate_caption(raw_image, model, processor)
+```
+
+<div class="flex justify-center">
+    <figure>
+        <img class="rounded-xl" src="https://github.com/Xiang-cd/DiffEdit-stable-diffusion/raw/main/assets/origin.png"/>
+        <figcaption class="text-center">generated caption: "a photograph of a bowl of fruit on a table"</figcaption>
+    </figure>
+</div>
+
+이제 캡션을 [`~StableDiffusionDiffEditPipeline.invert`] 함수에 놓아 부분적으로 반전된 latents를 생성할 수 있습니다!

docs/source/ko/using-diffusers/kandinsky.md

@@ -0,0 +1,768 @@
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License.
+-->
+
+# Kandinsky
+
+[[open-in-colab]]
+
+Kandinsky 모델은 일련의 다국어 text-to-image 생성 모델입니다. Kandinsky 2.0 모델은 두 개의 다국어 텍스트 인코더를 사용하고 그 결과를 연결해 UNet에 사용됩니다.
+
+[Kandinsky 2.1](../api/pipelines/kandinsky)은 텍스트와 이미지 임베딩 간의 매핑을 생성하는 image prior 모델([`CLIP`](https://huggingface.co/docs/transformers/model_doc/clip))을 포함하도록 아키텍처를 변경했습니다. 이 매핑은 더 나은 text-image alignment를 제공하며, 학습 중에 텍스트 임베딩과 함께 사용되어 더 높은 품질의 결과를 가져옵니다. 마지막으로, Kandinsky 2.1은 spatial conditional 정규화 레이어를 추가하여 사실감을 높여주는 [Modulating Quantized Vectors (MoVQ)](https://huggingface.co/papers/2209.09002) 디코더를 사용하여 latents를 이미지로 디코딩합니다.
+
+[Kandinsky 2.2](../api/pipelines/kandinsky_v22)는 image prior 모델의 이미지 인코더를 더 큰 CLIP-ViT-G 모델로 교체하여 품질을 개선함으로써 이전 모델을 개선했습니다. 또한 image prior 모델은 해상도와 종횡비가 다른 이미지로 재훈련되어 더 높은 해상도의 이미지와 다양한 이미지 크기를 생성합니다.
+
+[Kandinsky 3](../api/pipelines/kandinsky3)는 아키텍처를 단순화하고 prior 모델과 diffusion 모델을 포함하는 2단계 생성 프로세스에서 벗어나고 있습니다. 대신, Kandinsky 3는 [Flan-UL2](https://huggingface.co/google/flan-ul2)를 사용하여 텍스트를 인코딩하고, [BigGan-deep](https://hf.co/papers/1809.11096) 블록이 포함된 UNet을 사용하며, [Sber-MoVQGAN](https://github.com/ai-forever/MoVQGAN)을 사용하여 latents를 이미지로 디코딩합니다. 텍스트 이해와 생성된 이미지 품질은 주로 더 큰 텍스트 인코더와 UNet을 사용함으로써 달성됩니다.
+
+이 가이드에서는 text-to-image, image-to-image, 인페인팅, 보간 등을 위해 Kandinsky 모델을 사용하는 방법을 설명합니다.
+
+시작하기 전에 다음 라이브러리가 설치되어 있는지 확인하세요:
+
+```py
+# Colab에서 필요한 라이브러리를 설치하기 위해 주석을 제외하세요
+#!pip install -q diffusers transformers accelerate
+```
+
+<Tip warning={true}>
+
+Kandinsky 2.1과 2.2의 사용법은 매우 유사합니다! 유일한 차이점은 Kandinsky 2.2는 latents를 디코딩할 때 `프롬프트`를 입력으로 받지 않는다는 것입니다. 대신, Kandinsky 2.2는 디코딩 중에는 `image_embeds`만 받아들입니다.
+
+<br>
+
+Kandinsky 3는 더 간결한 아키텍처를 가지고 있으며 prior 모델이 필요하지 않습니다. 즉, [Stable Diffusion XL](sdxl)과 같은 다른 diffusion 모델과 사용법이 동일합니다.
+
+</Tip>
+
+## Text-to-image
+
+모든 작업에 Kandinsky 모델을 사용하려면 항상 프롬프트를 인코딩하고 이미지 임베딩을 생성하는 prior 파이프라인을 설정하는 것부터 시작해야 합니다. 이전 파이프라인은 negative 프롬프트 `""`에 해당하는 `negative_image_embeds`도 생성합니다. 더 나은 결과를 얻으려면 이전 파이프라인에 실제 `negative_prompt`를 전달할 수 있지만, 이렇게 하면 prior 파이프라인의 유효 배치 크기가 2배로 증가합니다.
+
+<hfoptions id="text-to-image">
+<hfoption id="Kandinsky 2.1">
+
+```py
+from diffusers import KandinskyPriorPipeline, KandinskyPipeline
+import torch
+
+prior_pipeline = KandinskyPriorPipeline.from_pretrained("kandinsky-community/kandinsky-2-1-prior", torch_dtype=torch.float16).to("cuda")
+pipeline = KandinskyPipeline.from_pretrained("kandinsky-community/kandinsky-2-1", torch_dtype=torch.float16).to("cuda")
+
+prompt = "A alien cheeseburger creature eating itself, claymation, cinematic, moody lighting"
+negative_prompt = "low quality, bad quality" # negative 프롬프트 포함은 선택적이지만, 보통 결과는 더 좋습니다
+image_embeds, negative_image_embeds = prior_pipeline(prompt, negative_prompt, guidance_scale=1.0).to_tuple()
+```
+
+이제 모든 프롬프트와 임베딩을 [`KandinskyPipeline`]에 전달하여 이미지를 생성합니다:
+
+```py
+image = pipeline(prompt, image_embeds=image_embeds, negative_prompt=negative_prompt, negative_image_embeds=negative_image_embeds, height=768, width=768).images[0]
+image
+```
+
+<div class="flex justify-center">
+    <img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/kandinsky-docs/cheeseburger.png"/>
+</div>
+
+</hfoption>
+<hfoption id="Kandinsky 2.2">
+
+```py
+from diffusers import KandinskyV22PriorPipeline, KandinskyV22Pipeline
+import torch
+
+prior_pipeline = KandinskyV22PriorPipeline.from_pretrained("kandinsky-community/kandinsky-2-2-prior", torch_dtype=torch.float16).to("cuda")
+pipeline = KandinskyV22Pipeline.from_pretrained("kandinsky-community/kandinsky-2-2-decoder", torch_dtype=torch.float16).to("cuda")
+
+prompt = "A alien cheeseburger creature eating itself, claymation, cinematic, moody lighting"
+negative_prompt = "low quality, bad quality" # negative 프롬프트 포함은 선택적이지만, 보통 결과는 더 좋습니다
+image_embeds, negative_image_embeds = prior_pipeline(prompt, guidance_scale=1.0).to_tuple()
+```
+
+이미지 생성을 위해 `image_embeds`와 `negative_image_embeds`를 [`KandinskyV22Pipeline`]에 전달합니다:
+
+```py
+image = pipeline(image_embeds=image_embeds, negative_image_embeds=negative_image_embeds, height=768, width=768).images[0]
+image
+```
+
+<div class="flex justify-center">
+    <img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/kandinsky-text-to-image.png"/>
+</div>
+
+</hfoption>
+<hfoption id="Kandinsky 3">
+
+Kandinsky 3는 prior 모델이 필요하지 않으므로 [`Kandinsky3Pipeline`]을 직접 불러오고 이미지 생성 프롬프트를 전달할 수 있습니다:
+
+```py
+from diffusers import Kandinsky3Pipeline
+import torch
+
+pipeline = Kandinsky3Pipeline.from_pretrained("kandinsky-community/kandinsky-3", variant="fp16", torch_dtype=torch.float16)
+pipeline.enable_model_cpu_offload()
+
+prompt = "A alien cheeseburger creature eating itself, claymation, cinematic, moody lighting"
+image = pipeline(prompt).images[0]
+image
+```
+
+</hfoption>
+</hfoptions>
+
+🤗 Diffusers는 또한 [`KandinskyCombinedPipeline`] 및 [`KandinskyV22CombinedPipeline`]이 포함된 end-to-end API를 제공하므로 prior 파이프라인과 text-to-image 변환 파이프라인을 별도로 불러올 필요가 없습니다. 결합된 파이프라인은 prior 모델과 디코더를 모두 자동으로 불러옵니다. 원하는 경우 `prior_guidance_scale` 및 `prior_num_inference_steps` 매개 변수를 사용하여 prior 파이프라인에 대해 다른 값을 설정할 수 있습니다.
+
+내부에서 결합된 파이프라인을 자동으로 호출하려면 [`AutoPipelineForText2Image`]를 사용합니다:
+
+<hfoptions id="text-to-image">
+<hfoption id="Kandinsky 2.1">
+
+```py
+from diffusers import AutoPipelineForText2Image
+import torch
+
+pipeline = AutoPipelineForText2Image.from_pretrained("kandinsky-community/kandinsky-2-1", torch_dtype=torch.float16)
+pipeline.enable_model_cpu_offload()
+
+prompt = "A alien cheeseburger creature eating itself, claymation, cinematic, moody lighting"
+negative_prompt = "low quality, bad quality"
+
+image = pipeline(prompt=prompt, negative_prompt=negative_prompt, prior_guidance_scale=1.0, guidance_scale=4.0, height=768, width=768).images[0]
+image
+```
+
+</hfoption>
+<hfoption id="Kandinsky 2.2">
+
+```py
+from diffusers import AutoPipelineForText2Image
+import torch
+
+pipeline = AutoPipelineForText2Image.from_pretrained("kandinsky-community/kandinsky-2-2-decoder", torch_dtype=torch.float16)
+pipeline.enable_model_cpu_offload()
+
+prompt = "A alien cheeseburger creature eating itself, claymation, cinematic, moody lighting"
+negative_prompt = "low quality, bad quality"
+
+image = pipeline(prompt=prompt, negative_prompt=negative_prompt, prior_guidance_scale=1.0, guidance_scale=4.0, height=768, width=768).images[0]
+image
+```
+
+</hfoption>
+</hfoptions>
+
+## Image-to-image
+
+Image-to-image 경우, 초기 이미지와 텍스트 프롬프트를 전달하여 파이프라인에 이미지를 conditioning합니다. Prior 파이프라인을 불러오는 것으로 시작합니다:
+
+<hfoptions id="image-to-image">
+<hfoption id="Kandinsky 2.1">
+
+```py
+import torch
+from diffusers import KandinskyImg2ImgPipeline, KandinskyPriorPipeline
+
+prior_pipeline = KandinskyPriorPipeline.from_pretrained("kandinsky-community/kandinsky-2-1-prior", torch_dtype=torch.float16, use_safetensors=True).to("cuda")
+pipeline = KandinskyImg2ImgPipeline.from_pretrained("kandinsky-community/kandinsky-2-1", torch_dtype=torch.float16, use_safetensors=True).to("cuda")
+```
+
+</hfoption>
+<hfoption id="Kandinsky 2.2">
+
+```py
+import torch
+from diffusers import KandinskyV22Img2ImgPipeline, KandinskyPriorPipeline
+
+prior_pipeline = KandinskyPriorPipeline.from_pretrained("kandinsky-community/kandinsky-2-2-prior", torch_dtype=torch.float16, use_safetensors=True).to("cuda")
+pipeline = KandinskyV22Img2ImgPipeline.from_pretrained("kandinsky-community/kandinsky-2-2-decoder", torch_dtype=torch.float16, use_safetensors=True).to("cuda")
+```
+
+</hfoption>
+<hfoption id="Kandinsky 3">
+
+Kandinsky 3는 prior 모델이 필요하지 않으므로 image-to-image 파이프라인을 직접 불러올 수 있습니다:
+
+```py
+from diffusers import Kandinsky3Img2ImgPipeline
+from diffusers.utils import load_image
+import torch
+
+pipeline = Kandinsky3Img2ImgPipeline.from_pretrained("kandinsky-community/kandinsky-3", variant="fp16", torch_dtype=torch.float16)
+pipeline.enable_model_cpu_offload()
+```
+
+</hfoption>
+</hfoptions>
+
+Conditioning할 이미지를 다운로드합니다:
+
+```py
+from diffusers.utils import load_image
+
+# 이미지 다운로드
+url = "https://raw.githubusercontent.com/CompVis/stable-diffusion/main/assets/stable-samples/img2img/sketch-mountains-input.jpg"
+original_image = load_image(url)
+original_image = original_image.resize((768, 512))
+```
+
+<div class="flex justify-center">
+    <img class="rounded-xl" src="https://raw.githubusercontent.com/CompVis/stable-diffusion/main/assets/stable-samples/img2img/sketch-mountains-input.jpg"/>
+</div>
+
+Prior 파이프라인으로 `image_embeds`와 `negative_image_embeds`를 생성합니다:
+
+```py
+prompt = "A fantasy landscape, Cinematic lighting"
+negative_prompt = "low quality, bad quality"
+
+image_embeds, negative_image_embeds = prior_pipeline(prompt, negative_prompt).to_tuple()
+```
+
+이제 원본 이미지와 모든 프롬프트 및 임베딩을 파이프라인으로 전달하여 이미지를 생성합니다:
+
+<hfoptions id="image-to-image">
+<hfoption id="Kandinsky 2.1">
+
+```py
+from diffusers.utils import make_image_grid
+
+image = pipeline(prompt, negative_prompt=negative_prompt, image=original_image, image_embeds=image_embeds, negative_image_embeds=negative_image_embeds, height=768, width=768, strength=0.3).images[0]
+make_image_grid([original_image.resize((512, 512)), image.resize((512, 512))], rows=1, cols=2)
+```
+
+<div class="flex justify-center">
+    <img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/kandinsky-docs/img2img_fantasyland.png"/>
+</div>
+
+</hfoption>
+<hfoption id="Kandinsky 2.2">
+
+```py
+from diffusers.utils import make_image_grid
+
+image = pipeline(image=original_image, image_embeds=image_embeds, negative_image_embeds=negative_image_embeds, height=768, width=768, strength=0.3).images[0]
+make_image_grid([original_image.resize((512, 512)), image.resize((512, 512))], rows=1, cols=2)
+```
+
+<div class="flex justify-center">
+    <img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/kandinsky-image-to-image.png"/>
+</div>
+
+</hfoption>
+<hfoption id="Kandinsky 3">
+
+```py
+image = pipeline(prompt, negative_prompt=negative_prompt, image=image, strength=0.75, num_inference_steps=25).images[0]
+image
+```
+
+</hfoption>
+</hfoptions>
+
+또한 🤗 Diffusers에서는 [`KandinskyImg2ImgCombinedPipeline`] 및 [`KandinskyV22Img2ImgCombinedPipeline`]이 포함된 end-to-end API를 제공하므로 prior 파이프라인과 image-to-image 파이프라인을 별도로 불러올 필요가 없습니다. 결합된 파이프라인은 prior 모델과 디코더를 모두 자동으로 불러옵니다. 원하는 경우 `prior_guidance_scale` 및 `prior_num_inference_steps` 매개 변수를 사용하여 이전 파이프라인에 대해 다른 값을 설정할 수 있습니다.
+
+내부에서 결합된 파이프라인을 자동으로 호출하려면 [`AutoPipelineForImage2Image`]를 사용합니다:
+
+<hfoptions id="image-to-image">
+<hfoption id="Kandinsky 2.1">
+
+```py
+from diffusers import AutoPipelineForImage2Image
+from diffusers.utils import make_image_grid, load_image
+import torch
+
+pipeline = AutoPipelineForImage2Image.from_pretrained("kandinsky-community/kandinsky-2-1", torch_dtype=torch.float16, use_safetensors=True)
+pipeline.enable_model_cpu_offload()
+
+prompt = "A fantasy landscape, Cinematic lighting"
+negative_prompt = "low quality, bad quality"
+
+url = "https://raw.githubusercontent.com/CompVis/stable-diffusion/main/assets/stable-samples/img2img/sketch-mountains-input.jpg"
+original_image = load_image(url)
+
+original_image.thumbnail((768, 768))
+
+image = pipeline(prompt=prompt, negative_prompt=negative_prompt, image=original_image, strength=0.3).images[0]
+make_image_grid([original_image.resize((512, 512)), image.resize((512, 512))], rows=1, cols=2)
+```
+
+</hfoption>
+<hfoption id="Kandinsky 2.2">
+
+```py
+from diffusers import AutoPipelineForImage2Image
+from diffusers.utils import make_image_grid, load_image
+import torch
+
+pipeline = AutoPipelineForImage2Image.from_pretrained("kandinsky-community/kandinsky-2-2-decoder", torch_dtype=torch.float16)
+pipeline.enable_model_cpu_offload()
+
+prompt = "A fantasy landscape, Cinematic lighting"
+negative_prompt = "low quality, bad quality"
+
+url = "https://raw.githubusercontent.com/CompVis/stable-diffusion/main/assets/stable-samples/img2img/sketch-mountains-input.jpg"
+original_image = load_image(url)
+
+original_image.thumbnail((768, 768))
+
+image = pipeline(prompt=prompt, negative_prompt=negative_prompt, image=original_image, strength=0.3).images[0]
+make_image_grid([original_image.resize((512, 512)), image.resize((512, 512))], rows=1, cols=2)
+```
+
+</hfoption>
+</hfoptions>
+
+## Inpainting
+
+<Tip warning={true}>
+
+⚠️ Kandinsky 모델은 이제 검은색 픽셀 대신 ⬜️ **흰색 픽셀**을 사용하여 마스크 영역을 표현합니다. 프로덕션에서 [`KandinskyInpaintPipeline`]을 사용하는 경우 흰색 픽셀을 사용하도록 마스크를 변경해야 합니다:
+
+```py
+# PIL 입력에 대해
+import PIL.ImageOps
+mask = PIL.ImageOps.invert(mask)
+
+# PyTorch와 NumPy 입력에 대해
+mask = 1 - mask
+```
+
+</Tip>
+
+인페인팅에서는 원본 이미지, 원본 이미지에서 대체할 영역의 마스크, 인페인팅할 내용에 대한 텍스트 프롬프트가 필요합니다. Prior 파이프라인을 불러옵니다:
+
+<hfoptions id="inpaint">
+<hfoption id="Kandinsky 2.1">
+
+```py
+from diffusers import KandinskyInpaintPipeline, KandinskyPriorPipeline
+from diffusers.utils import load_image, make_image_grid
+import torch
+import numpy as np
+from PIL import Image
+
+prior_pipeline = KandinskyPriorPipeline.from_pretrained("kandinsky-community/kandinsky-2-1-prior", torch_dtype=torch.float16, use_safetensors=True).to("cuda")
+pipeline = KandinskyInpaintPipeline.from_pretrained("kandinsky-community/kandinsky-2-1-inpaint", torch_dtype=torch.float16, use_safetensors=True).to("cuda")
+```
+
+</hfoption>
+<hfoption id="Kandinsky 2.2">
+
+```py
+from diffusers import KandinskyV22InpaintPipeline, KandinskyV22PriorPipeline
+from diffusers.utils import load_image, make_image_grid
+import torch
+import numpy as np
+from PIL import Image
+
+prior_pipeline = KandinskyV22PriorPipeline.from_pretrained("kandinsky-community/kandinsky-2-2-prior", torch_dtype=torch.float16, use_safetensors=True).to("cuda")
+pipeline = KandinskyV22InpaintPipeline.from_pretrained("kandinsky-community/kandinsky-2-2-decoder-inpaint", torch_dtype=torch.float16, use_safetensors=True).to("cuda")
+```
+
+</hfoption>
+</hfoptions>
+
+초기 이미지를 불러오고 마스크를 생성합니다:
+
+```py
+init_image = load_image("https://huggingface.co/datasets/hf-internal-testing/diffusers-images/resolve/main/kandinsky/cat.png")
+mask = np.zeros((768, 768), dtype=np.float32)
+# mask area above cat's head
+mask[:250, 250:-250] = 1
+```
+
+Prior 파이프라인으로 임베딩을 생성합니다:
+
+```py
+prompt = "a hat"
+prior_output = prior_pipeline(prompt)
+```
+
+이제 이미지 생성을 위해 초기 이미지, 마스크, 프롬프트와 임베딩을 파이프라인에 전달합니다:
+
+<hfoptions id="inpaint">
+<hfoption id="Kandinsky 2.1">
+
+```py
+output_image = pipeline(prompt, image=init_image, mask_image=mask, **prior_output, height=768, width=768, num_inference_steps=150).images[0]
+mask = Image.fromarray((mask*255).astype('uint8'), 'L')
+make_image_grid([init_image, mask, output_image], rows=1, cols=3)
+```
+
+<div class="flex justify-center">
+    <img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/kandinsky-docs/inpaint_cat_hat.png"/>
+</div>
+
+</hfoption>
+<hfoption id="Kandinsky 2.2">
+
+```py
+output_image = pipeline(image=init_image, mask_image=mask, **prior_output, height=768, width=768, num_inference_steps=150).images[0]
+mask = Image.fromarray((mask*255).astype('uint8'), 'L')
+make_image_grid([init_image, mask, output_image], rows=1, cols=3)
+```
+
+<div class="flex justify-center">
+    <img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/kandinskyv22-inpaint.png"/>
+</div>
+
+</hfoption>
+</hfoptions>
+
+[`KandinskyInpaintCombinedPipeline`] 및 [`KandinskyV22InpaintCombinedPipeline`]을 사용하여 내부에서 prior 및 디코더 파이프라인을 함께 호출할 수 있습니다. 이를 위해 [`AutoPipelineForInpainting`]을 사용합니다:
+
+<hfoptions id="inpaint">
+<hfoption id="Kandinsky 2.1">
+
+```py
+import torch
+import numpy as np
+from PIL import Image
+from diffusers import AutoPipelineForInpainting
+from diffusers.utils import load_image, make_image_grid
+
+pipe = AutoPipelineForInpainting.from_pretrained("kandinsky-community/kandinsky-2-1-inpaint", torch_dtype=torch.float16)
+pipe.enable_model_cpu_offload()
+
+init_image = load_image("https://huggingface.co/datasets/hf-internal-testing/diffusers-images/resolve/main/kandinsky/cat.png")
+mask = np.zeros((768, 768), dtype=np.float32)
+# 고양이 머리 위 마스크 지역
+mask[:250, 250:-250] = 1
+prompt = "a hat"
+
+output_image = pipe(prompt=prompt, image=init_image, mask_image=mask).images[0]
+mask = Image.fromarray((mask*255).astype('uint8'), 'L')
+make_image_grid([init_image, mask, output_image], rows=1, cols=3)
+```
+
+</hfoption>
+<hfoption id="Kandinsky 2.2">
+
+```py
+import torch
+import numpy as np
+from PIL import Image
+from diffusers import AutoPipelineForInpainting
+from diffusers.utils import load_image, make_image_grid
+
+pipe = AutoPipelineForInpainting.from_pretrained("kandinsky-community/kandinsky-2-2-decoder-inpaint", torch_dtype=torch.float16)
+pipe.enable_model_cpu_offload()
+
+init_image = load_image("https://huggingface.co/datasets/hf-internal-testing/diffusers-images/resolve/main/kandinsky/cat.png")
+mask = np.zeros((768, 768), dtype=np.float32)
+# 고양이 머리 위 마스크 영역
+mask[:250, 250:-250] = 1
+prompt = "a hat"
+
+output_image = pipe(prompt=prompt, image=original_image, mask_image=mask).images[0]
+mask = Image.fromarray((mask*255).astype('uint8'), 'L')
+make_image_grid([init_image, mask, output_image], rows=1, cols=3)
+```
+
+</hfoption>
+</hfoptions>
+
+## Interpolation (보간)
+
+Interpolation(보간)을 사용하면 이미지와 텍스트 임베딩 사이의 latent space를 탐색할 수 있어 prior 모델의 중간 결과물을 볼 수 있는 멋진 방법입니다. Prior 파이프라인과 보간하려는 두 개의 이미지를 불러옵니다:
+
+<hfoptions id="interpolate">
+<hfoption id="Kandinsky 2.1">
+
+```py
+from diffusers import KandinskyPriorPipeline, KandinskyPipeline
+from diffusers.utils import load_image, make_image_grid
+import torch
+
+prior_pipeline = KandinskyPriorPipeline.from_pretrained("kandinsky-community/kandinsky-2-1-prior", torch_dtype=torch.float16, use_safetensors=True).to("cuda")
+img_1 = load_image("https://huggingface.co/datasets/hf-internal-testing/diffusers-images/resolve/main/kandinsky/cat.png")
+img_2 = load_image("https://huggingface.co/datasets/hf-internal-testing/diffusers-images/resolve/main/kandinsky/starry_night.jpeg")
+make_image_grid([img_1.resize((512,512)), img_2.resize((512,512))], rows=1, cols=2)
+```
+
+</hfoption>
+<hfoption id="Kandinsky 2.2">
+
+```py
+from diffusers import KandinskyV22PriorPipeline, KandinskyV22Pipeline
+from diffusers.utils import load_image, make_image_grid
+import torch
+
+prior_pipeline = KandinskyV22PriorPipeline.from_pretrained("kandinsky-community/kandinsky-2-2-prior", torch_dtype=torch.float16, use_safetensors=True).to("cuda")
+img_1 = load_image("https://huggingface.co/datasets/hf-internal-testing/diffusers-images/resolve/main/kandinsky/cat.png")
+img_2 = load_image("https://huggingface.co/datasets/hf-internal-testing/diffusers-images/resolve/main/kandinsky/starry_night.jpeg")
+make_image_grid([img_1.resize((512,512)), img_2.resize((512,512))], rows=1, cols=2)
+```
+
+</hfoption>
+</hfoptions>
+
+<div class="flex gap-4">
+  <div>
+    <img class="rounded-xl" src="https://huggingface.co/datasets/hf-internal-testing/diffusers-images/resolve/main/kandinsky/cat.png"/>
+    <figcaption class="mt-2 text-center text-sm text-gray-500">a cat</figcaption>
+  </div>
+  <div>
+    <img class="rounded-xl" src="https://huggingface.co/datasets/hf-internal-testing/diffusers-images/resolve/main/kandinsky/starry_night.jpeg"/>
+    <figcaption class="mt-2 text-center text-sm text-gray-500">Van Gogh's Starry Night painting</figcaption>
+  </div>
+</div>
+
+보간할 텍스트 또는 이미지를 지정하고 각 텍스트 또는 이미지에 대한 가중치를 설정합니다. 가중치를 실험하여 보간에 어떤 영향을 미치는지 확인하세요!
+
+```py
+images_texts = ["a cat", img_1, img_2]
+weights = [0.3, 0.3, 0.4]
+```
+
+`interpolate` 함수를 호출하여 임베딩을 생성한 다음, 파이프라인으로 전달하여 이미지를 생성합니다:
+
+<hfoptions id="interpolate">
+<hfoption id="Kandinsky 2.1">
+
+```py
+# 프롬프트는 빈칸으로 남겨도 됩니다
+prompt = ""
+prior_out = prior_pipeline.interpolate(images_texts, weights)
+
+pipeline = KandinskyPipeline.from_pretrained("kandinsky-community/kandinsky-2-1", torch_dtype=torch.float16, use_safetensors=True).to("cuda")
+
+image = pipeline(prompt, **prior_out, height=768, width=768).images[0]
+image
+```
+
+<div class="flex justify-center">
+    <img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/kandinsky-docs/starry_cat.png"/>
+</div>
+
+</hfoption>
+<hfoption id="Kandinsky 2.2">
+
+```py
+# 프롬프트는 빈칸으로 남겨도 됩니다
+prompt = ""
+prior_out = prior_pipeline.interpolate(images_texts, weights)
+
+pipeline = KandinskyV22Pipeline.from_pretrained("kandinsky-community/kandinsky-2-2-decoder", torch_dtype=torch.float16, use_safetensors=True).to("cuda")
+
+image = pipeline(prompt, **prior_out, height=768, width=768).images[0]
+image
+```
+
+<div class="flex justify-center">
+    <img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/kandinskyv22-interpolate.png"/>
+</div>
+
+</hfoption>
+</hfoptions>
+
+## ControlNet
+
+<Tip warning={true}>
+
+⚠️ ControlNet은 Kandinsky 2.2에서만 지원됩니다!
+
+</Tip>
+
+ControlNet을 사용하면 depth map이나 edge detection와 같은 추가 입력을 통해 사전학습된 large diffusion 모델을 conditioning할 수 있습니다. 예를 들어, 모델이 depth map의 구조를 이해하고 보존할 수 있도록 깊이 맵으로 Kandinsky 2.2를 conditioning할 수 있습니다.
+
+이미지를 불러오고 depth map을 추출해 보겠습니다:
+
+```py
+from diffusers.utils import load_image
+
+img = load_image(
+    "https://huggingface.co/datasets/hf-internal-testing/diffusers-images/resolve/main/kandinskyv22/cat.png"
+).resize((768, 768))
+img
+```
+
+<div class="flex justify-center">
+    <img class="rounded-xl" src="https://huggingface.co/datasets/hf-internal-testing/diffusers-images/resolve/main/kandinskyv22/cat.png"/>
+</div>
+
+그런 다음 🤗 Transformers의 `depth-estimation` [`~transformers.Pipeline`]을 사용하여 이미지를 처리해 depth map을 구할 수 있습니다:
+
+```py
+import torch
+import numpy as np
+
+from transformers import pipeline
+
+def make_hint(image, depth_estimator):
+    image = depth_estimator(image)["depth"]
+    image = np.array(image)
+    image = image[:, :, None]
+    image = np.concatenate([image, image, image], axis=2)
+    detected_map = torch.from_numpy(image).float() / 255.0
+    hint = detected_map.permute(2, 0, 1)
+    return hint
+
+depth_estimator = pipeline("depth-estimation")
+hint = make_hint(img, depth_estimator).unsqueeze(0).half().to("cuda")
+```
+
+### Text-to-image [[controlnet-text-to-image]]
+
+Prior 파이프라인과 [`KandinskyV22ControlnetPipeline`]를 불러옵니다:
+
+```py
+from diffusers import KandinskyV22PriorPipeline, KandinskyV22ControlnetPipeline
+
+prior_pipeline = KandinskyV22PriorPipeline.from_pretrained(
+    "kandinsky-community/kandinsky-2-2-prior", torch_dtype=torch.float16, use_safetensors=True
+).to("cuda")
+
+pipeline = KandinskyV22ControlnetPipeline.from_pretrained(
+    "kandinsky-community/kandinsky-2-2-controlnet-depth", torch_dtype=torch.float16
+).to("cuda")
+```
+
+프롬프트와 negative 프롬프트로 이미지 임베딩을 생성합니다:
+
+```py
+prompt = "A robot, 4k photo"
+negative_prior_prompt = "lowres, text, error, cropped, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, out of frame, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck, username, watermark, signature"
+
+generator = torch.Generator(device="cuda").manual_seed(43)
+
+image_emb, zero_image_emb = prior_pipeline(
+    prompt=prompt, negative_prompt=negative_prior_prompt, generator=generator
+).to_tuple()
+```
+
+마지막으로 이미지 임베딩과 depth 이미지를 [`KandinskyV22ControlnetPipeline`]에 전달하여 이미지를 생성합니다:
+
+```py
+image = pipeline(image_embeds=image_emb, negative_image_embeds=zero_image_emb, hint=hint, num_inference_steps=50, generator=generator, height=768, width=768).images[0]
+image
+```
+
+<div class="flex justify-center">
+    <img class="rounded-xl" src="https://huggingface.co/datasets/hf-internal-testing/diffusers-images/resolve/main/kandinskyv22/robot_cat_text2img.png"/>
+</div>
+
+### Image-to-image [[controlnet-image-to-image]]
+
+ControlNet을 사용한 image-to-image의 경우, 다음을 사용할 필요가 있습니다:
+
+- [`KandinskyV22PriorEmb2EmbPipeline`]로 텍스트 프롬프트와 이미지에서 이미지 임베딩을 생성합니다.
+- [`KandinskyV22ControlnetImg2ImgPipeline`]로 초기 이미지와 이미지 임베딩에서 이미지를 생성합니다.
+
+🤗 Transformers에서 `depth-estimation` [`~transformers.Pipeline`]을 사용하여 고양이의 초기 이미지의 depth map을 처리해 추출합니다:
+
+```py
+import torch
+import numpy as np
+
+from diffusers import KandinskyV22PriorEmb2EmbPipeline, KandinskyV22ControlnetImg2ImgPipeline
+from diffusers.utils import load_image
+from transformers import pipeline
+
+img = load_image(
+    "https://huggingface.co/datasets/hf-internal-testing/diffusers-images/resolve/main/kandinskyv22/cat.png"
+).resize((768, 768))
+
+def make_hint(image, depth_estimator):
+    image = depth_estimator(image)["depth"]
+    image = np.array(image)
+    image = image[:, :, None]
+    image = np.concatenate([image, image, image], axis=2)
+    detected_map = torch.from_numpy(image).float() / 255.0
+    hint = detected_map.permute(2, 0, 1)
+    return hint
+
+depth_estimator = pipeline("depth-estimation")
+hint = make_hint(img, depth_estimator).unsqueeze(0).half().to("cuda")
+```
+
+Prior 파이프라인과 [`KandinskyV22ControlnetImg2ImgPipeline`]을 불러옵니다:
+
+```py
+prior_pipeline = KandinskyV22PriorEmb2EmbPipeline.from_pretrained(
+    "kandinsky-community/kandinsky-2-2-prior", torch_dtype=torch.float16, use_safetensors=True
+).to("cuda")
+
+pipeline = KandinskyV22ControlnetImg2ImgPipeline.from_pretrained(
+    "kandinsky-community/kandinsky-2-2-controlnet-depth", torch_dtype=torch.float16
+).to("cuda")
+```
+
+텍스트 프롬프트와 초기 이미지를 이전 파이프라인에 전달하여 이미지 임베딩을 생성합니다:
+
+```py
+prompt = "A robot, 4k photo"
+negative_prior_prompt = "lowres, text, error, cropped, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, out of frame, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck, username, watermark, signature"
+
+generator = torch.Generator(device="cuda").manual_seed(43)
+
+img_emb = prior_pipeline(prompt=prompt, image=img, strength=0.85, generator=generator)
+negative_emb = prior_pipeline(prompt=negative_prior_prompt, image=img, strength=1, generator=generator)
+```
+
+이제 [`KandinskyV22ControlnetImg2ImgPipeline`]을 실행하여 초기 이미지와 이미지 임베딩으로부터 이미지를 생성할 수 있습니다:
+
+```py
+image = pipeline(image=img, strength=0.5, image_embeds=img_emb.image_embeds, negative_image_embeds=negative_emb.image_embeds, hint=hint, num_inference_steps=50, generator=generator, height=768, width=768).images[0]
+make_image_grid([img.resize((512, 512)), image.resize((512, 512))], rows=1, cols=2)
+```
+
+<div class="flex justify-center">
+    <img class="rounded-xl" src="https://huggingface.co/datasets/hf-internal-testing/diffusers-images/resolve/main/kandinskyv22/robot_cat.png"/>
+</div>
+
+## 최적화
+
+Kandinsky는 mapping을 생성하기 위한 prior 파이프라인과 latents를 이미지로 디코딩하기 위한 두 번째 파이프라인이 필요하다는 점에서 독특합니다. 대부분의 계산이 두 번째 파이프라인에서 이루어지므로 최적화의 노력은 두 번째 파이프라인에 집중되어야 합니다. 다음은 추론 중 Kandinsky키를 개선하기 위한 몇 가지 팁입니다.
+
+1. PyTorch < 2.0을 사용할 경우 [xFormers](../optimization/xformers)을 활성화합니다.
+
+```diff
+  from diffusers import DiffusionPipeline
+  import torch
+
+  pipe = DiffusionPipeline.from_pretrained("kandinsky-community/kandinsky-2-1", torch_dtype=torch.float16)
++ pipe.enable_xformers_memory_efficient_attention()
+```
+
+2. PyTorch >= 2.0을 사용할 경우 `torch.compile`을 활성화하여 scaled dot-product attention (SDPA)를 자동으로 사용하도록 합니다:
+
+```diff
+  pipe.unet.to(memory_format=torch.channels_last)
++ pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
+```
+
+이는 attention processor를 명시적으로 [`~models.attention_processor.AttnAddedKVProcessor2_0`]을 사용하도록 설정하는 것과 동일합니다:
+
+```py
+from diffusers.models.attention_processor import AttnAddedKVProcessor2_0
+
+pipe.unet.set_attn_processor(AttnAddedKVProcessor2_0())
+```
+
+3. 메모리 부족 오류를 방지하기 위해 [`~KandinskyPriorPipeline.enable_model_cpu_offload`]를 사용하여 모델을 CPU로 오프로드합니다:
+
+```diff
+  from diffusers import DiffusionPipeline
+  import torch
+
+  pipe = DiffusionPipeline.from_pretrained("kandinsky-community/kandinsky-2-1", torch_dtype=torch.float16)
++ pipe.enable_model_cpu_offload()
+```
+
+4. 기본적으로 text-to-image 파이프라인은 [`DDIMScheduler`]를 사용하지만, [`DDPMScheduler`]와 같은 다른 스케줄러로 대체하여 추론 속도와 이미지 품질 간의 균형에 어떤 영향을 미치는지 확인할 수 있습니다:
+
+```py
+from diffusers import DDPMScheduler
+from diffusers import DiffusionPipeline
+
+scheduler = DDPMScheduler.from_pretrained("kandinsky-community/kandinsky-2-1", subfolder="ddpm_scheduler")
+pipe = DiffusionPipeline.from_pretrained("kandinsky-community/kandinsky-2-1", scheduler=scheduler, torch_dtype=torch.float16, use_safetensors=True).to("cuda")
+```

