Fix mirror_community_pipeline.yml name

.github/ISSUE_TEMPLATE/bug-report.yml

@@ -63,27 +63,23 @@ body:
         
         Please tag a maximum of 2 people.
 
-        Questions on DiffusionPipeline (Saving, Loading, From pretrained, ...): @sayakpaul @DN6
+        Questions on DiffusionPipeline (Saving, Loading, From pretrained, ...):
 
         Questions on pipelines:
-        - Stable Diffusion @yiyixuxu @asomoza
+        - Stable Diffusion @yiyixuxu @DN6 @sayakpaul 
         - Stable Diffusion XL @yiyixuxu @sayakpaul @DN6 
-        - Stable Diffusion 3: @yiyixuxu @sayakpaul @DN6 @asomoza
         - Kandinsky @yiyixuxu 
         - ControlNet @sayakpaul @yiyixuxu @DN6 
         - T2I Adapter @sayakpaul @yiyixuxu @DN6 
         - IF @DN6 
-        - Text-to-Video / Video-to-Video @DN6 @a-r-r-o-w
+        - Text-to-Video / Video-to-Video @DN6 @sayakpaul 
         - Wuerstchen @DN6 
         - Other: @yiyixuxu @DN6
-        - Improving generation quality: @asomoza
 
         Questions on models:
         - UNet @DN6 @yiyixuxu @sayakpaul 
         - VAE @sayakpaul @DN6 @yiyixuxu 
-        - Transformers/Attention @DN6 @yiyixuxu @sayakpaul
-
-        Questions on single file checkpoints: @DN6
+        - Transformers/Attention @DN6 @yiyixuxu @sayakpaul @DN6 
 
         Questions on Schedulers: @yiyixuxu 
 
@@ -103,7 +99,7 @@ body:
 
         Questions on JAX- and MPS-related things: @pcuenca
 
-        Questions on audio pipelines: @sanchit-gandhi
+        Questions on audio pipelines: @DN6 
         
 
         

.github/PULL_REQUEST_TEMPLATE.md

@@ -39,7 +39,7 @@ members/contributors who may be interested in your PR.
 Core library:
 
 - Schedulers: @yiyixuxu 
-- Pipelines and pipeline callbacks: @yiyixuxu and @asomoza
+- Pipelines:  @sayakpaul @yiyixuxu @DN6
 - Training examples: @sayakpaul 
 - Docs: @stevhliu and @sayakpaul
 - JAX and MPS: @pcuenca
@@ -48,8 +48,7 @@ Core library:
 
 Integrations:
 
-- deepspeed: HF Trainer/Accelerate: @SunMarc
-- PEFT: @sayakpaul @BenjaminBossan
+- deepspeed: HF Trainer/Accelerate: @pacman100
 
 HF projects:
 

.github/workflows/benchmark.yml

@@ -13,17 +13,14 @@ env:
 
 jobs:
   torch_pipelines_cuda_benchmark_tests:
-    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:
-      group: aws-g6-4xlarge-plus
+    runs-on: [single-gpu, nvidia-gpu, a10, ci]
     container:
-      image: diffusers/diffusers-pytorch-compile-cuda
-      options: --shm-size "16gb" --ipc host --gpus 0
+      image: diffusers/diffusers-pytorch-cuda
+      options: --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/ --gpus 0
     steps:
       - name: Checkout diffusers
         uses: actions/checkout@v3
@@ -54,13 +51,3 @@ jobs:
         with:
           name: benchmark_test_reports
           path: benchmarks/benchmark_outputs
-
-      - name: Report success status
-        if: ${{ success() }}
-        run: |
-          pip install requests && python utils/notify_benchmarking_status.py --status=success
-
-      - name: Report failure status
-        if: ${{ failure() }}
-        run: |
-          pip install requests && python utils/notify_benchmarking_status.py --status=failure

.github/workflows/build_docker_images.yml

@@ -20,8 +20,7 @@ env:
 
 jobs:
   test-build-docker-images:
-    runs-on:
-      group: aws-general-8-plus
+    runs-on: [ self-hosted, intel-cpu, 8-cpu, ci ]
     if: github.event_name == 'pull_request'
     steps:
       - name: Set up Docker Buildx
@@ -51,8 +50,7 @@ jobs:
         if: steps.file_changes.outputs.all != ''
 
   build-and-push-docker-images:
-    runs-on:
-      group: aws-general-8-plus
+    runs-on: [ self-hosted, intel-cpu, 8-cpu, ci ]
     if: github.event_name != 'pull_request'
 
     permissions:

.github/workflows/mirror_community_pipeline.yml

@@ -22,9 +22,6 @@ on:
 
 jobs:
   mirror_community_pipeline:
-    env:
-      SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL_COMMUNITY_MIRROR }}
-
     runs-on: ubuntu-latest
     steps:
       # Checkout to correct ref
@@ -57,12 +54,8 @@ jobs:
           else
             # e.g. refs/tags/v0.28.1 -> v0.28.1
             echo "CHECKOUT_REF=${{ github.ref }}" >> $GITHUB_ENV
-            echo "PATH_IN_REPO=$(echo ${{ github.ref }} | sed 's/^refs\/tags\///')" >> $GITHUB_ENV
+            echo "PATH_IN_REPO=${${{ github.ref }}#refs/tags/}" >> $GITHUB_ENV
           fi
-      - name: Print env vars
-        run: |
-          echo "CHECKOUT_REF: ${{ env.CHECKOUT_REF }}"
-          echo "PATH_IN_REPO: ${{ env.PATH_IN_REPO }}"
       - uses: actions/checkout@v3
         with:
           ref: ${{ env.CHECKOUT_REF }}
@@ -74,8 +67,8 @@ jobs:
           python-version: "3.10"
       - name: Install dependencies
         run: |
-          python -m pip install --upgrade pip
-          pip install --upgrade huggingface_hub
+          python -m pip install uv
+          uv pip install --upgrade huggingface_hub
 
       # Check secret is set
       - name: whoami
@@ -90,13 +83,3 @@ jobs:
         env:
             PATH_IN_REPO: ${{ env.PATH_IN_REPO }}
             HF_TOKEN: ${{ secrets.HF_TOKEN_MIRROR_COMMUNITY_PIPELINES }}
-
-      - name: Report success status
-        if: ${{ success() }}
-        run: |
-          pip install requests && python utils/notify_community_pipelines_mirror.py --status=success
-
-      - name: Report failure status
-        if: ${{ failure() }}
-        run: |
-          pip install requests && python utils/notify_community_pipelines_mirror.py --status=failure

.github/workflows/nightly_tests.yml

@@ -7,7 +7,7 @@ on:
 
 env:
   DIFFUSERS_IS_CI: yes
-  HF_HUB_ENABLE_HF_TRANSFER: 1
+  HF_HOME: /mnt/cache
   OMP_NUM_THREADS: 8
   MKL_NUM_THREADS: 8
   PYTEST_TIMEOUT: 600
@@ -18,11 +18,8 @@ env:
 
 jobs:
   setup_torch_cuda_pipeline_matrix:
-    name: Setup Torch Pipelines CUDA Slow Tests Matrix
-    runs-on:
-      group: aws-general-8-plus
-    container:
-      image: diffusers/diffusers-pytorch-cpu
+    name: Setup Torch Pipelines Matrix
+    runs-on: diffusers/diffusers-pytorch-cpu
     outputs:
       pipeline_test_matrix: ${{ steps.fetch_pipeline_matrix.outputs.pipeline_test_matrix }}
     steps:
@@ -30,9 +27,13 @@ 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 .[test]
+          pip install -e .
           pip install huggingface_hub
       - name: Fetch Pipeline Matrix
         id: fetch_pipeline_matrix
@@ -49,18 +50,16 @@ jobs:
           path: reports
 
   run_nightly_tests_for_torch_pipelines:
-    name: Nightly Torch Pipelines CUDA Tests
+    name: Torch Pipelines CUDA Nightly Tests
     needs: setup_torch_cuda_pipeline_matrix
     strategy:
       fail-fast: false
-      max-parallel: 8
       matrix:
         module: ${{ fromJson(needs.setup_torch_cuda_pipeline_matrix.outputs.pipeline_test_matrix) }}
-    runs-on:
-      group: aws-g4dn-2xlarge
+    runs-on: [single-gpu, nvidia-gpu, t4, ci]
     container:
       image: diffusers/diffusers-pytorch-cuda
-      options: --shm-size "16gb" --ipc host --gpus 0
+      options: --shm-size "16gb" --ipc host -v /mnt/cache/.cache/huggingface/diffusers:/mnt/cache/ --gpus 0
     steps:
       - name: Checkout diffusers
         uses: actions/checkout@v3
@@ -68,16 +67,19 @@ jobs:
           fetch-depth: 2
       - name: NVIDIA-SMI
         run: nvidia-smi
+
       - name: Install dependencies
         run: |
           python -m venv /opt/venv && export PATH="/opt/venv/bin:$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: Pipeline CUDA Test
+
+      - name: Nightly PyTorch CUDA checkpoint (pipelines) tests
         env:
           HF_TOKEN: ${{ secrets.HF_TOKEN }}
           # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
@@ -88,37 +90,38 @@ jobs:
             --make-reports=tests_pipeline_${{ 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 utils/log_reports.py >> $GITHUB_STEP_SUMMARY
+          python scripts/log_reports.py >> $GITHUB_STEP_SUMMARY
 
   run_nightly_tests_for_other_torch_modules:
-    name: Nightly Torch CUDA Tests
-    runs-on:
-      group: aws-g4dn-2xlarge
+    name: Torch Non-Pipelines CUDA Nightly Tests
+    runs-on: [single-gpu, nvidia-gpu, t4, ci]
     container:
       image: diffusers/diffusers-pytorch-cuda
-      options: --shm-size "16gb" --ipc host --gpus 0
+      options: --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/ --gpus 0
     defaults:
       run:
         shell: bash
     strategy:
-      max-parallel: 2
       matrix:
-        module: [models, schedulers, lora, others, single_file, examples]
+        module: [models, schedulers, others, examples]
     steps:
     - name: Checkout diffusers
       uses: actions/checkout@v3
@@ -130,8 +133,8 @@ 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
 