docs/source/ko/using-diffusers/loading.md

@@ -307,7 +307,7 @@ print(pipeline)
 
 위의 코드 출력 결과를 확인해보면, `pipeline`은 [`StableDiffusionPipeline`]의 인스턴스이며, 다음과 같이 총 7개의 컴포넌트로 구성된다는 것을 알 수 있습니다.
 
-- `"feature_extractor"`: [`~transformers.CLIPFeatureExtractor`]의 인스턴스
+- `"feature_extractor"`: [`~transformers.CLIPImageProcessor`]의 인스턴스
 - `"safety_checker"`: 유해한 컨텐츠를 스크리닝하기 위한 [컴포넌트](https://github.com/huggingface/diffusers/blob/e55687e1e15407f60f32242027b7bb8170e58266/src/diffusers/pipelines/stable_diffusion/safety_checker.py#L32)
 - `"scheduler"`: [`PNDMScheduler`]의 인스턴스
 - `"text_encoder"`: [`~transformers.CLIPTextModel`]의 인스턴스

docs/source/ko/using-diffusers/loading_adapters.md

@@ -0,0 +1,359 @@
+<!--Copyright 2024 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License.
+-->
+
+# 어댑터 불러오기
+
+[[open-in-colab]]
+
+특정 물체의 이미지 또는 특정 스타일의 이미지를 생성하도록 diffusion 모델을 개인화하기 위한 몇 가지 [학습](../training/overview) 기법이 있습니다. 이러한 학습 방법은 각각 다른 유형의 어댑터를 생성합니다. 일부 어댑터는 완전히 새로운 모델을 생성하는 반면, 다른 어댑터는 임베딩 또는 가중치의 작은 부분만 수정합니다. 이는 각 어댑터의 로딩 프로세스도 다르다는 것을 의미합니다.
+
+이 가이드에서는 DreamBooth, textual inversion 및 LoRA 가중치를 불러오는 방법을 설명합니다.
+
+<Tip>
+
+사용할 체크포인트와 임베딩은 [Stable Diffusion Conceptualizer](https://huggingface.co/spaces/sd-concepts-library/stable-diffusion-conceptualizer), [LoRA the Explorer](https://huggingface.co/spaces/multimodalart/LoraTheExplorer), [Diffusers Models Gallery](https://huggingface.co/spaces/huggingface-projects/diffusers-gallery)에서 찾아보시기 바랍니다.
+
+</Tip>
+
+## DreamBooth
+
+[DreamBooth](https://dreambooth.github.io/)는 물체의 여러 이미지에 대한 *diffusion 모델 전체*를 미세 조정하여 새로운 스타일과 설정으로 해당 물체의 이미지를 생성합니다. 이 방법은 모델이 물체 이미지와 연관시키는 방법을 학습하는 프롬프트에 특수 단어를 사용하는 방식으로 작동합니다. 모든 학습 방법 중에서 드림부스는 전체 체크포인트 모델이기 때문에 파일 크기가 가장 큽니다(보통 몇 GB).
+
+Hergé가 그린 단 10개의 이미지로 학습된 [herge_style](https://huggingface.co/sd-dreambooth-library/herge-style) 체크포인트를 불러와 해당 스타일의 이미지를 생성해 보겠습니다. 이 모델이 작동하려면 체크포인트를 트리거하는 프롬프트에 특수 단어 `herge_style`을 포함시켜야 합니다:
+
+```py
+from diffusers import AutoPipelineForText2Image
+import torch
+
+pipeline = AutoPipelineForText2Image.from_pretrained("sd-dreambooth-library/herge-style", torch_dtype=torch.float16).to("cuda")
+prompt = "A cute herge_style brown bear eating a slice of pizza, stunning color scheme, masterpiece, illustration"
+image = pipeline(prompt).images[0]
+image
+```
+
+<div class="flex justify-center">
+    <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/load_dreambooth.png" />
+</div>
+
+## Textual inversion
+
+[Textual inversion](https://textual-inversion.github.io/)은 DreamBooth와 매우 유사하며 몇 개의 이미지만으로 특정 개념(스타일, 개체)을 생성하는 diffusion 모델을 개인화할 수도 있습니다. 이 방법은 프롬프트에 특정 단어를 입력하면 해당 이미지를 나타내는 새로운 임베딩을 학습하고 찾아내는 방식으로 작동합니다. 결과적으로 diffusion 모델 가중치는 동일하게 유지되고 훈련 프로세스는 비교적 작은(수 KB) 파일을 생성합니다.
+
+Textual inversion은 임베딩을 생성하기 때문에 DreamBooth처럼 단독으로 사용할 수 없으며 또 다른 모델이 필요합니다.
+
+```py
+from diffusers import AutoPipelineForText2Image
+import torch
+
+pipeline = AutoPipelineForText2Image.from_pretrained("runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16).to("cuda")
+```
+
+이제 [`~loaders.TextualInversionLoaderMixin.load_textual_inversion`] 메서드를 사용하여 textual inversion 임베딩을 불러와 이미지를 생성할 수 있습니다. [sd-concepts-library/gta5-artwork](https://huggingface.co/sd-concepts-library/gta5-artwork) 임베딩을 불러와 보겠습니다. 이를 트리거하려면 프롬프트에 특수 단어 `<gta5-artwork>`를 포함시켜야 합니다:
+
+```py
+pipeline.load_textual_inversion("sd-concepts-library/gta5-artwork")
+prompt = "A cute brown bear eating a slice of pizza, stunning color scheme, masterpiece, illustration, <gta5-artwork> style"
+image = pipeline(prompt).images[0]
+image
+```
+
+<div class="flex justify-center">
+    <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/load_txt_embed.png" />
+</div>
+
+Textual inversion은 또한 바람직하지 않은 사물에 대해 *네거티브 임베딩*을 생성하여 모델이 흐릿한 이미지나 손의 추가 손가락과 같은 바람직하지 않은 사물이 포함된 이미지를 생성하지 못하도록 학습할 수도 있습니다. 이는 프롬프트를 빠르게 개선하는 것이 쉬운 방법이 될 수 있습니다. 이는 이전과 같이 임베딩을 [`~loaders.TextualInversionLoaderMixin.load_textual_inversion`]으로 불러오지만 이번에는 두 개의 매개변수가 더 필요합니다:
+
+- `weight_name`: 파일이 특정 이름의 🤗 Diffusers 형식으로 저장된 경우이거나 파일이 A1111 형식으로 저장된 경우, 불러올 가중치 파일을 지정합니다.
+- `token`: 임베딩을 트리거하기 위해 프롬프트에서 사용할 특수 단어를 지정합니다.
+
+[sayakpaul/EasyNegative-test](https://huggingface.co/sayakpaul/EasyNegative-test) 임베딩을 불러와 보겠습니다:
+
+```py
+pipeline.load_textual_inversion(
+    "sayakpaul/EasyNegative-test", weight_name="EasyNegative.safetensors", token="EasyNegative"
+)
+```
+
+이제 `token`을 사용해 네거티브 임베딩이 있는 이미지를 생성할 수 있습니다:
+
+```py
+prompt = "A cute brown bear eating a slice of pizza, stunning color scheme, masterpiece, illustration, EasyNegative"
+negative_prompt = "EasyNegative"
+
+image = pipeline(prompt, negative_prompt=negative_prompt, num_inference_steps=50).images[0]
+image
+```
+
+<div class="flex justify-center">
+    <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/load_neg_embed.png" />
+</div>
+
+## LoRA
+
+[Low-Rank Adaptation (LoRA)](https://huggingface.co/papers/2106.09685)은 속도가 빠르고 파일 크기가 (수백 MB로) 작기 때문에 널리 사용되는 학습 기법입니다. 이 가이드의 다른 방법과 마찬가지로, LoRA는 몇 장의 이미지만으로 새로운 스타일을 학습하도록 모델을 학습시킬 수 있습니다. 이는 diffusion 모델에 새로운 가중치를 삽입한 다음 전체 모델 대신 새로운 가중치만 학습시키는 방식으로 작동합니다. 따라서 LoRA를 더 빠르게 학습시키고 더 쉽게 저장할 수 있습니다.
+
+<Tip>
+
+LoRA는 다른 학습 방법과 함께 사용할 수 있는 매우 일반적인 학습 기법입니다. 예를 들어, DreamBooth와 LoRA로 모델을 학습하는 것이 일반적입니다. 또한 새롭고 고유한 이미지를 생성하기 위해 여러 개의 LoRA를 불러오고 병합하는 것이 점점 더 일반화되고 있습니다. 병합은 이 불러오기 가이드의 범위를 벗어나므로 자세한 내용은 심층적인 [LoRA 병합](merge_loras) 가이드에서 확인할 수 있습니다.
+
+</Tip>
+
+LoRA는 다른 모델과 함께 사용해야 합니다:
+
+```py
+from diffusers import AutoPipelineForText2Image
+import torch
+
+pipeline = AutoPipelineForText2Image.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.float16).to("cuda")
+```
+
+그리고 [`~loaders.LoraLoaderMixin.load_lora_weights`] 메서드를 사용하여 [ostris/super-cereal-sdxl-lora](https://huggingface.co/ostris/super-cereal-sdxl-lora) 가중치를 불러오고 리포지토리에서 가중치 파일명을 지정합니다:
+
+```py
+pipeline.load_lora_weights("ostris/super-cereal-sdxl-lora", weight_name="cereal_box_sdxl_v1.safetensors")
+prompt = "bears, pizza bites"
+image = pipeline(prompt).images[0]
+image
+```
+
+<div class="flex justify-center">
+    <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/load_lora.png" />
+</div>
+
+[`~loaders.LoraLoaderMixin.load_lora_weights`] 메서드는 LoRA 가중치를 UNet과 텍스트 인코더에 모두 불러옵니다. 이 메서드는 해당 케이스에서 LoRA를 불러오는 데 선호되는 방식입니다:
+
+- LoRA 가중치에 UNet 및 텍스트 인코더에 대한 별도의 식별자가 없는 경우
+- LoRA 가중치에 UNet과 텍스트 인코더에 대한 별도의 식별자가 있는 경우
+
+하지만 LoRA 가중치만 UNet에 로드해야 하는 경우에는 [`~loaders.UNet2DConditionLoadersMixin.load_attn_procs`] 메서드를 사용할 수 있습니다. [jbilcke-hf/sdxl-cinematic-1](https://huggingface.co/jbilcke-hf/sdxl-cinematic-1) LoRA를 불러와 보겠습니다:
+
+```py
+from diffusers import AutoPipelineForText2Image
+import torch
+
+pipeline = AutoPipelineForText2Image.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.float16).to("cuda")
+pipeline.unet.load_attn_procs("jbilcke-hf/sdxl-cinematic-1", weight_name="pytorch_lora_weights.safetensors")
+
+# 프롬프트에서 cnmt를 사용하여 LoRA를 트리거합니다.
+prompt = "A cute cnmt eating a slice of pizza, stunning color scheme, masterpiece, illustration"
+image = pipeline(prompt).images[0]
+image
+```
+
+<div class="flex justify-center">
+    <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/load_attn_proc.png" />
+</div>
+
+LoRA 가중치를 언로드하려면 [`~loaders.LoraLoaderMixin.unload_lora_weights`] 메서드를 사용하여 LoRA 가중치를 삭제하고 모델을 원래 가중치로 복원합니다:
+
+```py
+pipeline.unload_lora_weights()
+```
+
+### LoRA 가중치 스케일 조정하기
+
+[`~loaders.LoraLoaderMixin.load_lora_weights`] 및 [`~loaders.UNet2DConditionLoadersMixin.load_attn_procs`] 모두 `cross_attention_kwargs={"scale": 0.5}` 파라미터를 전달하여 얼마나 LoRA 가중치를 사용할지 조정할 수 있습니다. 값이 `0`이면 기본 모델 가중치만 사용하는 것과 같고, 값이 `1`이면 완전히 미세 조정된 LoRA를 사용하는 것과 같습니다.
+
+레이어당 사용되는 LoRA 가중치의 양을 보다 세밀하게 제어하려면 [`~loaders.LoraLoaderMixin.set_adapters`]를 사용하여 각 레이어의 가중치를 얼마만큼 조정할지 지정하는 딕셔너리를 전달할 수 있습니다.
+```python
+pipe = ... # 파이프라인 생성
+pipe.load_lora_weights(..., adapter_name="my_adapter")
+scales = {
+    "text_encoder": 0.5,
+    "text_encoder_2": 0.5,  # 파이프에 두 번째 텍스트 인코더가 있는 경우에만 사용 가능
+    "unet": {
+        "down": 0.9,  # down 부분의 모든 트랜스포머는 스케일 0.9를 사용
+        # "mid"  # 이 예제에서는 "mid"가 지정되지 않았으므로 중간 부분의 모든 트랜스포머는 기본 스케일 1.0을 사용
+        "up": {
+            "block_0": 0.6,  # # up의 0번째 블록에 있는 3개의 트랜스포머는 모두 스케일 0.6을 사용
+            "block_1": [0.4, 0.8, 1.0],  # up의 첫 번째 블록에 있는 3개의 트랜스포머는 각각 스케일 0.4, 0.8, 1.0을 사용
+        }
+    }
+}
+pipe.set_adapters("my_adapter", scales)
+```
+
+이는 여러 어댑터에서도 작동합니다. 방법은 [이 가이드](https://huggingface.co/docs/diffusers/tutorials/using_peft_for_inference#customize-adapters-strength)를 참조하세요.
+
+<Tip warning={true}>
+
+현재 [`~loaders.LoraLoaderMixin.set_adapters`]는 어텐션 가중치의 스케일링만 지원합니다. LoRA에 다른 부분(예: resnets or down-/upsamplers)이 있는 경우 1.0의 스케일을 유지합니다.
+
+</Tip>
+
+### Kohya와 TheLastBen
+
+커뮤니티에서 인기 있는 다른 LoRA trainer로는 [Kohya](https://github.com/kohya-ss/sd-scripts/)와 [TheLastBen](https://github.com/TheLastBen/fast-stable-diffusion)의 trainer가 있습니다. 이 trainer들은 🤗 Diffusers가 훈련한 것과는 다른 LoRA 체크포인트를 생성하지만, 같은 방식으로 불러올 수 있습니다.
+
+<hfoptions id="other-trainers">
+<hfoption id="Kohya">
+
+Kohya LoRA를 불러오기 위해, 예시로 [Civitai](https://civitai.com/)에서 [Blueprintify SD XL 1.0](https://civitai.com/models/150986/blueprintify-sd-xl-10) 체크포인트를 다운로드합니다:
+
+```sh
+!wget https://civitai.com/api/download/models/168776 -O blueprintify-sd-xl-10.safetensors
+```
+
+LoRA 체크포인트를 [`~loaders.LoraLoaderMixin.load_lora_weights`] 메서드로 불러오고 `weight_name` 파라미터에 파일명을 지정합니다:
+
+```py
+from diffusers import AutoPipelineForText2Image
+import torch
+
+pipeline = AutoPipelineForText2Image.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.float16).to("cuda")
+pipeline.load_lora_weights("path/to/weights", weight_name="blueprintify-sd-xl-10.safetensors")
+```
+
+이미지를 생성합니다:
+
+```py
+# LoRA를 트리거하기 위해 bl3uprint를 프롬프트에 사용
+prompt = "bl3uprint, a highly detailed blueprint of the eiffel tower, explaining how to build all parts, many txt, blueprint grid backdrop"
+image = pipeline(prompt).images[0]
+image
+```
+
+<Tip warning={true}>
+
+Kohya LoRA를 🤗 Diffusers와 함께 사용할 때 몇 가지 제한 사항이 있습니다:
+
+- [여기](https://github.com/huggingface/diffusers/pull/4287/#issuecomment-1655110736)에 설명된 여러 가지 이유로 인해 이미지가 ComfyUI와 같은 UI에서 생성된 이미지와 다르게 보일 수 있습니다.
+- [LyCORIS 체크포인트](https://github.com/KohakuBlueleaf/LyCORIS)가 완전히 지원되지 않습니다. [`~loaders.LoraLoaderMixin.load_lora_weights`] 메서드는 LoRA 및 LoCon 모듈로 LyCORIS 체크포인트를 불러올 수 있지만, Hada 및 LoKR은 지원되지 않습니다.
+
+</Tip>
+
+</hfoption>
+<hfoption id="TheLastBen">
+
+TheLastBen에서 체크포인트를 불러오는 방법은 매우 유사합니다. 예를 들어, [TheLastBen/William_Eggleston_Style_SDXL](https://huggingface.co/TheLastBen/William_Eggleston_Style_SDXL) 체크포인트를 불러오려면:
+
+```py
+from diffusers import AutoPipelineForText2Image
+import torch
+
+pipeline = AutoPipelineForText2Image.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.float16).to("cuda")
+pipeline.load_lora_weights("TheLastBen/William_Eggleston_Style_SDXL", weight_name="wegg.safetensors")
+
+# LoRA를 트리거하기 위해 william eggleston를 프롬프트에 사용
+prompt = "a house by william eggleston, sunrays, beautiful, sunlight, sunrays, beautiful"
+image = pipeline(prompt=prompt).images[0]
+image
+```
+
+</hfoption>
+</hfoptions>
+
+## IP-Adapter
+
+[IP-Adapter](https://ip-adapter.github.io/)는 모든 diffusion 모델에 이미지 프롬프트를 사용할 수 있는 경량 어댑터입니다. 이 어댑터는 이미지와 텍스트 feature의 cross-attention 레이어를 분리하여 작동합니다. 다른 모든 모델 컴포넌트튼 freeze되고 UNet의 embedded 이미지 features만 학습됩니다. 따라서 IP-Adapter 파일은 일반적으로 최대 100MB에 불과합니다.
+
+다양한 작업과 구체적인 사용 사례에 IP-Adapter를 사용하는 방법에 대한 자세한 내용은 [IP-Adapter](../using-diffusers/ip_adapter) 가이드에서 확인할 수 있습니다.
+
+> [!TIP]
+> Diffusers는 현재 가장 많이 사용되는 일부 파이프라인에 대해서만 IP-Adapter를 지원합니다. 멋진 사용 사례가 있는 지원되지 않는 파이프라인에 IP-Adapter를 통합하고 싶다면 언제든지 기능 요청을 여세요!
+> 공식 IP-Adapter 체크포인트는 [h94/IP-Adapter](https://huggingface.co/h94/IP-Adapter)에서 확인할 수 있습니다.
+
+시작하려면 Stable Diffusion 체크포인트를 불러오세요.
+
+```py
+from diffusers import AutoPipelineForText2Image
+import torch
+from diffusers.utils import load_image
+
+pipeline = AutoPipelineForText2Image.from_pretrained("runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16).to("cuda")
+```
+
+그런 다음 IP-Adapter 가중치를 불러와 [`~loaders.IPAdapterMixin.load_ip_adapter`] 메서드를 사용하여 파이프라인에 추가합니다.
+
+```py
+pipeline.load_ip_adapter("h94/IP-Adapter", subfolder="models", weight_name="ip-adapter_sd15.bin")
+```
+
+불러온 뒤, 이미지 및 텍스트 프롬프트가 있는 파이프라인을 사용하여 이미지 생성 프로세스를 가이드할 수 있습니다.
+
+```py
+image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/load_neg_embed.png")
+generator = torch.Generator(device="cpu").manual_seed(33)
+images = pipeline(
+    prompt='best quality, high quality, wearing sunglasses',
+    ip_adapter_image=image,
+    negative_prompt="monochrome, lowres, bad anatomy, worst quality, low quality",
+    num_inference_steps=50,
+    generator=generator,
+).images[0]
+images
+```
+
+<div class="flex justify-center">
+    <img src="https://huggingface.co/datasets/YiYiXu/testing-images/resolve/main/ip-bear.png" />
+</div>
+
+### IP-Adapter Plus
+
+IP-Adapter는 이미지 인코더를 사용하여 이미지 feature를 생성합니다. IP-Adapter 리포지토리에 `image_encoder` 하위 폴더가 있는 경우, 이미지 인코더가 자동으로 불러와 파이프라인에 등록됩니다. 그렇지 않은 경우, [`~transformers.CLIPVisionModelWithProjection`] 모델을 사용하여 이미지 인코더를 명시적으로 불러와 파이프라인에 전달해야 합니다.
+
+이는 ViT-H 이미지 인코더를 사용하는 *IP-Adapter Plus* 체크포인트에 해당하는 케이스입니다.
+
+```py
+from transformers import CLIPVisionModelWithProjection
+
+image_encoder = CLIPVisionModelWithProjection.from_pretrained(
+    "h94/IP-Adapter",
+    subfolder="models/image_encoder",
+    torch_dtype=torch.float16
+)
+
+pipeline = AutoPipelineForText2Image.from_pretrained(
+    "stabilityai/stable-diffusion-xl-base-1.0",
+    image_encoder=image_encoder,
+    torch_dtype=torch.float16
+).to("cuda")
+
+pipeline.load_ip_adapter("h94/IP-Adapter", subfolder="sdxl_models", weight_name="ip-adapter-plus_sdxl_vit-h.safetensors")
+```
+
+### IP-Adapter Face ID 모델
+
+IP-Adapter FaceID 모델은 CLIP 이미지 임베딩 대신 `insightface`에서 생성한 이미지 임베딩을 사용하는 실험적인 IP Adapter입니다. 이러한 모델 중 일부는 LoRA를 사용하여 ID 일관성을 개선하기도 합니다.
+이러한 모델을 사용하려면 `insightface`와 해당 요구 사항을 모두 설치해야 합니다.
+
+<Tip warning={true}>
+InsightFace 사전학습된 모델은 비상업적 연구 목적으로만 사용할 수 있으므로, IP-Adapter-FaceID 모델은 연구 목적으로만 릴리즈되었으며 상업적 용도로는 사용할 수 없습니다.
+</Tip>
+
+```py
+pipeline = AutoPipelineForText2Image.from_pretrained(
+    "stabilityai/stable-diffusion-xl-base-1.0",
+    torch_dtype=torch.float16
+).to("cuda")
+
+pipeline.load_ip_adapter("h94/IP-Adapter-FaceID", subfolder=None, weight_name="ip-adapter-faceid_sdxl.bin", image_encoder_folder=None)
+```
+
+두 가지 IP 어댑터 FaceID Plus 모델 중 하나를 사용하려는 경우, 이 모델들은 더 나은 사실감을 얻기 위해 `insightface`와 CLIP 이미지 임베딩을 모두 사용하므로, CLIP 이미지 인코더도 불러와야 합니다.
+
+```py
+from transformers import CLIPVisionModelWithProjection
+
+image_encoder = CLIPVisionModelWithProjection.from_pretrained(
+    "laion/CLIP-ViT-H-14-laion2B-s32B-b79K",
+    torch_dtype=torch.float16,
+)
+
+pipeline = AutoPipelineForText2Image.from_pretrained(
+    "runwayml/stable-diffusion-v1-5",
+    image_encoder=image_encoder,
+    torch_dtype=torch.float16
+).to("cuda")
+
+pipeline.load_ip_adapter("h94/IP-Adapter-FaceID", subfolder=None, weight_name="ip-adapter-faceid-plus_sd15.bin")
+```

docs/source/ko/using-diffusers/loading_overview.md

@@ -1,18 +0,0 @@
-<!--Copyright 2024 The HuggingFace Team. All rights reserved.
-
-Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
-the License. You may obtain a copy of the License at
-
-http://www.apache.org/licenses/LICENSE-2.0
-
-Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
-an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
-specific language governing permissions and limitations under the License.
--->
-
-# Overview
-
-🧨 Diffusers는 생성 작업을 위한 다양한 파이프라인, 모델, 스케줄러를 제공합니다. 이러한 컴포넌트를 최대한 간단하게 로드할 수 있도록 단일 통합 메서드인 `from_pretrained()`를 제공하여 Hugging Face [Hub](https://huggingface.co/models?library=diffusers&sort=downloads) 또는 로컬 머신에서 이러한 컴포넌트를 불러올 수 있습니다. 파이프라인이나 모델을 로드할 때마다, 최신 파일이 자동으로 다운로드되고 캐시되므로, 다음에 파일을 다시 다운로드하지 않고도 빠르게 재사용할 수 있습니다.
-
-이 섹션은 파이프라인 로딩, 파이프라인에서 다양한 컴포넌트를 로드하는 방법, 체크포인트 variants를 불러오는 방법, 그리고 커뮤니티 파이프라인을 불러오는 방법에 대해 알아야 할 모든 것들을 다룹니다. 또한 스케줄러를 불러오는 방법과 서로 다른 스케줄러를 사용할 때 발생하는 속도와 품질간의 트레이드 오프를 비교하는 방법 역시 다룹니다. 그리고 마지막으로 🧨 Diffusers와 함께 파이토치에서 사용할 수 있도록 KerasCV 체크포인트를 변환하고 불러오는 방법을 살펴봅니다.
-

docs/source/ko/using-diffusers/other-formats.md

@@ -127,7 +127,7 @@ image = pipeline(prompt, num_inference_steps=50).images[0]
 
 [Automatic1111](https://github.com/AUTOMATIC1111/stable-diffusion-webui) (A1111)은 Stable Diffusion을 위해 널리 사용되는 웹 UI로, [Civitai](https://civitai.com/) 와 같은 모델 공유 플랫폼을 지원합니다. 특히 LoRA 기법으로 학습된 모델은 학습 속도가 빠르고 완전히 파인튜닝된 모델보다 파일 크기가 훨씬 작기 때문에 인기가 높습니다.
 
-🤗 Diffusers는 [`~loaders.LoraLoaderMixin.load_lora_weights`]:를 사용하여 A1111 LoRA 체크포인트 불러오기를 지원합니다:
+🤗 Diffusers는 [`~loaders.StableDiffusionLoraLoaderMixin.load_lora_weights`]:를 사용하여 A1111 LoRA 체크포인트 불러오기를 지원합니다:
 
 ```py
 from diffusers import DiffusionPipeline, UniPCMultistepScheduler

docs/source/ko/using-diffusers/pipeline_overview.md

@@ -1,17 +0,0 @@
-<!--Copyright 2024 The HuggingFace Team. All rights reserved.
-
-Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
-the License. You may obtain a copy of the License at
-
-http://www.apache.org/licenses/LICENSE-2.0
-
-Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
-an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
-specific language governing permissions and limitations under the License.
--->
-
-# Overview
-
-파이프라인은 독립적으로 훈련된 모델과 스케줄러를 함께 모아서 추론을 위해 diffusion 시스템을 빠르고 쉽게 사용할 수 있는 방법을 제공하는 end-to-end 클래스입니다. 모델과 스케줄러의 특정 조합은 특수한 기능과 함께 [`StableDiffusionPipeline`] 또는 [`StableDiffusionControlNetPipeline`]과 같은 특정 파이프라인 유형을 정의합니다. 모든 파이프라인 유형은 기본 [`DiffusionPipeline`] 클래스에서 상속됩니다. 어느 체크포인트를 전달하면, 파이프라인 유형을 자동으로 감지하고 필요한 구성 요소들을 불러옵니다.
-
-이 섹션에서는 unconditional 이미지 생성, text-to-image 생성의 다양한 테크닉과 변화를 파이프라인에서 지원하는 작업들을 소개합니다. 프롬프트에 있는 특정 단어가 출력에 영향을 미치는 것을 조정하기 위해 재현성을 위한 시드 설정과 프롬프트에 가중치를 부여하는 것으로 생성 프로세스를 더 잘 제어하는 방법에 대해 배울 수 있습니다. 마지막으로 음성에서부터 이미지 생성과 같은 커스텀 작업을 위한 커뮤니티 파이프라인을 만드는 방법을 알 수 있습니다.

docs/source/ko/using-diffusers/push_to_hub.md

@@ -0,0 +1,177 @@
+<!--Copyright 2024 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License.
+-->
+
+# 파일들을 Hub로 푸시하기
+
+[[open-in-colab]]
+
+🤗 Diffusers는 모델, 스케줄러 또는 파이프라인을 Hub에 업로드할 수 있는 [`~diffusers.utils.PushToHubMixin`]을 제공합니다. 이는 Hub에 당신의 파일을 저장하는 쉬운 방법이며, 다른 사람들과 작업을 공유할 수도 있습니다. 실제적으로 [`~diffusers.utils.PushToHubMixin`]가 동작하는 방식은 다음과 같습니다:
+
+1. Hub에 리포지토리를 생성합니다.
+2. 나중에 다시 불러올 수 있도록 모델, 스케줄러 또는 파이프라인 파일을 저장합니다.
+3. 이러한 파일이 포함된 폴더를 Hub에 업로드합니다.
+
+이 가이드는 [`~diffusers.utils.PushToHubMixin`]을 사용하여 Hub에 파일을 업로드하는 방법을 보여줍니다.
+
+먼저 액세스 [토큰](https://huggingface.co/settings/tokens)으로 Hub 계정에 로그인해야 합니다:
+
+```py
+from huggingface_hub import notebook_login
+
+notebook_login()
+```
+
+## 모델
+
+모델을 허브에 푸시하려면 [`~diffusers.utils.PushToHubMixin.push_to_hub`]를 호출하고 Hub에 저장할 모델의 리포지토리 id를 지정합니다:
+
+```py
+from diffusers import ControlNetModel
+
+controlnet = ControlNetModel(
+    block_out_channels=(32, 64),
+    layers_per_block=2,
+    in_channels=4,
+    down_block_types=("DownBlock2D", "CrossAttnDownBlock2D"),
+    cross_attention_dim=32,
+    conditioning_embedding_out_channels=(16, 32),
+)
+controlnet.push_to_hub("my-controlnet-model")
+```
+
+모델의 경우 Hub에 푸시할 가중치의 [*변형*](loading#checkpoint-variants)을 지정할 수도 있습니다. 예를 들어, `fp16` 가중치를 푸시하려면 다음과 같이 하세요:
+
+```py
+controlnet.push_to_hub("my-controlnet-model", variant="fp16")
+```
+
+[`~diffusers.utils.PushToHubMixin.push_to_hub`] 함수는 모델의 `config.json` 파일을 저장하고 가중치는 `safetensors` 형식으로 자동으로 저장됩니다.
+
+이제 Hub의 리포지토리에서 모델을 다시 불러올 수 있습니다:
+
+```py
+model = ControlNetModel.from_pretrained("your-namespace/my-controlnet-model")
+```
+
+## 스케줄러
+
+스케줄러를 허브에 푸시하려면 [`~diffusers.utils.PushToHubMixin.push_to_hub`]를 호출하고 Hub에 저장할 스케줄러의 리포지토리 id를 지정합니다:
+
+```py
+from diffusers import DDIMScheduler
+
+scheduler = DDIMScheduler(
+    beta_start=0.00085,
+    beta_end=0.012,
+    beta_schedule="scaled_linear",
+    clip_sample=False,
+    set_alpha_to_one=False,
+)
+scheduler.push_to_hub("my-controlnet-scheduler")
+```
+
+[`~diffusers.utils.PushToHubMixin.push_to_hub`] 함수는 스케줄러의 `scheduler_config.json` 파일을 지정된 리포지토리에 저장합니다.
+
+이제 허브의 리포지토리에서 스케줄러를 다시 불러올 수 있습니다:
+
+```py
+scheduler = DDIMScheduler.from_pretrained("your-namepsace/my-controlnet-scheduler")
+```
+
+## 파이프라인
+
+모든 컴포넌트가 포함된 전체 파이프라인을 Hub로 푸시할 수도 있습니다. 예를 들어, 원하는 파라미터로 [`StableDiffusionPipeline`]의 컴포넌트들을 초기화합니다:
+
+```py
+from diffusers import (
+    UNet2DConditionModel,
+    AutoencoderKL,
+    DDIMScheduler,
+    StableDiffusionPipeline,
+)
+from transformers import CLIPTextModel, CLIPTextConfig, CLIPTokenizer
+
+unet = UNet2DConditionModel(
+    block_out_channels=(32, 64),
+    layers_per_block=2,
+    sample_size=32,
+    in_channels=4,
+    out_channels=4,
+    down_block_types=("DownBlock2D", "CrossAttnDownBlock2D"),
+    up_block_types=("CrossAttnUpBlock2D", "UpBlock2D"),
+    cross_attention_dim=32,
+)
+
+scheduler = DDIMScheduler(
+    beta_start=0.00085,
+    beta_end=0.012,
+    beta_schedule="scaled_linear",
+    clip_sample=False,
+    set_alpha_to_one=False,
+)
+
+vae = AutoencoderKL(
+    block_out_channels=[32, 64],
+    in_channels=3,
+    out_channels=3,
+    down_block_types=["DownEncoderBlock2D", "DownEncoderBlock2D"],
+    up_block_types=["UpDecoderBlock2D", "UpDecoderBlock2D"],
+    latent_channels=4,
+)
+
+text_encoder_config = CLIPTextConfig(
+    bos_token_id=0,
+    eos_token_id=2,
+    hidden_size=32,
+    intermediate_size=37,
+    layer_norm_eps=1e-05,
+    num_attention_heads=4,
+    num_hidden_layers=5,
+    pad_token_id=1,
+    vocab_size=1000,
+)
+text_encoder = CLIPTextModel(text_encoder_config)
+tokenizer = CLIPTokenizer.from_pretrained("hf-internal-testing/tiny-random-clip")
+```
+
+모든 컴포넌트들을 [`StableDiffusionPipeline`]에 전달하고 [`~diffusers.utils.PushToHubMixin.push_to_hub`]를 호출하여 파이프라인을 Hub로 푸시합니다:
+
+```py
+components = {
+    "unet": unet,
+    "scheduler": scheduler,
+    "vae": vae,
+    "text_encoder": text_encoder,
+    "tokenizer": tokenizer,
+    "safety_checker": None,
+    "feature_extractor": None,
+}
+
+pipeline = StableDiffusionPipeline(**components)
+pipeline.push_to_hub("my-pipeline")
+```
+
+[`~diffusers.utils.PushToHubMixin.push_to_hub`] 함수는 각 컴포넌트를 리포지토리의 하위 폴더에 저장합니다. 이제 Hub의 리포지토리에서 파이프라인을 다시 불러올 수 있습니다:
+
+```py
+pipeline = StableDiffusionPipeline.from_pretrained("your-namespace/my-pipeline")
+```
+
+## 비공개
+
+모델, 스케줄러 또는 파이프라인 파일들을 비공개로 두려면 [`~diffusers.utils.PushToHubMixin.push_to_hub`] 함수에서 `private=True`를 설정하세요:
+
+```py
+controlnet.push_to_hub("my-controlnet-model-private", private=True)
+```
+
+비공개 리포지토리는 본인만 볼 수 있으며 다른 사용자는 리포지토리를 복제할 수 없고 리포지토리가 검색 결과에 표시되지 않습니다. 사용자가 비공개 리포지토리의 URL을 가지고 있더라도 `404 - Sorry, we can't find the page you are looking for`라는 메시지가 표시됩니다. 비공개 리포지토리에서 모델을 로드하려면 [로그인](https://huggingface.co/docs/huggingface_hub/quick-start#login) 상태여야 합니다.

docs/source/ko/using-diffusers/reproducibility.md

@@ -1,201 +0,0 @@
-<!--Copyright 2024 The HuggingFace Team. All rights reserved.
-
-Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
-the License. You may obtain a copy of the License at
-
-http://www.apache.org/licenses/LICENSE-2.0
-
-Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
-an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
-specific language governing permissions and limitations under the License.
--->
-
-# 재현 가능한 파이프라인 생성하기
-
-[[open-in-colab]]
-
-재현성은 테스트, 결과 재현, 그리고 [이미지 퀄리티 높이기](resuing_seeds)에서 중요합니다.
-그러나 diffusion 모델의 무작위성은 매번 모델이 돌아갈 때마다 파이프라인이 다른 이미지를 생성할 수 있도록 하는 이유로 필요합니다.
-플랫폼 간에 정확하게 동일한 결과를 얻을 수는 없지만, 특정 허용 범위 내에서 릴리스 및 플랫폼 간에 결과를 재현할 수는 있습니다.
-그럼에도 diffusion 파이프라인과 체크포인트에 따라 허용 오차가 달라집니다.
-
-diffusion 모델에서 무작위성의 원천을 제어하거나 결정론적 알고리즘을 사용하는 방법을 이해하는 것이 중요한 이유입니다.
-
-<Tip>
-
-💡 Pytorch의 [재현성에 대한 선언](https://pytorch.org/docs/stable/notes/randomness.html)를 꼭 읽어보길 추천합니다:
-
-> 완전하게 재현가능한 결과는 Pytorch 배포, 개별적인 커밋, 혹은 다른 플랫폼들에서 보장되지 않습니다.
-> 또한, 결과는 CPU와 GPU 실행간에 심지어 같은 seed를 사용할 때도 재현 가능하지 않을 수 있습니다.
-
-</Tip>
-
-## 무작위성 제어하기
-
-추론에서, 파이프라인은 노이즈를 줄이기 위해 가우시안 노이즈를 생성하거나 스케줄링 단계에 노이즈를 더하는 등의 랜덤 샘플링 실행에 크게 의존합니다,
-
-[DDIMPipeline](https://huggingface.co/docs/diffusers/v0.18.0/en/api/pipelines/ddim#diffusers.DDIMPipeline)에서 두 추론 단계 이후의 텐서 값을 살펴보세요:
-
-```python
-from diffusers import DDIMPipeline
-import numpy as np
-
-model_id = "google/ddpm-cifar10-32"
-
-# 모델과 스케줄러를 불러오기
-ddim = DDIMPipeline.from_pretrained(model_id)
-
-# 두 개의 단계에 대해서 파이프라인을 실행하고 numpy tensor로 값을 반환하기
-image = ddim(num_inference_steps=2, output_type="np").images
-print(np.abs(image).sum())
-```
-
-위의 코드를 실행하면 하나의 값이 나오지만, 다시 실행하면 다른 값이 나옵니다. 무슨 일이 일어나고 있는 걸까요?
-
-파이프라인이 실행될 때마다, [torch.randn](https://pytorch.org/docs/stable/generated/torch.randn.html)은
-단계적으로 노이즈 제거되는 가우시안 노이즈가 생성하기 위한 다른 랜덤 seed를 사용합니다.
-
-그러나 동일한 이미지를 안정적으로 생성해야 하는 경우에는 CPU에서 파이프라인을 실행하는지 GPU에서 실행하는지에 따라 달라집니다.
-
-### CPU
-
-CPU에서 재현 가능한 결과를 생성하려면, PyTorch [Generator](https://pytorch.org/docs/stable/generated/torch.randn.html)로 seed를 고정합니다:
-
-```python
-import torch
-from diffusers import DDIMPipeline
-import numpy as np
-
-model_id = "google/ddpm-cifar10-32"
-
-# 모델과 스케줄러 불러오기
-ddim = DDIMPipeline.from_pretrained(model_id)
-
-# 재현성을 위해 generator 만들기
-generator = torch.Generator(device="cpu").manual_seed(0)
-
-# 두 개의 단계에 대해서 파이프라인을 실행하고 numpy tensor로 값을 반환하기
-image = ddim(num_inference_steps=2, output_type="np", generator=generator).images
-print(np.abs(image).sum())
-```
-
-이제 위의 코드를 실행하면 seed를 가진 `Generator` 객체가 파이프라인의 모든 랜덤 함수에 전달되므로 항상 `1491.1711` 값이 출력됩니다.
-
-특정 하드웨어 및 PyTorch 버전에서 이 코드 예제를 실행하면 동일하지는 않더라도 유사한 결과를 얻을 수 있습니다.
-
-<Tip>
-
-💡 처음에는 시드를 나타내는 정수값 대신에 `Generator` 개체를 파이프라인에 전달하는 것이 약간 비직관적일 수 있지만,
-`Generator`는 순차적으로 여러 파이프라인에 전달될 수 있는 \랜덤상태\이기 때문에 PyTorch에서 확률론적 모델을 다룰 때 권장되는 설계입니다.
-
-</Tip>
-
-### GPU
-
-예를 들면, GPU 상에서 같은 코드 예시를 실행하면:
-
-```python
-import torch
-from diffusers import DDIMPipeline
-import numpy as np
-
-model_id = "google/ddpm-cifar10-32"
-
-# 모델과 스케줄러 불러오기
-ddim = DDIMPipeline.from_pretrained(model_id)
-ddim.to("cuda")
-
-# 재현성을 위한 generator 만들기
-generator = torch.Generator(device="cuda").manual_seed(0)
-
-# 두 개의 단계에 대해서 파이프라인을 실행하고 numpy tensor로 값을 반환하기
-image = ddim(num_inference_steps=2, output_type="np", generator=generator).images
-print(np.abs(image).sum())
-```
-
-GPU가 CPU와 다른 난수 생성기를 사용하기 때문에 동일한 시드를 사용하더라도 결과가 같지 않습니다.
-
-이 문제를 피하기 위해 🧨 Diffusers는 CPU에 임의의 노이즈를 생성한 다음 필요에 따라 텐서를 GPU로 이동시키는
-[randn_tensor()](https://huggingface.co/docs/diffusers/v0.18.0/en/api/utilities#diffusers.utils.randn_tensor)기능을 가지고 있습니다.
-`randn_tensor` 기능은 파이프라인 내부 어디에서나 사용되므로 파이프라인이 GPU에서 실행되더라도 **항상** CPU `Generator`를 통과할 수 있습니다.
-
-이제 결과에 훨씬 더 다가왔습니다!
-
-```python
-import torch
-from diffusers import DDIMPipeline
-import numpy as np
-
-model_id = "google/ddpm-cifar10-32"
-
-# 모델과 스케줄러 불러오기
-ddim = DDIMPipeline.from_pretrained(model_id)
-ddim.to("cuda")
-
-#재현성을 위한 generator 만들기 (GPU에 올리지 않도록 조심한다!)
-generator = torch.manual_seed(0)
-
-# 두 개의 단계에 대해서 파이프라인을 실행하고 numpy tensor로 값을 반환하기
-image = ddim(num_inference_steps=2, output_type="np", generator=generator).images
-print(np.abs(image).sum())
-```
-
-<Tip>
-
-💡 재현성이 중요한 경우에는 항상 CPU generator를 전달하는 것이 좋습니다.
-성능 손실은 무시할 수 없는 경우가 많으며 파이프라인이 GPU에서 실행되었을 때보다 훨씬 더 비슷한 값을 생성할 수 있습니다.
-
-</Tip>
-
-마지막으로 [UnCLIPPipeline](https://huggingface.co/docs/diffusers/v0.18.0/en/api/pipelines/unclip#diffusers.UnCLIPPipeline)과 같은
-더 복잡한 파이프라인의 경우, 이들은 종종 정밀 오차 전파에 극도로 취약합니다.
-다른 GPU 하드웨어 또는 PyTorch 버전에서 유사한 결과를 기대하지 마세요.
-이 경우 완전한 재현성을 위해 완전히 동일한 하드웨어 및 PyTorch 버전을 실행해야 합니다.
-
-## 결정론적 알고리즘
-
-결정론적 알고리즘을 사용하여 재현 가능한 파이프라인을 생성하도록 PyTorch를 구성할 수도 있습니다.
-그러나 결정론적 알고리즘은 비결정론적 알고리즘보다 느리고 성능이 저하될 수 있습니다.
-하지만 재현성이 중요하다면, 이것이 최선의 방법입니다!
-
-둘 이상의 CUDA 스트림에서 작업이 시작될 때 비결정론적 동작이 발생합니다.
-이 문제를 방지하려면 환경 변수 [CUBLAS_WORKSPACE_CONFIG](https://docs.nvidia.com/cuda/cublas/index.html#results-reproducibility)를 `:16:8`로 설정해서
-런타임 중에 오직 하나의 버퍼 크리만 사용하도록 설정합니다.
-
-PyTorch는 일반적으로 가장 빠른 알고리즘을 선택하기 위해 여러 알고리즘을 벤치마킹합니다.
-하지만 재현성을 원하는 경우, 벤치마크가 매 순간 다른 알고리즘을 선택할 수 있기 때문에 이 기능을 사용하지 않도록 설정해야 합니다.
-마지막으로, [torch.use_deterministic_algorithms](https://pytorch.org/docs/stable/generated/torch.use_deterministic_algorithms.html)에
-`True`를 통과시켜 결정론적 알고리즘이 활성화 되도록 합니다.
-
-```py
-import os
-
-os.environ["CUBLAS_WORKSPACE_CONFIG"] = ":16:8"
-
-torch.backends.cudnn.benchmark = False
-torch.use_deterministic_algorithms(True)
-```
-
-이제 동일한 파이프라인을 두번 실행하면 동일한 결과를 얻을 수 있습니다.
-
-```py
-import torch
-from diffusers import DDIMScheduler, StableDiffusionPipeline
-import numpy as np
-
-model_id = "runwayml/stable-diffusion-v1-5"
-pipe = StableDiffusionPipeline.from_pretrained(model_id).to("cuda")
-pipe.scheduler = DDIMScheduler.from_config(pipe.scheduler.config)
-g = torch.Generator(device="cuda")
-
-prompt = "A bear is playing a guitar on Times Square"
-
-g.manual_seed(0)
-result1 = pipe(prompt=prompt, num_inference_steps=50, generator=g, output_type="latent").images
-
-g.manual_seed(0)
-result2 = pipe(prompt=prompt, num_inference_steps=50, generator=g, output_type="latent").images
-
-print("L_inf dist = ", abs(result1 - result2).max())
-"L_inf dist =  tensor(0., device='cuda:0')"
-```

docs/source/ko/using-diffusers/reusing_seeds.md

@@ -1,63 +0,0 @@
-<!--Copyright 2024 The HuggingFace Team. All rights reserved.
-
-Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
-the License. You may obtain a copy of the License at
-
-http://www.apache.org/licenses/LICENSE-2.0
-
-Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
-an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
-specific language governing permissions and limitations under the License.
--->
-
-# Deterministic(결정적) 생성을 통한 이미지 품질 개선
-
-생성된 이미지의 품질을 개선하는 일반적인 방법은 *결정적 batch(배치) 생성*을 사용하는 것입니다. 이 방법은 이미지 batch(배치)를 생성하고 두 번째 추론 라운드에서 더 자세한 프롬프트와 함께 개선할 이미지 하나를 선택하는 것입니다. 핵심은 일괄 이미지 생성을 위해 파이프라인에 [`torch.Generator`](https://pytorch.org/docs/stable/generated/torch.Generator.html#generator) 목록을 전달하고, 각 `Generator`를 시드에 연결하여 이미지에 재사용할 수 있도록 하는 것입니다.
-
-예를 들어 [`runwayml/stable-diffusion-v1-5`](runwayml/stable-diffusion-v1-5)를 사용하여 다음 프롬프트의 여러 버전을 생성해 봅시다.
-
-```py
-prompt = "Labrador in the style of Vermeer"
-```
-
-(가능하다면) 파이프라인을 [`DiffusionPipeline.from_pretrained`]로 인스턴스화하여 GPU에 배치합니다.
-
-```python
->>> from diffusers import DiffusionPipeline
-
->>> pipe = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16)
->>> pipe = pipe.to("cuda")
-```
-
-이제 네 개의 서로 다른 `Generator`를 정의하고 각 `Generator`에 시드(`0` ~ `3`)를 할당하여 나중에 특정 이미지에 대해 `Generator`를 재사용할 수 있도록 합니다.
-
-```python
->>> import torch
-
->>> generator = [torch.Generator(device="cuda").manual_seed(i) for i in range(4)]
-```
-
-이미지를 생성하고 살펴봅니다.
-
-```python
->>> images = pipe(prompt, generator=generator, num_images_per_prompt=4).images
->>> images
-```
-
-![img](https://huggingface.co/datasets/diffusers/diffusers-images-docs/resolve/main/reusabe_seeds.jpg)
-
-이 예제에서는 첫 번째 이미지를 개선했지만 실제로는 원하는 모든 이미지를 사용할 수 있습니다(심지어 두 개의 눈이 있는 이미지도!). 첫 번째 이미지에서는 시드가 '0'인 '생성기'를 사용했기 때문에 두 번째 추론 라운드에서는 이 '생성기'를 재사용할 것입니다. 이미지의 품질을 개선하려면 프롬프트에 몇 가지 텍스트를 추가합니다:
-
-```python
-prompt = [prompt + t for t in [", highly realistic", ", artsy", ", trending", ", colorful"]]
-generator = [torch.Generator(device="cuda").manual_seed(0) for i in range(4)]
-```
-
-시드가 `0`인 제너레이터 4개를 생성하고, 이전 라운드의 첫 번째 이미지처럼 보이는 다른 이미지 batch(배치)를 생성합니다!
-
-```python
->>> images = pipe(prompt, generator=generator).images
->>> images
-```
-
-![img](https://huggingface.co/datasets/diffusers/diffusers-images-docs/resolve/main/reusabe_seeds_2.jpg)

docs/source/ko/using-diffusers/sdxl_turbo.md

@@ -0,0 +1,114 @@
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License.
+-->
+
+# Stable Diffusion XL Turbo
+
+[[open-in-colab]]
+
+SDXL Turbo는 adversarial time-distilled(적대적 시간 전이) [Stable Diffusion XL](https://huggingface.co/papers/2307.01952)(SDXL) 모델로, 단 한 번의 스텝만으로 추론을 실행할 수 있습니다.
+
+이 가이드에서는 text-to-image와 image-to-image를 위한 SDXL-Turbo를 사용하는 방법을 설명합니다.
+
+시작하기 전에 다음 라이브러리가 설치되어 있는지 확인하세요:
+
+```py
+# Colab에서 필요한 라이브러리를 설치하기 위해 주석을 제외하세요
+#!pip install -q diffusers transformers accelerate
+```
+
+## 모델 체크포인트 불러오기
+
+모델 가중치는 Hub의 별도 하위 폴더 또는 로컬에 저장할 수 있으며, 이 경우 [`~StableDiffusionXLPipeline.from_pretrained`] 메서드를 사용해야 합니다:
+
+```py
+from diffusers import AutoPipelineForText2Image, AutoPipelineForImage2Image
+import torch
+
+pipeline = AutoPipelineForText2Image.from_pretrained("stabilityai/sdxl-turbo", torch_dtype=torch.float16, variant="fp16")
+pipeline = pipeline.to("cuda")
+```
+
+또한 [`~StableDiffusionXLPipeline.from_single_file`] 메서드를 사용하여 허브 또는 로컬에서 단일 파일 형식(`.ckpt` 또는 `.safetensors`)으로 저장된 모델 체크포인트를 불러올 수도 있습니다:
+
+```py
+from diffusers import StableDiffusionXLPipeline
+import torch
+
+pipeline = StableDiffusionXLPipeline.from_single_file(
+    "https://huggingface.co/stabilityai/sdxl-turbo/blob/main/sd_xl_turbo_1.0_fp16.safetensors", torch_dtype=torch.float16)
+pipeline = pipeline.to("cuda")
+```
+
+## Text-to-image
+
+Text-to-image의 경우 텍스트 프롬프트를 전달합니다. 기본적으로 SDXL Turbo는 512x512 이미지를 생성하며, 이 해상도에서 최상의 결과를 제공합니다. `height` 및 `width` 매개 변수를 768x768 또는 1024x1024로 설정할 수 있지만 이 경우 품질 저하를 예상할 수 있습니다.
+
+모델이 `guidance_scale` 없이 학습되었으므로 이를 0.0으로 설정해 비활성화해야 합니다. 단일 추론 스텝만으로도 고품질 이미지를 생성할 수 있습니다.
+스텝 수를 2, 3 또는 4로 늘리면 이미지 품질이 향상됩니다.
+
+```py
+from diffusers import AutoPipelineForText2Image
+import torch
+
+pipeline_text2image = AutoPipelineForText2Image.from_pretrained("stabilityai/sdxl-turbo", torch_dtype=torch.float16, variant="fp16")
+pipeline_text2image = pipeline_text2image.to("cuda")
+
+prompt = "A cinematic shot of a baby racoon wearing an intricate italian priest robe."
+
+image = pipeline_text2image(prompt=prompt, guidance_scale=0.0, num_inference_steps=1).images[0]
+image
+```
+
+<div class="flex justify-center">
+    <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/sdxl-turbo-text2img.png" alt="generated image of a racoon in a robe"/>
+</div>
+
+## Image-to-image
+
+Image-to-image 생성의 경우 `num_inference_steps * strength`가 1보다 크거나 같은지 확인하세요.
+Image-to-image 파이프라인은 아래 예제에서 `0.5 * 2.0 = 1` 스텝과 같이 `int(num_inference_steps * strength)` 스텝으로 실행됩니다.
+
+```py
+from diffusers import AutoPipelineForImage2Image
+from diffusers.utils import load_image, make_image_grid
+
+# 체크포인트를 불러올 때 추가 메모리 소모를 피하려면 from_pipe를 사용하세요.
+pipeline = AutoPipelineForImage2Image.from_pipe(pipeline_text2image).to("cuda")
+
+init_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png")
+init_image = init_image.resize((512, 512))
+
+prompt = "cat wizard, gandalf, lord of the rings, detailed, fantasy, cute, adorable, Pixar, Disney, 8k"
+
+image = pipeline(prompt, image=init_image, strength=0.5, guidance_scale=0.0, num_inference_steps=2).images[0]
+make_image_grid([init_image, image], rows=1, cols=2)
+```
+
+<div class="flex justify-center">
+    <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/sdxl-turbo-img2img.png" alt="Image-to-image generation sample using SDXL Turbo"/>
+</div>
+
+## SDXL Turbo 속도 훨씬 더 빠르게 하기
+
+- PyTorch 버전 2 이상을 사용하는 경우 UNet을 컴파일합니다. 첫 번째 추론 실행은 매우 느리지만 이후 실행은 훨씬 빨라집니다.
+
+```py
+pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
+```
+
+- 기본 VAE를 사용하는 경우, 각 생성 전후에 비용이 많이 드는 `dtype` 변환을 피하기 위해 `float32`로 유지하세요. 이 작업은 첫 생성 이전에 한 번만 수행하면 됩니다:
+
+```py
+pipe.upcast_vae()
+```
+
+또는, 커뮤니티 회원인 [`@madebyollin`](https://huggingface.co/madebyollin)이 만든 [16비트 VAE](https://huggingface.co/madebyollin/sdxl-vae-fp16-fix)를 사용할 수도 있으며, 이는 `float32`로 업캐스트할 필요가 없습니다.

docs/source/ko/using-diffusers/shap-e.md

@@ -0,0 +1,192 @@
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License.
+-->
+
+# Shap-E
+
+[[open-in-colab]]
+
+Shap-E는 비디오 게임 개발, 인테리어 디자인, 건축에 사용할 수 있는 3D 에셋을 생성하기 위한 conditional 모델입니다. 대규모 3D 에셋 데이터셋을 학습되었고, 각 오브젝트의 더 많은 뷰를 렌더링하고 4K point cloud 대신 16K를 생성하도록 후처리합니다. Shap-E 모델은 두 단계로 학습됩니다:
+
+1. 인코더가 3D 에셋의 포인트 클라우드와 렌더링된 뷰를 받아들이고 에셋을 나타내는 implicit functions의 파라미터를 출력합니다.
+2. 인코더가 생성한 latents를 바탕으로 diffusion 모델을 훈련하여 neural radiance fields(NeRF) 또는 textured 3D 메시를 생성하여 다운스트림 애플리케이션에서 3D 에셋을 더 쉽게 렌더링하고 사용할 수 있도록 합니다.
+
+이 가이드에서는 Shap-E를 사용하여 나만의 3D 에셋을 생성하는 방법을 보입니다!
+
+시작하기 전에 다음 라이브러리가 설치되어 있는지 확인하세요:
+
+```py
+# Colab에서 필요한 라이브러리를 설치하기 위해 주석을 제외하세요
+#!pip install -q diffusers transformers accelerate trimesh
+```
+
+## Text-to-3D
+
+3D 객체의 gif를 생성하려면 텍스트 프롬프트를 [`ShapEPipeline`]에 전달합니다. 파이프라인은 3D 객체를 생성하는 데 사용되는 이미지 프레임 리스트를 생성합니다.
+
+```py
+import torch
+from diffusers import ShapEPipeline
+
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+
+pipe = ShapEPipeline.from_pretrained("openai/shap-e", torch_dtype=torch.float16, variant="fp16")
+pipe = pipe.to(device)
+
+guidance_scale = 15.0
+prompt = ["A firecracker", "A birthday cupcake"]
+
+images = pipe(
+    prompt,
+    guidance_scale=guidance_scale,
+    num_inference_steps=64,
+    frame_size=256,
+).images
+```
+
+이제 [`~utils.export_to_gif`] 함수를 사용하여 이미지 프레임 리스트를 3D 객체의 gif로 변환합니다.
+
+```py
+from diffusers.utils import export_to_gif
+
+export_to_gif(images[0], "firecracker_3d.gif")
+export_to_gif(images[1], "cake_3d.gif")
+```
+
+<div class="flex gap-4">
+  <div>
+    <img class="rounded-xl" src="https://huggingface.co/datasets/hf-internal-testing/diffusers-images/resolve/main/shap_e/firecracker_out.gif"/>
+    <figcaption class="mt-2 text-center text-sm text-gray-500">prompt = "A firecracker"</figcaption>
+  </div>
+  <div>
+    <img class="rounded-xl" src="https://huggingface.co/datasets/hf-internal-testing/diffusers-images/resolve/main/shap_e/cake_out.gif"/>
+    <figcaption class="mt-2 text-center text-sm text-gray-500">prompt = "A birthday cupcake"</figcaption>
+  </div>
+</div>
+
+## Image-to-3D
+
+다른 이미지로부터 3D 개체를 생성하려면 [`ShapEImg2ImgPipeline`]을 사용합니다. 기존 이미지를 사용하거나 완전히 새로운 이미지를 생성할 수 있습니다. [Kandinsky 2.1](../api/pipelines/kandinsky) 모델을 사용하여 새 이미지를 생성해 보겠습니다.
+
+```py
+from diffusers import DiffusionPipeline
+import torch
+
+prior_pipeline = DiffusionPipeline.from_pretrained("kandinsky-community/kandinsky-2-1-prior", torch_dtype=torch.float16, use_safetensors=True).to("cuda")
+pipeline = DiffusionPipeline.from_pretrained("kandinsky-community/kandinsky-2-1", torch_dtype=torch.float16, use_safetensors=True).to("cuda")
+
+prompt = "A cheeseburger, white background"
+
+image_embeds, negative_image_embeds = prior_pipeline(prompt, guidance_scale=1.0).to_tuple()
+image = pipeline(
+    prompt,
+    image_embeds=image_embeds,
+    negative_image_embeds=negative_image_embeds,
+).images[0]
+
+image.save("burger.png")
+```
+
+치즈버거를 [`ShapEImg2ImgPipeline`]에 전달하여 3D representation을 생성합니다.
+
+```py
+from PIL import Image
+from diffusers import ShapEImg2ImgPipeline
+from diffusers.utils import export_to_gif
+
+pipe = ShapEImg2ImgPipeline.from_pretrained("openai/shap-e-img2img", torch_dtype=torch.float16, variant="fp16").to("cuda")
+
+guidance_scale = 3.0
+image = Image.open("burger.png").resize((256, 256))
+
+images = pipe(
+    image,
+    guidance_scale=guidance_scale,
+    num_inference_steps=64,
+    frame_size=256,
+).images
+
+gif_path = export_to_gif(images[0], "burger_3d.gif")
+```
+
+<div class="flex gap-4">
+  <div>
+    <img class="rounded-xl" src="https://huggingface.co/datasets/hf-internal-testing/diffusers-images/resolve/main/shap_e/burger_in.png"/>
+    <figcaption class="mt-2 text-center text-sm text-gray-500">cheeseburger</figcaption>
+  </div>
+  <div>
+    <img class="rounded-xl" src="https://huggingface.co/datasets/hf-internal-testing/diffusers-images/resolve/main/shap_e/burger_out.gif"/>
+    <figcaption class="mt-2 text-center text-sm text-gray-500">3D cheeseburger</figcaption>
+  </div>
+</div>
+
+## 메시 생성하기
+
+Shap-E는 다운스트림 애플리케이션에 렌더링할 textured 메시 출력을 생성할 수도 있는 유연한 모델입니다. 이 예제에서는 🤗 Datasets 라이브러리에서 [Dataset viewer](https://huggingface.co/docs/hub/datasets-viewer#dataset-preview)를 사용해 메시 시각화를 지원하는 `glb` 파일로 변환합니다.
+
+`output_type` 매개변수를 `"mesh"`로 지정함으로써 [`ShapEPipeline`]과 [`ShapEImg2ImgPipeline`] 모두에 대한 메시 출력을 생성할 수 있습니다:
+
+```py
+import torch
+from diffusers import ShapEPipeline
+
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+
+pipe = ShapEPipeline.from_pretrained("openai/shap-e", torch_dtype=torch.float16, variant="fp16")
+pipe = pipe.to(device)
+
+guidance_scale = 15.0
+prompt = "A birthday cupcake"
+
+images = pipe(prompt, guidance_scale=guidance_scale, num_inference_steps=64, frame_size=256, output_type="mesh").images
+```
+
+메시 출력을 `ply` 파일로 저장하려면 [`~utils.export_to_ply`] 함수를 사용합니다:
+
+<Tip>
+
+선택적으로 [`~utils.export_to_obj`] 함수를 사용하여 메시 출력을 `obj` 파일로 저장할 수 있습니다. 다양한 형식으로 메시 출력을 저장할 수 있어 다운스트림에서 더욱 유연하게 사용할 수 있습니다!
+
+</Tip>
+
+```py
+from diffusers.utils import export_to_ply
+
+ply_path = export_to_ply(images[0], "3d_cake.ply")
+print(f"Saved to folder: {ply_path}")
+```
+
+그 다음 trimesh 라이브러리를 사용하여 `ply` 파일을 `glb` 파일로 변환할 수 있습니다:
+
+```py
+import trimesh
+
+mesh = trimesh.load("3d_cake.ply")
+mesh_export = mesh.export("3d_cake.glb", file_type="glb")
+```
+
+기본적으로 메시 출력은 아래쪽 시점에 초점이 맞춰져 있지만 회전 변환을 적용하여 기본 시점을 변경할 수 있습니다:
+
+```py
+import trimesh
+import numpy as np
+
+mesh = trimesh.load("3d_cake.ply")
+rot = trimesh.transformations.rotation_matrix(-np.pi / 2, [1, 0, 0])
+mesh = mesh.apply_transform(rot)
+mesh_export = mesh.export("3d_cake.glb", file_type="glb")
+```
+
+메시 파일을 데이터셋 레포지토리에 업로드해 Dataset viewer로 시각화하세요!
+
+<div class="flex justify-center">
+    <img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/3D-cake.gif"/>
+</div>

docs/source/ko/using-diffusers/svd.md

@@ -0,0 +1,121 @@
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License.
+-->
+
+# Stable Video Diffusion
+
+[[open-in-colab]]
+
+[Stable Video Diffusion (SVD)](https://huggingface.co/papers/2311.15127)은 입력 이미지에 맞춰 2~4초 분량의 고해상도(576x1024) 비디오를 생성할 수 있는 강력한 image-to-video 생성 모델입니다.
+
+이 가이드에서는 SVD를 사용하여 이미지에서 짧은 동영상을 생성하는 방법을 설명합니다.
+
+시작하기 전에 다음 라이브러리가 설치되어 있는지 확인하세요:
+
+```py
+!pip install -q -U diffusers transformers accelerate
+```
+
+이 모델에는 [SVD](https://huggingface.co/stabilityai/stable-video-diffusion-img2vid)와 [SVD-XT](https://huggingface.co/stabilityai/stable-video-diffusion-img2vid-xt) 두 가지 종류가 있습니다. SVD 체크포인트는 14개의 프레임을 생성하도록 학습되었고, SVD-XT 체크포인트는 25개의 프레임을 생성하도록 파인튜닝되었습니다.
+
+이 가이드에서는 SVD-XT 체크포인트를 사용합니다.
+
+```python
+import torch
+
+from diffusers import StableVideoDiffusionPipeline
+from diffusers.utils import load_image, export_to_video
+
+pipe = StableVideoDiffusionPipeline.from_pretrained(
+    "stabilityai/stable-video-diffusion-img2vid-xt", torch_dtype=torch.float16, variant="fp16"
+)
+pipe.enable_model_cpu_offload()
+
+# Conditioning 이미지 불러오기
+image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/svd/rocket.png")
+image = image.resize((1024, 576))
+
+generator = torch.manual_seed(42)
+frames = pipe(image, decode_chunk_size=8, generator=generator).frames[0]
+
+export_to_video(frames, "generated.mp4", fps=7)
+```
+
+<div class="flex gap-4">
+  <div>
+    <img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/svd/rocket.png"/>
+    <figcaption class="mt-2 text-center text-sm text-gray-500">"source image of a rocket"</figcaption>
+  </div>
+  <div>
+    <img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/svd/output_rocket.gif"/>
+    <figcaption class="mt-2 text-center text-sm text-gray-500">"generated video from source image"</figcaption>
+  </div>
+</div>
+
+## torch.compile
+
+UNet을 [컴파일](../optimization/torch2.0#torchcompile)하면 메모리 사용량이 살짝 증가하지만, 20~25%의 속도 향상을 얻을 수 있습니다.
+
+```diff
+- pipe.enable_model_cpu_offload()
++ pipe.to("cuda")
++ pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
+```
+
+## 메모리 사용량 줄이기
+
+비디오 생성은 기본적으로 배치 크기가 큰 text-to-image 생성과 유사하게 'num_frames'를 한 번에 생성하기 때문에 메모리 사용량이 매우 높습니다. 메모리 사용량을 줄이기 위해 추론 속도와 메모리 사용량을 절충하는 여러 가지 옵션이 있습니다:
+
+- 모델 오프로링 활성화: 파이프라인의 각 구성 요소가 더 이상 필요하지 않을 때 CPU로 오프로드됩니다.
+- Feed-forward chunking 활성화: feed-forward 레이어가 배치 크기가 큰 단일 feed-forward를 실행하는 대신 루프로 반복해서 실행됩니다.
+- `decode_chunk_size` 감소: VAE가 프레임들을 한꺼번에 디코딩하는 대신 chunk 단위로 디코딩합니다. `decode_chunk_size=1`을 설정하면 한 번에 한 프레임씩 디코딩하고 최소한의 메모리만 사용하지만(GPU 메모리에 따라 이 값을 조정하는 것이 좋습니다), 동영상에 약간의 깜박임이 발생할 수 있습니다.
+
+```diff
+- pipe.enable_model_cpu_offload()
+- frames = pipe(image, decode_chunk_size=8, generator=generator).frames[0]
++ pipe.enable_model_cpu_offload()
++ pipe.unet.enable_forward_chunking()
++ frames = pipe(image, decode_chunk_size=2, generator=generator, num_frames=25).frames[0]
+```
+
+이러한 모든 방법들을 사용하면 메모리 사용량이 8GAM VRAM보다 적을 것입니다.
+
+## Micro-conditioning
+
+Stable Diffusion Video는 또한 이미지 conditoning 외에도 micro-conditioning을 허용하므로 생성된 비디오를 더 잘 제어할 수 있습니다:
+
+- `fps`: 생성된 비디오의 초당 프레임 수입니다.
+- `motion_bucket_id`: 생성된 동영상에 사용할 모션 버킷 아이디입니다. 생성된 동영상의 모션을 제어하는 데 사용할 수 있습니다. 모션 버킷 아이디를 늘리면 생성되는 동영상의 모션이 증가합니다.
+- `noise_aug_strength`: Conditioning 이미지에 추가되는 노이즈의 양입니다. 값이 클수록 비디오가 conditioning 이미지와 덜 유사해집니다. 이 값을 높이면 생성된 비디오의 움직임도 증가합니다.
+
+예를 들어, 모션이 더 많은 동영상을 생성하려면 `motion_bucket_id` 및 `noise_aug_strength` micro-conditioning 파라미터를 사용합니다:
+
+```python
+import torch
+
+from diffusers import StableVideoDiffusionPipeline
+from diffusers.utils import load_image, export_to_video
+
+pipe = StableVideoDiffusionPipeline.from_pretrained(
+  "stabilityai/stable-video-diffusion-img2vid-xt", torch_dtype=torch.float16, variant="fp16"
+)
+pipe.enable_model_cpu_offload()
+
+# Conditioning 이미지 불러오기
+image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/svd/rocket.png")
+image = image.resize((1024, 576))
+
+generator = torch.manual_seed(42)
+frames = pipe(image, decode_chunk_size=8, generator=generator, motion_bucket_id=180, noise_aug_strength=0.1).frames[0]
+export_to_video(frames, "generated.mp4", fps=7)
+```
+
+![](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/svd/output_rocket_with_conditions.gif)

docs/source/ko/using-diffusers/textual_inversion_inference.md

@@ -24,7 +24,7 @@ import PIL
 from PIL import Image
 
 from diffusers import StableDiffusionPipeline
-from transformers import CLIPFeatureExtractor, CLIPTextModel, CLIPTokenizer
+from transformers import CLIPImageProcessor, CLIPTextModel, CLIPTokenizer
 
 
 def image_grid(imgs, rows, cols):

docs/source/ko/using-diffusers/using_safetensors.md

@@ -1,67 +0,0 @@
-# 세이프텐서 로드
-
-[safetensors](https://github.com/huggingface/safetensors)는 텐서를 저장하고 로드하기 위한 안전하고 빠른 파일 형식입니다. 일반적으로 PyTorch 모델 가중치는 Python의 [`pickle`](https://docs.python.org/3/library/pickle.html) 유틸리티를 사용하여 `.bin` 파일에 저장되거나 `피클`됩니다. 그러나 `피클`은 안전하지 않으며 피클된 파일에는 실행될 수 있는 악성 코드가 포함될 수 있습니다. 세이프텐서는 `피클`의 안전한 대안으로 모델 가중치를 공유하는 데 이상적입니다.
-
-이 가이드에서는 `.safetensor` 파일을 로드하는 방법과 다른 형식으로 저장된 안정적 확산 모델 가중치를 `.safetensor`로 변환하는 방법을 보여드리겠습니다. 시작하기 전에 세이프텐서가 설치되어 있는지 확인하세요:
-
-```bash
-!pip install safetensors
-```
-
-['runwayml/stable-diffusion-v1-5`] (https://huggingface.co/runwayml/stable-diffusion-v1-5/tree/main) 리포지토리를 보면 `text_encoder`, `unet` 및 `vae` 하위 폴더에 가중치가 `.safetensors` 형식으로 저장되어 있는 것을 볼 수 있습니다. 기본적으로 🤗 디퓨저는 모델 저장소에서 사용할 수 있는 경우 해당 하위 폴더에서 이러한 '.safetensors` 파일을 자동으로 로드합니다.
-
-보다 명시적인 제어를 위해 선택적으로 `사용_세이프텐서=True`를 설정할 수 있습니다(`세이프텐서`가 설치되지 않은 경우 설치하라는 오류 메시지가 표시됨):
-
-```py
-from diffusers import DiffusionPipeline
-
-pipeline = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", use_safetensors=True)
-```
-
-그러나 모델 가중치가 위의 예시처럼 반드시 별도의 하위 폴더에 저장되는 것은 아닙니다. 모든 가중치가 하나의 '.safetensors` 파일에 저장되는 경우도 있습니다. 이 경우 가중치가 Stable Diffusion 가중치인 경우 [`~diffusers.loaders.FromCkptMixin.from_ckpt`] 메서드를 사용하여 파일을 직접 로드할 수 있습니다:
-
-```py
-from diffusers import StableDiffusionPipeline
-
-pipeline = StableDiffusionPipeline.from_ckpt(
-    "https://huggingface.co/WarriorMama777/OrangeMixs/blob/main/Models/AbyssOrangeMix/AbyssOrangeMix.safetensors"
-)
-```
-
-## 세이프텐서로 변환
-
-허브의 모든 가중치를 '.safetensors` 형식으로 사용할 수 있는 것은 아니며, '.bin`으로 저장된 가중치가 있을 수 있습니다. 이 경우 [Convert Space](https://huggingface.co/spaces/diffusers/convert)을 사용하여 가중치를 '.safetensors'로 변환하세요. Convert Space는 피클된 가중치를 다운로드하여 변환한 후 풀 리퀘스트를 열어 허브에 새로 변환된 `.safetensors` 파일을 업로드합니다. 이렇게 하면 피클된 파일에 악성 코드가 포함되어 있는 경우, 안전하지 않은 파일과 의심스러운 피클 가져오기를 탐지하는 [보안 스캐너](https://huggingface.co/docs/hub/security-pickle#hubs-security-scanner)가 있는 허브로 업로드됩니다. - 개별 컴퓨터가 아닌.
-
-개정` 매개변수에 풀 리퀘스트에 대한 참조를 지정하여 새로운 '.safetensors` 가중치가 적용된 모델을 사용할 수 있습니다(허브의 [Check PR](https://huggingface.co/spaces/diffusers/check_pr) 공간에서 테스트할 수도 있음)(예: `refs/pr/22`):
-
-```py
-from diffusers import DiffusionPipeline
-
-pipeline = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-2-1", revision="refs/pr/22")
-```
-
-## 세이프센서를 사용하는 이유는 무엇인가요?
-
-세이프티 센서를 사용하는 데에는 여러 가지 이유가 있습니다:
-
-- 세이프텐서를 사용하는 가장 큰 이유는 안전입니다.오픈 소스 및 모델 배포가 증가함에 따라 다운로드한 모델 가중치에 악성 코드가 포함되어 있지 않다는 것을 신뢰할 수 있는 것이 중요해졌습니다.세이프센서의 현재 헤더 크기는 매우 큰 JSON 파일을 구문 분석하지 못하게 합니다.
-- 모델 전환 간의 로딩 속도는 텐서의 제로 카피를 수행하는 세이프텐서를 사용해야 하는 또 다른 이유입니다. 가중치를 CPU(기본값)로 로드하는 경우 '피클'에 비해 특히 빠르며, 가중치를 GPU로 직접 로드하는 경우에도 빠르지는 않더라도 비슷하게 빠릅니다. 모델이 이미 로드된 경우에만 성능 차이를 느낄 수 있으며, 가중치를 다운로드하거나 모델을 처음 로드하는 경우에는 성능 차이를 느끼지 못할 것입니다.
-
-	전체 파이프라인을 로드하는 데 걸리는 시간입니다:
-
-	```py
- from diffusers import StableDiffusionPipeline
-
- pipeline = StableDiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-2-1")
- "Loaded in safetensors 0:00:02.033658"
- "Loaded in PyTorch 0:00:02.663379"
-	```
-
-	하지만 실제로 500MB의 모델 가중치를 로드하는 데 걸리는 시간은 얼마 되지 않습니다:
-
-	```bash
-	safetensors: 3.4873ms
-	PyTorch: 172.7537ms
-	```
-
-지연 로딩은 세이프텐서에서도 지원되며, 이는 분산 설정에서 일부 텐서만 로드하는 데 유용합니다. 이 형식을 사용하면 [BLOOM](https://huggingface.co/bigscience/bloom) 모델을 일반 PyTorch 가중치를 사용하여 10분이 걸리던 것을 8개의 GPU에서 45초 만에 로드할 수 있습니다.

examples/advanced_diffusion_training/train_dreambooth_lora_sd15_advanced.py

@@ -57,7 +57,7 @@ from diffusers import (
     StableDiffusionPipeline,
     UNet2DConditionModel,
 )
-from diffusers.loaders import LoraLoaderMixin
+from diffusers.loaders import StableDiffusionLoraLoaderMixin
 from diffusers.optimization import get_scheduler
 from diffusers.training_utils import compute_snr
 from diffusers.utils import (
@@ -1302,7 +1302,7 @@ def main(args):
                 text_encoder_lora_layers=text_encoder_one_lora_layers_to_save,
             )
         if args.train_text_encoder_ti:
-            embedding_handler.save_embeddings(f"{output_dir}/{args.output_dir}_emb.safetensors")
+            embedding_handler.save_embeddings(f"{args.output_dir}/{Path(args.output_dir).name}_emb.safetensors")
 
     def load_model_hook(models, input_dir):
         unet_ = None
@@ -1318,11 +1318,11 @@ def main(args):
             else:
                 raise ValueError(f"unexpected save model: {model.__class__}")
 
-        lora_state_dict, network_alphas = LoraLoaderMixin.lora_state_dict(input_dir)
-        LoraLoaderMixin.load_lora_into_unet(lora_state_dict, network_alphas=network_alphas, unet=unet_)
+        lora_state_dict, network_alphas = StableDiffusionLoraLoaderMixin.lora_state_dict(input_dir)
+        StableDiffusionLoraLoaderMixin.load_lora_into_unet(lora_state_dict, network_alphas=network_alphas, unet=unet_)
 
         text_encoder_state_dict = {k: v for k, v in lora_state_dict.items() if "text_encoder." in k}
-        LoraLoaderMixin.load_lora_into_text_encoder(
+        StableDiffusionLoraLoaderMixin.load_lora_into_text_encoder(
             text_encoder_state_dict, network_alphas=network_alphas, text_encoder=text_encoder_one_
         )
 

examples/advanced_diffusion_training/train_dreambooth_lora_sdxl_advanced.py

@@ -60,7 +60,7 @@ from diffusers import (
     StableDiffusionXLPipeline,
     UNet2DConditionModel,
 )
-from diffusers.loaders import LoraLoaderMixin
+from diffusers.loaders import StableDiffusionLoraLoaderMixin
 from diffusers.optimization import get_scheduler
 from diffusers.training_utils import _set_state_dict_into_text_encoder, cast_training_params, compute_snr
 from diffusers.utils import (
@@ -1605,13 +1605,15 @@ def main(args):
                 if isinstance(model, type(unwrap_model(unet))):
                     unet_lora_layers_to_save = convert_state_dict_to_diffusers(get_peft_model_state_dict(model))
                 elif isinstance(model, type(unwrap_model(text_encoder_one))):
-                    text_encoder_one_lora_layers_to_save = convert_state_dict_to_diffusers(
-                        get_peft_model_state_dict(model)
-                    )
+                    if args.train_text_encoder:
+                        text_encoder_one_lora_layers_to_save = convert_state_dict_to_diffusers(
+                            get_peft_model_state_dict(model)
+                        )
                 elif isinstance(model, type(unwrap_model(text_encoder_two))):
-                    text_encoder_two_lora_layers_to_save = convert_state_dict_to_diffusers(
-                        get_peft_model_state_dict(model)
-                    )
+                    if args.train_text_encoder:
+                        text_encoder_two_lora_layers_to_save = convert_state_dict_to_diffusers(
+                            get_peft_model_state_dict(model)
+                        )
                 else:
                     raise ValueError(f"unexpected save model: {model.__class__}")
 
@@ -1625,7 +1627,7 @@ def main(args):
                 text_encoder_2_lora_layers=text_encoder_two_lora_layers_to_save,
             )
         if args.train_text_encoder_ti:
-            embedding_handler.save_embeddings(f"{output_dir}/{args.output_dir}_emb.safetensors")
+            embedding_handler.save_embeddings(f"{args.output_dir}/{Path(args.output_dir).name}_emb.safetensors")
 
     def load_model_hook(models, input_dir):
         unet_ = None
@@ -1644,7 +1646,7 @@ def main(args):
             else:
                 raise ValueError(f"unexpected save model: {model.__class__}")
 
-        lora_state_dict, network_alphas = LoraLoaderMixin.lora_state_dict(input_dir)
+        lora_state_dict, network_alphas = StableDiffusionLoraLoaderMixin.lora_state_dict(input_dir)
 
         unet_state_dict = {f'{k.replace("unet.", "")}': v for k, v in lora_state_dict.items() if k.startswith("unet.")}
         unet_state_dict = convert_unet_state_dict_to_peft(unet_state_dict)

examples/amused/train_amused.py

@@ -41,7 +41,7 @@ from transformers import (
 
 import diffusers.optimization
 from diffusers import AmusedPipeline, AmusedScheduler, EMAModel, UVit2DModel, VQModel
-from diffusers.loaders import LoraLoaderMixin
+from diffusers.loaders import AmusedLoraLoaderMixin
 from diffusers.utils import is_wandb_available
 
 
@@ -532,7 +532,7 @@ def main(args):
                 weights.pop()
 
             if transformer_lora_layers_to_save is not None or text_encoder_lora_layers_to_save is not None:
-                LoraLoaderMixin.save_lora_weights(
+                AmusedLoraLoaderMixin.save_lora_weights(
                     output_dir,
                     transformer_lora_layers=transformer_lora_layers_to_save,
                     text_encoder_lora_layers=text_encoder_lora_layers_to_save,
@@ -566,11 +566,11 @@ def main(args):
                 raise ValueError(f"unexpected save model: {model.__class__}")
 
         if transformer is not None or text_encoder_ is not None:
-            lora_state_dict, network_alphas = LoraLoaderMixin.lora_state_dict(input_dir)
-            LoraLoaderMixin.load_lora_into_text_encoder(
+            lora_state_dict, network_alphas = AmusedLoraLoaderMixin.lora_state_dict(input_dir)
+            AmusedLoraLoaderMixin.load_lora_into_text_encoder(
                 lora_state_dict, network_alphas=network_alphas, text_encoder=text_encoder_
             )
-            LoraLoaderMixin.load_lora_into_transformer(
+            AmusedLoraLoaderMixin.load_lora_into_transformer(
                 lora_state_dict, network_alphas=network_alphas, transformer=transformer
             )
 

examples/community/README.md

@@ -71,6 +71,7 @@ Please also check out our [Community Scripts](https://github.com/huggingface/dif
 | Stable Diffusion BoxDiff Pipeline | Training-free controlled generation with bounding boxes using [BoxDiff](https://github.com/showlab/BoxDiff) | [Stable Diffusion BoxDiff Pipeline](#stable-diffusion-boxdiff) | - | [Jingyang Zhang](https://github.com/zjysteven/) |
 |   FRESCO V2V Pipeline                                                                                                    | Implementation of [[CVPR 2024] FRESCO: Spatial-Temporal Correspondence for Zero-Shot Video Translation](https://arxiv.org/abs/2403.12962)                                                                                                                                                                                                                                                                                                                                                                                                                                      | [FRESCO V2V Pipeline](#fresco)      | - |              [Yifan Zhou](https://github.com/SingleZombie) |
 | AnimateDiff IPEX Pipeline | Accelerate AnimateDiff inference pipeline with BF16/FP32 precision on Intel Xeon CPUs with [IPEX](https://github.com/intel/intel-extension-for-pytorch) | [AnimateDiff on IPEX](#animatediff-on-ipex) | - | [Dan Li](https://github.com/ustcuna/) |
+| HunyuanDiT Differential Diffusion Pipeline | Applies [Differential Diffsuion](https://github.com/exx8/differential-diffusion) to [HunyuanDiT](https://github.com/huggingface/diffusers/pull/8240). | [HunyuanDiT with Differential Diffusion](#hunyuandit-with-differential-diffusion) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1v44a5fpzyr4Ffr4v2XBQ7BajzG874N4P?usp=sharing) | [Monjoy Choudhury](https://github.com/MnCSSJ4x) |
 
 To load a custom pipeline you just need to pass the `custom_pipeline` argument to `DiffusionPipeline`, as one of the files in `diffusers/examples/community`. Feel free to send a PR with your own pipelines, we will merge them quickly.
 
@@ -1435,9 +1436,9 @@ import requests
 import torch
 from diffusers import DiffusionPipeline
 from PIL import Image
-from transformers import CLIPFeatureExtractor, CLIPModel
+from transformers import CLIPImageProcessor, CLIPModel
 
-feature_extractor = CLIPFeatureExtractor.from_pretrained(
+feature_extractor = CLIPImageProcessor.from_pretrained(
     "laion/CLIP-ViT-B-32-laion2B-s34B-b79K"
 )
 clip_model = CLIPModel.from_pretrained(
@@ -1487,17 +1488,16 @@ NOTE: The ONNX conversions and TensorRT engine build may take up to 30 minutes.
 ```python
 import torch
 from diffusers import DDIMScheduler
-from diffusers.pipelines.stable_diffusion import StableDiffusionPipeline
+from diffusers.pipelines import DiffusionPipeline
 
 # Use the DDIMScheduler scheduler here instead
-scheduler = DDIMScheduler.from_pretrained("stabilityai/stable-diffusion-2-1",
-                                            subfolder="scheduler")
+scheduler = DDIMScheduler.from_pretrained("stabilityai/stable-diffusion-2-1", subfolder="scheduler")
 
-pipe = StableDiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-2-1",
-                                                custom_pipeline="stable_diffusion_tensorrt_txt2img",
-                                                variant='fp16',
-                                                torch_dtype=torch.float16,
-                                                scheduler=scheduler,)
+pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-2-1",
+    custom_pipeline="stable_diffusion_tensorrt_txt2img",
+    variant='fp16',
+    torch_dtype=torch.float16,
+    scheduler=scheduler,)
 
 # re-use cached folder to save ONNX models and TensorRT Engines
 pipe.set_cached_folder("stabilityai/stable-diffusion-2-1", variant='fp16',)
@@ -1641,18 +1641,17 @@ from io import BytesIO
 from PIL import Image
 import torch
 from diffusers import DDIMScheduler
-from diffusers.pipelines.stable_diffusion import StableDiffusionImg2ImgPipeline
+from diffusers import DiffusionPipeline
 
 # Use the DDIMScheduler scheduler here instead
 scheduler = DDIMScheduler.from_pretrained("stabilityai/stable-diffusion-2-1",
                                             subfolder="scheduler")
 
-
-pipe = StableDiffusionImg2ImgPipeline.from_pretrained("stabilityai/stable-diffusion-2-1",
-                                                custom_pipeline="stable_diffusion_tensorrt_img2img",
-                                                variant='fp16',
-                                                torch_dtype=torch.float16,
-                                                scheduler=scheduler,)
+pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-2-1",
+                                            custom_pipeline="stable_diffusion_tensorrt_img2img",
+                                            variant='fp16',
+                                            torch_dtype=torch.float16,
+                                            scheduler=scheduler,)
 
 # re-use cached folder to save ONNX models and TensorRT Engines
 pipe.set_cached_folder("stabilityai/stable-diffusion-2-1", variant='fp16',)
@@ -1662,7 +1661,6 @@ pipe = pipe.to("cuda")
 url = "https://pajoca.com/wp-content/uploads/2022/09/tekito-yamakawa-1.png"
 response = requests.get(url)
 input_image = Image.open(BytesIO(response.content)).convert("RGB")
-
 prompt = "photorealistic new zealand hills"
 image = pipe(prompt, image=input_image, strength=0.75,).images[0]
 image.save('tensorrt_img2img_new_zealand_hills.png')
@@ -2123,7 +2121,7 @@ import torch
 import open_clip
 from open_clip import SimpleTokenizer
 from diffusers import DiffusionPipeline
-from transformers import CLIPFeatureExtractor, CLIPModel
+from transformers import CLIPImageProcessor, CLIPModel
 
 
 def download_image(url):
@@ -2131,7 +2129,7 @@ def download_image(url):
     return PIL.Image.open(BytesIO(response.content)).convert("RGB")
 
 # Loading additional models
-feature_extractor = CLIPFeatureExtractor.from_pretrained(
+feature_extractor = CLIPImageProcessor.from_pretrained(
     "laion/CLIP-ViT-B-32-laion2B-s34B-b79K"
 )
 clip_model = CLIPModel.from_pretrained(
@@ -2231,12 +2229,12 @@ from io import BytesIO
 from PIL import Image
 import torch
 from diffusers import PNDMScheduler
-from diffusers.pipelines.stable_diffusion import StableDiffusionInpaintPipeline
+from diffusers.pipelines import DiffusionPipeline
 
 # Use the PNDMScheduler scheduler here instead
 scheduler = PNDMScheduler.from_pretrained("stabilityai/stable-diffusion-2-inpainting", subfolder="scheduler")
 
-pipe = StableDiffusionInpaintPipeline.from_pretrained("stabilityai/stable-diffusion-2-inpainting",
+pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-2-inpainting",
     custom_pipeline="stable_diffusion_tensorrt_inpaint",
     variant='fp16',
     torch_dtype=torch.float16,
@@ -4210,6 +4208,52 @@ print("Latency of AnimateDiffPipelineIpex--fp32", latency, "s for total", step,
 latency = elapsed_time(pipe4, num_inference_steps=step)
 print("Latency of AnimateDiffPipeline--fp32",latency, "s for total", step, "steps")
 ```
+### HunyuanDiT with Differential Diffusion
+
+#### Usage
+
+```python
+import torch
+from diffusers import FlowMatchEulerDiscreteScheduler
+from diffusers.utils import load_image
+from PIL import Image
+from torchvision import transforms
+
+from pipeline_hunyuandit_differential_img2img import (
+    HunyuanDiTDifferentialImg2ImgPipeline,
+)
+
+
+pipe = HunyuanDiTDifferentialImg2ImgPipeline.from_pretrained(
+    "Tencent-Hunyuan/HunyuanDiT-Diffusers", torch_dtype=torch.float16
+).to("cuda")
+
+
+source_image = load_image(
+    "https://huggingface.co/datasets/OzzyGT/testing-resources/resolve/main/differential/20240329211129_4024911930.png"
+)
+map = load_image(
+    "https://huggingface.co/datasets/OzzyGT/testing-resources/resolve/main/differential/gradient_mask_2.png"
+)
+prompt = "a green pear"
+negative_prompt = "blurry"
+
+image = pipe(
+    prompt=prompt,
+    negative_prompt=negative_prompt,
+    image=source_image,
+    num_inference_steps=28,
+    guidance_scale=4.5,
+    strength=1.0,
+    map=map,
+).images[0]
+```
+
+| ![Gradient](https://github.com/user-attachments/assets/e38ce4d5-1ae6-4df0-ab43-adc1b45716b5) | ![Input](https://github.com/user-attachments/assets/9c95679c-e9d7-4f5a-90d6-560203acd6b3) | ![Output](https://github.com/user-attachments/assets/5313ff64-a0c4-418b-8b55-a38f1a5e7532) |
+| ------------------------------------------------------------------------------------------ | --------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------- |
+| Gradient                                                                                   | Input                                                                                   | Output                                                                                   |
+
+A colab notebook demonstrating all results can be found [here](https://colab.research.google.com/drive/1v44a5fpzyr4Ffr4v2XBQ7BajzG874N4P?usp=sharing). Depth Maps have also been added in the same colab.
 
 # Perturbed-Attention Guidance
 
@@ -4286,4 +4330,4 @@ grid_image.save(grid_dir + "sample.png")
 
 `pag_scale` : guidance scale of PAG (ex: 5.0)
 
-`pag_applied_layers_index` : index of the layer to apply perturbation (ex: ['m0'])
+`pag_applied_layers_index` : index of the layer to apply perturbation (ex: ['m0'])

examples/community/checkpoint_merger.py

@@ -71,7 +71,7 @@ class CheckpointMergerPipeline(DiffusionPipeline):
             **kwargs:
                 Supports all the default DiffusionPipeline.get_config_dict kwargs viz..
 
-                cache_dir, resume_download, force_download, proxies, local_files_only, token, revision, torch_dtype, device_map.
+                cache_dir, force_download, proxies, local_files_only, token, revision, torch_dtype, device_map.
 
                 alpha - The interpolation parameter. Ranges from 0 to 1.  It affects the ratio in which the checkpoints are merged. A 0.8 alpha
                     would mean that the first model checkpoints would affect the final result far less than an alpha of 0.2
@@ -86,7 +86,6 @@ class CheckpointMergerPipeline(DiffusionPipeline):
         """
         # Default kwargs from DiffusionPipeline
         cache_dir = kwargs.pop("cache_dir", None)
-        resume_download = kwargs.pop("resume_download", False)
         force_download = kwargs.pop("force_download", False)
         proxies = kwargs.pop("proxies", None)
         local_files_only = kwargs.pop("local_files_only", False)
@@ -124,7 +123,6 @@ class CheckpointMergerPipeline(DiffusionPipeline):
             config_dict = DiffusionPipeline.load_config(
                 pretrained_model_name_or_path,
                 cache_dir=cache_dir,
-                resume_download=resume_download,
                 force_download=force_download,
                 proxies=proxies,
                 local_files_only=local_files_only,
@@ -160,7 +158,6 @@ class CheckpointMergerPipeline(DiffusionPipeline):
                 else snapshot_download(
                     pretrained_model_name_or_path,
                     cache_dir=cache_dir,
-                    resume_download=resume_download,
                     proxies=proxies,
                     local_files_only=local_files_only,
                     token=token,

examples/community/clip_guided_images_mixing_stable_diffusion.py

@@ -7,7 +7,7 @@ import PIL.Image
 import torch
 from torch.nn import functional as F
 from torchvision import transforms
-from transformers import CLIPFeatureExtractor, CLIPModel, CLIPTextModel, CLIPTokenizer
+from transformers import CLIPImageProcessor, CLIPModel, CLIPTextModel, CLIPTokenizer
 
 from diffusers import (
     AutoencoderKL,
@@ -86,7 +86,7 @@ class CLIPGuidedImagesMixingStableDiffusion(DiffusionPipeline, StableDiffusionMi
         tokenizer: CLIPTokenizer,
         unet: UNet2DConditionModel,
         scheduler: Union[PNDMScheduler, LMSDiscreteScheduler, DDIMScheduler, DPMSolverMultistepScheduler],
-        feature_extractor: CLIPFeatureExtractor,
+        feature_extractor: CLIPImageProcessor,
         coca_model=None,
         coca_tokenizer=None,
         coca_transform=None,

examples/community/clip_guided_stable_diffusion_img2img.py

@@ -7,7 +7,7 @@ import torch
 from torch import nn
 from torch.nn import functional as F
 from torchvision import transforms
-from transformers import CLIPFeatureExtractor, CLIPModel, CLIPTextModel, CLIPTokenizer
+from transformers import CLIPImageProcessor, CLIPModel, CLIPTextModel, CLIPTokenizer
 
 from diffusers import (
     AutoencoderKL,
@@ -32,9 +32,9 @@ EXAMPLE_DOC_STRING = """
         import torch
         from diffusers import DiffusionPipeline
         from PIL import Image
-        from transformers import CLIPFeatureExtractor, CLIPModel
+        from transformers import CLIPImageProcessor, CLIPModel
 
-        feature_extractor = CLIPFeatureExtractor.from_pretrained(
+        feature_extractor = CLIPImageProcessor.from_pretrained(
             "laion/CLIP-ViT-B-32-laion2B-s34B-b79K"
         )
         clip_model = CLIPModel.from_pretrained(
@@ -139,7 +139,7 @@ class CLIPGuidedStableDiffusion(DiffusionPipeline, StableDiffusionMixin):
         tokenizer: CLIPTokenizer,
         unet: UNet2DConditionModel,
         scheduler: Union[PNDMScheduler, LMSDiscreteScheduler, DDIMScheduler, DPMSolverMultistepScheduler],
-        feature_extractor: CLIPFeatureExtractor,
+        feature_extractor: CLIPImageProcessor,
     ):
         super().__init__()
         self.register_modules(

examples/community/fresco_v2v.py

@@ -26,7 +26,7 @@ from gmflow.gmflow import GMFlow
 from transformers import CLIPImageProcessor, CLIPTextModel, CLIPTokenizer, CLIPVisionModelWithProjection
 
 from diffusers.image_processor import PipelineImageInput, VaeImageProcessor
-from diffusers.loaders import LoraLoaderMixin, TextualInversionLoaderMixin
+from diffusers.loaders import StableDiffusionLoraLoaderMixin, TextualInversionLoaderMixin
 from diffusers.models import AutoencoderKL, ControlNetModel, ImageProjection, UNet2DConditionModel
 from diffusers.models.attention_processor import AttnProcessor2_0
 from diffusers.models.lora import adjust_lora_scale_text_encoder
@@ -1252,8 +1252,8 @@ class FrescoV2VPipeline(StableDiffusionControlNetImg2ImgPipeline):
 
     The pipeline also inherits the following loading methods:
         - [`~loaders.TextualInversionLoaderMixin.load_textual_inversion`] for loading textual inversion embeddings
-        - [`~loaders.LoraLoaderMixin.load_lora_weights`] for loading LoRA weights
-        - [`~loaders.LoraLoaderMixin.save_lora_weights`] for saving LoRA weights
+        - [`~loaders.StableDiffusionLoraLoaderMixin.load_lora_weights`] for loading LoRA weights
+        - [`~loaders.StableDiffusionLoraLoaderMixin.save_lora_weights`] for saving LoRA weights
         - [`~loaders.FromSingleFileMixin.from_single_file`] for loading `.ckpt` files
         - [`~loaders.IPAdapterMixin.load_ip_adapter`] for loading IP Adapters
 
@@ -1456,7 +1456,7 @@ class FrescoV2VPipeline(StableDiffusionControlNetImg2ImgPipeline):
         """
         # set lora scale so that monkey patched LoRA
         # function of text encoder can correctly access it
-        if lora_scale is not None and isinstance(self, LoraLoaderMixin):
+        if lora_scale is not None and isinstance(self, StableDiffusionLoraLoaderMixin):
             self._lora_scale = lora_scale
 
             # dynamically adjust the LoRA scale
@@ -1588,7 +1588,7 @@ class FrescoV2VPipeline(StableDiffusionControlNetImg2ImgPipeline):
             negative_prompt_embeds = negative_prompt_embeds.repeat(1, num_images_per_prompt, 1)
             negative_prompt_embeds = negative_prompt_embeds.view(batch_size * num_images_per_prompt, seq_len, -1)
 
-        if isinstance(self, LoraLoaderMixin) and USE_PEFT_BACKEND:
+        if isinstance(self, StableDiffusionLoraLoaderMixin) and USE_PEFT_BACKEND:
             # Retrieve the original scale by scaling back the LoRA layers
             unscale_lora_layers(self.text_encoder, lora_scale)
 
@@ -2436,7 +2436,7 @@ class FrescoV2VPipeline(StableDiffusionControlNetImg2ImgPipeline):
                 )
 
                 if guess_mode and self.do_classifier_free_guidance:
-                    # Infered ControlNet only for the conditional batch.
+                    # Inferred ControlNet only for the conditional batch.
                     # To apply the output of ControlNet to both the unconditional and conditional batches,
                     # add 0 to the unconditional batch to keep it unchanged.
                     down_block_res_samples = [torch.cat([torch.zeros_like(d), d]) for d in down_block_res_samples]

examples/community/gluegen.py

@@ -7,7 +7,7 @@ from transformers import AutoModel, AutoTokenizer, CLIPImageProcessor
 
 from diffusers import DiffusionPipeline
 from diffusers.image_processor import VaeImageProcessor
-from diffusers.loaders import LoraLoaderMixin
+from diffusers.loaders import StableDiffusionLoraLoaderMixin
 from diffusers.models import AutoencoderKL, UNet2DConditionModel
 from diffusers.models.lora import adjust_lora_scale_text_encoder
 from diffusers.pipelines.pipeline_utils import StableDiffusionMixin
@@ -194,7 +194,7 @@ def retrieve_timesteps(
     return timesteps, num_inference_steps
 
 
-class GlueGenStableDiffusionPipeline(DiffusionPipeline, StableDiffusionMixin, LoraLoaderMixin):
+class GlueGenStableDiffusionPipeline(DiffusionPipeline, StableDiffusionMixin, StableDiffusionLoraLoaderMixin):
     def __init__(
         self,
         vae: AutoencoderKL,
@@ -290,7 +290,7 @@ class GlueGenStableDiffusionPipeline(DiffusionPipeline, StableDiffusionMixin, Lo
         """
         # set lora scale so that monkey patched LoRA
         # function of text encoder can correctly access it
-        if lora_scale is not None and isinstance(self, LoraLoaderMixin):
+        if lora_scale is not None and isinstance(self, StableDiffusionLoraLoaderMixin):
             self._lora_scale = lora_scale
 
             # dynamically adjust the LoRA scale
@@ -424,7 +424,7 @@ class GlueGenStableDiffusionPipeline(DiffusionPipeline, StableDiffusionMixin, Lo
             negative_prompt_embeds = negative_prompt_embeds.repeat(1, num_images_per_prompt, 1)
             negative_prompt_embeds = negative_prompt_embeds.view(batch_size * num_images_per_prompt, seq_len, -1)
 
-        if isinstance(self, LoraLoaderMixin) and USE_PEFT_BACKEND:
+        if isinstance(self, StableDiffusionLoraLoaderMixin) and USE_PEFT_BACKEND:
             # Retrieve the original scale by scaling back the LoRA layers
             unscale_lora_layers(self.text_encoder, lora_scale)
 

examples/community/instaflow_one_step.py

@@ -21,7 +21,7 @@ from transformers import CLIPImageProcessor, CLIPTextModel, CLIPTokenizer
 
 from diffusers.configuration_utils import FrozenDict
 from diffusers.image_processor import VaeImageProcessor
-from diffusers.loaders import FromSingleFileMixin, LoraLoaderMixin, TextualInversionLoaderMixin
+from diffusers.loaders import FromSingleFileMixin, StableDiffusionLoraLoaderMixin, TextualInversionLoaderMixin
 from diffusers.models import AutoencoderKL, UNet2DConditionModel
 from diffusers.models.lora import adjust_lora_scale_text_encoder
 from diffusers.pipelines.pipeline_utils import DiffusionPipeline, StableDiffusionMixin
@@ -53,7 +53,11 @@ def rescale_noise_cfg(noise_cfg, noise_pred_text, guidance_rescale=0.0):
 
 
 class InstaFlowPipeline(
-    DiffusionPipeline, StableDiffusionMixin, TextualInversionLoaderMixin, LoraLoaderMixin, FromSingleFileMixin
+    DiffusionPipeline,
+    StableDiffusionMixin,
+    TextualInversionLoaderMixin,
+    StableDiffusionLoraLoaderMixin,
+    FromSingleFileMixin,
 ):
     r"""
     Pipeline for text-to-image generation using Rectified Flow and Euler discretization.
@@ -64,8 +68,8 @@ class InstaFlowPipeline(
 
     The pipeline also inherits the following loading methods:
         - [`~loaders.TextualInversionLoaderMixin.load_textual_inversion`] for loading textual inversion embeddings
-        - [`~loaders.LoraLoaderMixin.load_lora_weights`] for loading LoRA weights
-        - [`~loaders.LoraLoaderMixin.save_lora_weights`] for saving LoRA weights
+        - [`~loaders.StableDiffusionLoraLoaderMixin.load_lora_weights`] for loading LoRA weights
+        - [`~loaders.StableDiffusionLoraLoaderMixin.save_lora_weights`] for saving LoRA weights
         - [`~loaders.FromSingleFileMixin.from_single_file`] for loading `.ckpt` files
 
     Args:
@@ -251,7 +255,7 @@ class InstaFlowPipeline(
         """
         # set lora scale so that monkey patched LoRA
         # function of text encoder can correctly access it
-        if lora_scale is not None and isinstance(self, LoraLoaderMixin):
+        if lora_scale is not None and isinstance(self, StableDiffusionLoraLoaderMixin):
             self._lora_scale = lora_scale
 
             # dynamically adjust the LoRA scale

examples/community/ip_adapter_face_id.py

@@ -24,7 +24,12 @@ from transformers import CLIPImageProcessor, CLIPTextModel, CLIPTokenizer, CLIPV
 
 from diffusers.configuration_utils import FrozenDict
 from diffusers.image_processor import VaeImageProcessor
-from diffusers.loaders import FromSingleFileMixin, IPAdapterMixin, LoraLoaderMixin, TextualInversionLoaderMixin
+from diffusers.loaders import (
+    FromSingleFileMixin,
+    IPAdapterMixin,
+    StableDiffusionLoraLoaderMixin,
+    TextualInversionLoaderMixin,
+)
 from diffusers.models import AutoencoderKL, UNet2DConditionModel
 from diffusers.models.attention_processor import (
     AttnProcessor,
@@ -130,7 +135,7 @@ class IPAdapterFaceIDStableDiffusionPipeline(
     DiffusionPipeline,
     StableDiffusionMixin,
     TextualInversionLoaderMixin,
-    LoraLoaderMixin,
+    StableDiffusionLoraLoaderMixin,
     IPAdapterMixin,
     FromSingleFileMixin,
 ):
@@ -142,8 +147,8 @@ class IPAdapterFaceIDStableDiffusionPipeline(
 
     The pipeline also inherits the following loading methods:
         - [`~loaders.TextualInversionLoaderMixin.load_textual_inversion`] for loading textual inversion embeddings
-        - [`~loaders.LoraLoaderMixin.load_lora_weights`] for loading LoRA weights
-        - [`~loaders.LoraLoaderMixin.save_lora_weights`] for saving LoRA weights
+        - [`~loaders.StableDiffusionLoraLoaderMixin.load_lora_weights`] for loading LoRA weights
+        - [`~loaders.StableDiffusionLoraLoaderMixin.save_lora_weights`] for saving LoRA weights
         - [`~loaders.FromSingleFileMixin.from_single_file`] for loading `.ckpt` files
         - [`~loaders.IPAdapterMixin.load_ip_adapter`] for loading IP Adapters
 
@@ -267,7 +272,6 @@ class IPAdapterFaceIDStableDiffusionPipeline(
     def load_ip_adapter_face_id(self, pretrained_model_name_or_path_or_dict, weight_name, **kwargs):
         cache_dir = kwargs.pop("cache_dir", None)
         force_download = kwargs.pop("force_download", False)
-        resume_download = kwargs.pop("resume_download", False)
         proxies = kwargs.pop("proxies", None)
         local_files_only = kwargs.pop("local_files_only", None)
         token = kwargs.pop("token", None)
@@ -283,7 +287,6 @@ class IPAdapterFaceIDStableDiffusionPipeline(
             weights_name=weight_name,
             cache_dir=cache_dir,
             force_download=force_download,
-            resume_download=resume_download,
             proxies=proxies,
             local_files_only=local_files_only,
             token=token,
@@ -520,7 +523,7 @@ class IPAdapterFaceIDStableDiffusionPipeline(
         """
         # set lora scale so that monkey patched LoRA
         # function of text encoder can correctly access it
-        if lora_scale is not None and isinstance(self, LoraLoaderMixin):
+        if lora_scale is not None and isinstance(self, StableDiffusionLoraLoaderMixin):
             self._lora_scale = lora_scale
 
             # dynamically adjust the LoRA scale
@@ -652,7 +655,7 @@ class IPAdapterFaceIDStableDiffusionPipeline(
             negative_prompt_embeds = negative_prompt_embeds.repeat(1, num_images_per_prompt, 1)
             negative_prompt_embeds = negative_prompt_embeds.view(batch_size * num_images_per_prompt, seq_len, -1)
 
-        if isinstance(self, LoraLoaderMixin) and USE_PEFT_BACKEND:
+        if isinstance(self, StableDiffusionLoraLoaderMixin) and USE_PEFT_BACKEND:
             # Retrieve the original scale by scaling back the LoRA layers
             unscale_lora_layers(self.text_encoder, lora_scale)
 

examples/community/kohya_hires_fix.py

@@ -395,8 +395,8 @@ class StableDiffusionHighResFixPipeline(StableDiffusionPipeline):
 
     The pipeline also inherits the following loading methods:
         - [`~loaders.TextualInversionLoaderMixin.load_textual_inversion`] for loading textual inversion embeddings
-        - [`~loaders.LoraLoaderMixin.load_lora_weights`] for loading LoRA weights
-        - [`~loaders.LoraLoaderMixin.save_lora_weights`] for saving LoRA weights
+        - [`~loaders.StableDiffusionLoraLoaderMixin.load_lora_weights`] for loading LoRA weights
+        - [`~loaders.StableDiffusionLoraLoaderMixin.save_lora_weights`] for saving LoRA weights
         - [`~loaders.FromSingleFileMixin.from_single_file`] for loading `.ckpt` files
         - [`~loaders.IPAdapterMixin.load_ip_adapter`] for loading IP Adapters
 

examples/community/latent_consistency_interpolate.py

@@ -6,7 +6,7 @@ import torch
 from transformers import CLIPImageProcessor, CLIPTextModel, CLIPTokenizer
 
 from diffusers.image_processor import VaeImageProcessor
-from diffusers.loaders import FromSingleFileMixin, LoraLoaderMixin, TextualInversionLoaderMixin
+from diffusers.loaders import FromSingleFileMixin, StableDiffusionLoraLoaderMixin, TextualInversionLoaderMixin
 from diffusers.models import AutoencoderKL, UNet2DConditionModel
 from diffusers.models.lora import adjust_lora_scale_text_encoder
 from diffusers.pipelines.pipeline_utils import DiffusionPipeline, StableDiffusionMixin
@@ -190,7 +190,11 @@ def slerp(
 
 
 class LatentConsistencyModelWalkPipeline(
-    DiffusionPipeline, StableDiffusionMixin, TextualInversionLoaderMixin, LoraLoaderMixin, FromSingleFileMixin
+    DiffusionPipeline,
+    StableDiffusionMixin,
+    TextualInversionLoaderMixin,
+    StableDiffusionLoraLoaderMixin,
+    FromSingleFileMixin,
 ):
     r"""
     Pipeline for text-to-image generation using a latent consistency model.
@@ -200,8 +204,8 @@ class LatentConsistencyModelWalkPipeline(
 
     The pipeline also inherits the following loading methods:
         - [`~loaders.TextualInversionLoaderMixin.load_textual_inversion`] for loading textual inversion embeddings
-        - [`~loaders.LoraLoaderMixin.load_lora_weights`] for loading LoRA weights
-        - [`~loaders.LoraLoaderMixin.save_lora_weights`] for saving LoRA weights
+        - [`~loaders.StableDiffusionLoraLoaderMixin.load_lora_weights`] for loading LoRA weights
+        - [`~loaders.StableDiffusionLoraLoaderMixin.save_lora_weights`] for saving LoRA weights
         - [`~loaders.FromSingleFileMixin.from_single_file`] for loading `.ckpt` files
 
     Args:
@@ -317,7 +321,7 @@ class LatentConsistencyModelWalkPipeline(
         """
         # set lora scale so that monkey patched LoRA
         # function of text encoder can correctly access it
-        if lora_scale is not None and isinstance(self, LoraLoaderMixin):
+        if lora_scale is not None and isinstance(self, StableDiffusionLoraLoaderMixin):
             self._lora_scale = lora_scale
 
             # dynamically adjust the LoRA scale
@@ -449,7 +453,7 @@ class LatentConsistencyModelWalkPipeline(
             negative_prompt_embeds = negative_prompt_embeds.repeat(1, num_images_per_prompt, 1)
             negative_prompt_embeds = negative_prompt_embeds.view(batch_size * num_images_per_prompt, seq_len, -1)
 
-        if isinstance(self, LoraLoaderMixin) and USE_PEFT_BACKEND:
+        if isinstance(self, StableDiffusionLoraLoaderMixin) and USE_PEFT_BACKEND:
             # Retrieve the original scale by scaling back the LoRA layers
             unscale_lora_layers(self.text_encoder, lora_scale)
 

examples/community/llm_grounded_diffusion.py

@@ -29,7 +29,12 @@ from transformers import CLIPImageProcessor, CLIPTextModel, CLIPTokenizer, CLIPV
 
 from diffusers.configuration_utils import FrozenDict
 from diffusers.image_processor import PipelineImageInput, VaeImageProcessor
-from diffusers.loaders import FromSingleFileMixin, IPAdapterMixin, LoraLoaderMixin, TextualInversionLoaderMixin
+from diffusers.loaders import (
+    FromSingleFileMixin,
+    IPAdapterMixin,
+    StableDiffusionLoraLoaderMixin,
+    TextualInversionLoaderMixin,
+)
 from diffusers.models import AutoencoderKL, UNet2DConditionModel
 from diffusers.models.attention import Attention, GatedSelfAttentionDense
 from diffusers.models.attention_processor import AttnProcessor2_0
@@ -271,7 +276,7 @@ class LLMGroundedDiffusionPipeline(
     DiffusionPipeline,
     StableDiffusionMixin,
     TextualInversionLoaderMixin,
-    LoraLoaderMixin,
+    StableDiffusionLoraLoaderMixin,
     IPAdapterMixin,
     FromSingleFileMixin,
 ):
@@ -1263,7 +1268,7 @@ class LLMGroundedDiffusionPipeline(
         """
         # set lora scale so that monkey patched LoRA
         # function of text encoder can correctly access it
-        if lora_scale is not None and isinstance(self, LoraLoaderMixin):
+        if lora_scale is not None and isinstance(self, StableDiffusionLoraLoaderMixin):
             self._lora_scale = lora_scale
 
             # dynamically adjust the LoRA scale
@@ -1397,7 +1402,7 @@ class LLMGroundedDiffusionPipeline(
             negative_prompt_embeds = negative_prompt_embeds.repeat(1, num_images_per_prompt, 1)
             negative_prompt_embeds = negative_prompt_embeds.view(batch_size * num_images_per_prompt, seq_len, -1)
 
-        if isinstance(self, LoraLoaderMixin) and USE_PEFT_BACKEND:
+        if isinstance(self, StableDiffusionLoraLoaderMixin) and USE_PEFT_BACKEND:
             # Retrieve the original scale by scaling back the LoRA layers
             unscale_lora_layers(self.text_encoder, lora_scale)
 

examples/community/lpw_stable_diffusion.py

@@ -11,15 +11,19 @@ from transformers import CLIPImageProcessor, CLIPTextModel, CLIPTokenizer
 from diffusers import DiffusionPipeline
 from diffusers.configuration_utils import FrozenDict
 from diffusers.image_processor import VaeImageProcessor
-from diffusers.loaders import FromSingleFileMixin, LoraLoaderMixin, TextualInversionLoaderMixin
+from diffusers.loaders import FromSingleFileMixin, StableDiffusionLoraLoaderMixin, TextualInversionLoaderMixin
 from diffusers.models import AutoencoderKL, UNet2DConditionModel
+from diffusers.models.lora import adjust_lora_scale_text_encoder
 from diffusers.pipelines.pipeline_utils import StableDiffusionMixin
 from diffusers.pipelines.stable_diffusion import StableDiffusionPipelineOutput, StableDiffusionSafetyChecker
 from diffusers.schedulers import KarrasDiffusionSchedulers
 from diffusers.utils import (
     PIL_INTERPOLATION,
+    USE_PEFT_BACKEND,
     deprecate,
     logging,
+    scale_lora_layers,
+    unscale_lora_layers,
 )
 from diffusers.utils.torch_utils import randn_tensor
 
@@ -199,6 +203,7 @@ def get_unweighted_text_embeddings(
     text_input: torch.Tensor,
     chunk_length: int,
     no_boseos_middle: Optional[bool] = True,
+    clip_skip: Optional[int] = None,
 ):
     """
     When the length of tokens is a multiple of the capacity of the text encoder,
@@ -214,7 +219,20 @@ def get_unweighted_text_embeddings(
             # cover the head and the tail by the starting and the ending tokens
             text_input_chunk[:, 0] = text_input[0, 0]
             text_input_chunk[:, -1] = text_input[0, -1]
-            text_embedding = pipe.text_encoder(text_input_chunk)[0]
+            if clip_skip is None:
+                prompt_embeds = pipe.text_encoder(text_input_chunk.to(pipe.device))
+                text_embedding = prompt_embeds[0]
+            else:
+                prompt_embeds = pipe.text_encoder(text_input_chunk.to(pipe.device), output_hidden_states=True)
+                # Access the `hidden_states` first, that contains a tuple of
+                # all the hidden states from the encoder layers. Then index into
+                # the tuple to access the hidden states from the desired layer.
+                prompt_embeds = prompt_embeds[-1][-(clip_skip + 1)]
+                # We also need to apply the final LayerNorm here to not mess with the
+                # representations. The `last_hidden_states` that we typically use for
+                # obtaining the final prompt representations passes through the LayerNorm
+                # layer.
+                text_embedding = pipe.text_encoder.text_model.final_layer_norm(prompt_embeds)
 
             if no_boseos_middle:
                 if i == 0:
@@ -230,7 +248,10 @@ def get_unweighted_text_embeddings(
             text_embeddings.append(text_embedding)
         text_embeddings = torch.concat(text_embeddings, axis=1)
     else:
-        text_embeddings = pipe.text_encoder(text_input)[0]
+        if clip_skip is None:
+            clip_skip = 0
+        prompt_embeds = pipe.text_encoder(text_input, output_hidden_states=True)[-1][-(clip_skip + 1)]
+        text_embeddings = pipe.text_encoder.text_model.final_layer_norm(prompt_embeds)
     return text_embeddings
 
 
@@ -242,6 +263,8 @@ def get_weighted_text_embeddings(
     no_boseos_middle: Optional[bool] = False,
     skip_parsing: Optional[bool] = False,
     skip_weighting: Optional[bool] = False,
+    clip_skip=None,
+    lora_scale=None,
 ):
     r"""
     Prompts can be assigned with local weights using brackets. For example,
@@ -268,6 +291,16 @@ def get_weighted_text_embeddings(
         skip_weighting (`bool`, *optional*, defaults to `False`):
             Skip the weighting. When the parsing is skipped, it is forced True.
     """
+    # set lora scale so that monkey patched LoRA
+    # function of text encoder can correctly access it
+    if lora_scale is not None and isinstance(pipe, StableDiffusionLoraLoaderMixin):
+        pipe._lora_scale = lora_scale
+
+        # dynamically adjust the LoRA scale
+        if not USE_PEFT_BACKEND:
+            adjust_lora_scale_text_encoder(pipe.text_encoder, lora_scale)
+        else:
+            scale_lora_layers(pipe.text_encoder, lora_scale)
     max_length = (pipe.tokenizer.model_max_length - 2) * max_embeddings_multiples + 2
     if isinstance(prompt, str):
         prompt = [prompt]
@@ -334,10 +367,7 @@ def get_weighted_text_embeddings(
 
     # get the embeddings
     text_embeddings = get_unweighted_text_embeddings(
-        pipe,
-        prompt_tokens,
-        pipe.tokenizer.model_max_length,
-        no_boseos_middle=no_boseos_middle,
+        pipe, prompt_tokens, pipe.tokenizer.model_max_length, no_boseos_middle=no_boseos_middle, clip_skip=clip_skip
     )
     prompt_weights = torch.tensor(prompt_weights, dtype=text_embeddings.dtype, device=text_embeddings.device)
     if uncond_prompt is not None:
@@ -346,6 +376,7 @@ def get_weighted_text_embeddings(
             uncond_tokens,
             pipe.tokenizer.model_max_length,
             no_boseos_middle=no_boseos_middle,
+            clip_skip=clip_skip,
         )
         uncond_weights = torch.tensor(uncond_weights, dtype=uncond_embeddings.dtype, device=uncond_embeddings.device)
 
@@ -362,6 +393,11 @@ def get_weighted_text_embeddings(
             current_mean = uncond_embeddings.float().mean(axis=[-2, -1]).to(uncond_embeddings.dtype)
             uncond_embeddings *= (previous_mean / current_mean).unsqueeze(-1).unsqueeze(-1)
 
+    if pipe.text_encoder is not None:
+        if isinstance(pipe, StableDiffusionLoraLoaderMixin) and USE_PEFT_BACKEND:
+            # Retrieve the original scale by scaling back the LoRA layers
+            unscale_lora_layers(pipe.text_encoder, lora_scale)
+
     if uncond_prompt is not None:
         return text_embeddings, uncond_embeddings
     return text_embeddings, None
@@ -409,7 +445,11 @@ def preprocess_mask(mask, batch_size, scale_factor=8):
 
 
 class StableDiffusionLongPromptWeightingPipeline(
-    DiffusionPipeline, StableDiffusionMixin, TextualInversionLoaderMixin, LoraLoaderMixin, FromSingleFileMixin
+    DiffusionPipeline,
+    StableDiffusionMixin,
+    TextualInversionLoaderMixin,
+    StableDiffusionLoraLoaderMixin,
+    FromSingleFileMixin,
 ):
     r"""
     Pipeline for text-to-image generation using Stable Diffusion without tokens length limit, and support parsing
@@ -545,6 +585,8 @@ class StableDiffusionLongPromptWeightingPipeline(
         max_embeddings_multiples=3,
         prompt_embeds: Optional[torch.Tensor] = None,
         negative_prompt_embeds: Optional[torch.Tensor] = None,
+        clip_skip: Optional[int] = None,
+        lora_scale: Optional[float] = None,
     ):
         r"""
         Encodes the prompt into text encoder hidden states.
@@ -593,6 +635,8 @@ class StableDiffusionLongPromptWeightingPipeline(
                 prompt=prompt,
                 uncond_prompt=negative_prompt if do_classifier_free_guidance else None,
                 max_embeddings_multiples=max_embeddings_multiples,
+                clip_skip=clip_skip,
+                lora_scale=lora_scale,
             )
             if prompt_embeds is None:
                 prompt_embeds = prompt_embeds1
@@ -786,6 +830,7 @@ class StableDiffusionLongPromptWeightingPipeline(
         return_dict: bool = True,
         callback: Optional[Callable[[int, int, torch.Tensor], None]] = None,
         is_cancelled_callback: Optional[Callable[[], bool]] = None,
+        clip_skip: Optional[int] = None,
         callback_steps: int = 1,
         cross_attention_kwargs: Optional[Dict[str, Any]] = None,
     ):
@@ -861,6 +906,9 @@ class StableDiffusionLongPromptWeightingPipeline(
             is_cancelled_callback (`Callable`, *optional*):
                 A function that will be called every `callback_steps` steps during inference. If the function returns
                 `True`, the inference will be cancelled.
+            clip_skip (`int`, *optional*):
+                Number of layers to be skipped from CLIP while computing the prompt embeddings. A value of 1 means that
+                the output of the pre-final layer will be used for computing the prompt embeddings.
             callback_steps (`int`, *optional*, defaults to 1):
                 The frequency at which the `callback` function will be called. If not specified, the callback will be
                 called at every step.
@@ -899,6 +947,7 @@ class StableDiffusionLongPromptWeightingPipeline(
         # of the Imagen paper: https://arxiv.org/pdf/2205.11487.pdf . `guidance_scale = 1`
         # corresponds to doing no classifier free guidance.
         do_classifier_free_guidance = guidance_scale > 1.0
+        lora_scale = cross_attention_kwargs.get("scale", None) if cross_attention_kwargs is not None else None
 
         # 3. Encode input prompt
         prompt_embeds = self._encode_prompt(
@@ -910,6 +959,8 @@ class StableDiffusionLongPromptWeightingPipeline(
             max_embeddings_multiples,
             prompt_embeds=prompt_embeds,
             negative_prompt_embeds=negative_prompt_embeds,
+            clip_skip=clip_skip,
+            lora_scale=lora_scale,
         )
         dtype = prompt_embeds.dtype
 
@@ -1040,6 +1091,7 @@ class StableDiffusionLongPromptWeightingPipeline(
         return_dict: bool = True,
         callback: Optional[Callable[[int, int, torch.Tensor], None]] = None,
         is_cancelled_callback: Optional[Callable[[], bool]] = None,
+        clip_skip=None,
         callback_steps: int = 1,
         cross_attention_kwargs: Optional[Dict[str, Any]] = None,
     ):
@@ -1097,6 +1149,9 @@ class StableDiffusionLongPromptWeightingPipeline(
             is_cancelled_callback (`Callable`, *optional*):
                 A function that will be called every `callback_steps` steps during inference. If the function returns
                 `True`, the inference will be cancelled.
+            clip_skip (`int`, *optional*):
+                Number of layers to be skipped from CLIP while computing the prompt embeddings. A value of 1 means that
+                the output of the pre-final layer will be used for computing the prompt embeddings.
             callback_steps (`int`, *optional*, defaults to 1):
                 The frequency at which the `callback` function will be called. If not specified, the callback will be
                 called at every step.
@@ -1131,6 +1186,7 @@ class StableDiffusionLongPromptWeightingPipeline(
             return_dict=return_dict,
             callback=callback,
             is_cancelled_callback=is_cancelled_callback,
+            clip_skip=clip_skip,
             callback_steps=callback_steps,
             cross_attention_kwargs=cross_attention_kwargs,
         )

examples/community/lpw_stable_diffusion_xl.py

@@ -22,19 +22,28 @@ from transformers import (
 
 from diffusers import DiffusionPipeline, StableDiffusionXLPipeline
 from diffusers.image_processor import PipelineImageInput, VaeImageProcessor
-from diffusers.loaders import FromSingleFileMixin, IPAdapterMixin, LoraLoaderMixin, TextualInversionLoaderMixin
+from diffusers.loaders import (
+    FromSingleFileMixin,
+    IPAdapterMixin,
+    StableDiffusionXLLoraLoaderMixin,
+    TextualInversionLoaderMixin,
+)
 from diffusers.models import AutoencoderKL, ImageProjection, UNet2DConditionModel
 from diffusers.models.attention_processor import AttnProcessor2_0, XFormersAttnProcessor
+from diffusers.models.lora import adjust_lora_scale_text_encoder
 from diffusers.pipelines.pipeline_utils import StableDiffusionMixin
 from diffusers.pipelines.stable_diffusion_xl.pipeline_output import StableDiffusionXLPipelineOutput
 from diffusers.schedulers import KarrasDiffusionSchedulers
 from diffusers.utils import (
+    USE_PEFT_BACKEND,
     deprecate,
     is_accelerate_available,
     is_accelerate_version,
     is_invisible_watermark_available,
     logging,
     replace_example_docstring,
+    scale_lora_layers,
+    unscale_lora_layers,
 )
 from diffusers.utils.torch_utils import randn_tensor
 
@@ -256,6 +265,7 @@ def get_weighted_text_embeddings_sdxl(
     num_images_per_prompt: int = 1,
     device: Optional[torch.device] = None,
     clip_skip: Optional[int] = None,
+    lora_scale: Optional[int] = None,
 ):
     """
     This function can process long prompt with weights, no length limitation
@@ -276,6 +286,24 @@ def get_weighted_text_embeddings_sdxl(
     """
     device = device or pipe._execution_device
 
+    # set lora scale so that monkey patched LoRA
+    # function of text encoder can correctly access it
+    if lora_scale is not None and isinstance(pipe, StableDiffusionXLLoraLoaderMixin):
+        pipe._lora_scale = lora_scale
+
+        # dynamically adjust the LoRA scale
+        if pipe.text_encoder is not None:
+            if not USE_PEFT_BACKEND:
+                adjust_lora_scale_text_encoder(pipe.text_encoder, lora_scale)
+            else:
+                scale_lora_layers(pipe.text_encoder, lora_scale)
+
+        if pipe.text_encoder_2 is not None:
+            if not USE_PEFT_BACKEND:
+                adjust_lora_scale_text_encoder(pipe.text_encoder_2, lora_scale)
+            else:
+                scale_lora_layers(pipe.text_encoder_2, lora_scale)
+
     if prompt_2:
         prompt = f"{prompt} {prompt_2}"
 
@@ -424,6 +452,16 @@ def get_weighted_text_embeddings_sdxl(
         bs_embed * num_images_per_prompt, -1
     )
 
+    if pipe.text_encoder is not None:
+        if isinstance(pipe, StableDiffusionXLLoraLoaderMixin) and USE_PEFT_BACKEND:
+            # Retrieve the original scale by scaling back the LoRA layers
+            unscale_lora_layers(pipe.text_encoder, lora_scale)
+
+    if pipe.text_encoder_2 is not None:
+        if isinstance(pipe, StableDiffusionXLLoraLoaderMixin) and USE_PEFT_BACKEND:
+            # Retrieve the original scale by scaling back the LoRA layers
+            unscale_lora_layers(pipe.text_encoder_2, lora_scale)
+
     return prompt_embeds, negative_prompt_embeds, pooled_prompt_embeds, negative_pooled_prompt_embeds
 
 
@@ -544,7 +582,7 @@ class SDXLLongPromptWeightingPipeline(
     StableDiffusionMixin,
     FromSingleFileMixin,
     IPAdapterMixin,
-    LoraLoaderMixin,
+    StableDiffusionXLLoraLoaderMixin,
     TextualInversionLoaderMixin,
 ):
     r"""
@@ -556,8 +594,8 @@ class SDXLLongPromptWeightingPipeline(
     The pipeline also inherits the following loading methods:
         - [`~loaders.FromSingleFileMixin.from_single_file`] for loading `.ckpt` files
         - [`~loaders.IPAdapterMixin.load_ip_adapter`] for loading IP Adapters
-        - [`~loaders.LoraLoaderMixin.load_lora_weights`] for loading LoRA weights
-        - [`~loaders.LoraLoaderMixin.save_lora_weights`] for saving LoRA weights
+        - [`~loaders.StableDiffusionXLLoraLoaderMixin.load_lora_weights`] for loading LoRA weights
+        - [`~loaders.StableDiffusionXLLoraLoaderMixin.save_lora_weights`] for saving LoRA weights
         - [`~loaders.TextualInversionLoaderMixin.load_textual_inversion`] for loading textual inversion embeddings
 
     Args:
@@ -738,7 +776,7 @@ class SDXLLongPromptWeightingPipeline(
 
         # set lora scale so that monkey patched LoRA
         # function of text encoder can correctly access it
-        if lora_scale is not None and isinstance(self, LoraLoaderMixin):
+        if lora_scale is not None and isinstance(self, StableDiffusionXLLoraLoaderMixin):
             self._lora_scale = lora_scale
 
         if prompt is not None and isinstance(prompt, str):
@@ -1607,7 +1645,9 @@ class SDXLLongPromptWeightingPipeline(
                 image_embeds = torch.cat([negative_image_embeds, image_embeds])
 
         # 3. Encode input prompt
-        (self.cross_attention_kwargs.get("scale", None) if self.cross_attention_kwargs is not None else None)
+        lora_scale = (
+            self._cross_attention_kwargs.get("scale", None) if self._cross_attention_kwargs is not None else None
+        )
 
         negative_prompt = negative_prompt if negative_prompt is not None else ""
 
@@ -1622,6 +1662,7 @@ class SDXLLongPromptWeightingPipeline(
             neg_prompt=negative_prompt,
             num_images_per_prompt=num_images_per_prompt,
             clip_skip=clip_skip,
+            lora_scale=lora_scale,
         )
         dtype = prompt_embeds.dtype
 

examples/community/mixture_canvas.py

@@ -9,7 +9,7 @@ import torch
 from numpy import exp, pi, sqrt
 from torchvision.transforms.functional import resize
 from tqdm.auto import tqdm
-from transformers import CLIPFeatureExtractor, CLIPTextModel, CLIPTokenizer
+from transformers import CLIPImageProcessor, CLIPTextModel, CLIPTokenizer
 
 from diffusers.models import AutoencoderKL, UNet2DConditionModel
 from diffusers.pipelines.pipeline_utils import DiffusionPipeline, StableDiffusionMixin
@@ -275,7 +275,7 @@ class StableDiffusionCanvasPipeline(DiffusionPipeline, StableDiffusionMixin):
         unet: UNet2DConditionModel,
         scheduler: Union[DDIMScheduler, LMSDiscreteScheduler, PNDMScheduler],
         safety_checker: StableDiffusionSafetyChecker,
-        feature_extractor: CLIPFeatureExtractor,
+        feature_extractor: CLIPImageProcessor,
     ):
         super().__init__()
         self.register_modules(