@@ -155,6 +158,7 @@ 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 \
@@ -177,7 +181,64 @@ jobs:
       if: always()
       run: |
         pip install slack_sdk tabulate
-        python utils/log_reports.py >> $GITHUB_STEP_SUMMARY
+        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
 
   run_flax_tpu_tests:
     name: Nightly Flax TPU Tests
@@ -233,15 +294,14 @@ jobs:
       if: always()
       run: |
         pip install slack_sdk tabulate
-        python utils/log_reports.py >> $GITHUB_STEP_SUMMARY
+        python scripts/log_reports.py >> $GITHUB_STEP_SUMMARY
 
   run_nightly_onnx_tests:
     name: Nightly ONNXRuntime CUDA tests on Ubuntu
-    runs-on:
-      group: aws-g4dn-2xlarge
+    runs-on: [single-gpu, nvidia-gpu, t4, ci]
     container:
       image: diffusers/diffusers-onnxruntime-cuda
-      options: --gpus 0 --shm-size "16gb" --ipc host
+      options: --gpus 0 --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/
 
     steps:
     - name: Checkout diffusers
@@ -258,10 +318,11 @@ 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: |
@@ -288,7 +349,7 @@ jobs:
       if: always()
       run: |
         pip install slack_sdk tabulate
-        python utils/log_reports.py >> $GITHUB_STEP_SUMMARY
+        python scripts/log_reports.py >> $GITHUB_STEP_SUMMARY
 
   run_nightly_tests_apple_m1:
     name: Nightly PyTorch MPS tests on MacOS
@@ -350,4 +411,4 @@ jobs:
         if: always()
         run: |
           pip install slack_sdk tabulate
-          python utils/log_reports.py >> $GITHUB_STEP_SUMMARY
+          python scripts/log_reports.py >> $GITHUB_STEP_SUMMARY

.github/workflows/pr_dependency_test.yml

@@ -33,3 +33,4 @@ jobs:
         run: |
           python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
           pytest tests/others/test_dependencies.py
+      

.github/workflows/pr_test_fetcher.yml

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

@@ -71,8 +71,7 @@ jobs:
 
     name: LoRA - ${{ matrix.lib-versions }}
 
-    runs-on:
-      group: aws-general-8-plus
+    runs-on: [ self-hosted, intel-cpu, 8-cpu, ci ]
 
     container:
       image: diffusers/diffusers-pytorch-cpu

.github/workflows/pr_tests.yml

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

.github/workflows/push_tests.yml

@@ -11,16 +11,17 @@ 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:
-      group: aws-general-8-plus
+    runs-on: [ self-hosted, intel-cpu, 8-cpu, ci ]
     container:
       image: diffusers/diffusers-pytorch-cpu
     outputs:
@@ -51,18 +52,17 @@ jobs:
           path: reports
 
   torch_pipelines_cuda_tests:
-    name: Torch Pipelines CUDA Tests
+    name: Torch Pipelines CUDA Slow 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:
-      group: aws-g4dn-2xlarge
+    runs-on: [single-gpu, nvidia-gpu, t4, ci]
     container:
       image: diffusers/diffusers-pytorch-cuda
-      options: --shm-size "16gb" --ipc host --gpus 0
+      options: --shm-size "16gb" --ipc host -v /mnt/cache/.cache/huggingface/diffusers:/mnt/cache/ --gpus 0
     steps:
       - name: Checkout diffusers
         uses: actions/checkout@v3
@@ -103,11 +103,10 @@ jobs:
 
   torch_cuda_tests:
     name: Torch CUDA Tests
-    runs-on:
-      group: aws-g4dn-2xlarge
+    runs-on: [single-gpu, nvidia-gpu, t4, ci]
     container:
       image: diffusers/diffusers-pytorch-cuda
-      options: --shm-size "16gb" --ipc host --gpus 0
+      options: --shm-size "16gb" --ipc host -v /mnt/cache/.cache/huggingface/diffusers:/mnt/cache/ --gpus 0
     defaults:
       run:
         shell: bash
@@ -125,13 +124,12 @@ 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 PyTorch CUDA tests
+    - name: Run slow PyTorch CUDA tests
       env:
         HF_TOKEN: ${{ secrets.HF_TOKEN }}
         # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
@@ -155,6 +153,61 @@ 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
@@ -204,8 +257,7 @@ jobs:
 
   onnx_cuda_tests:
     name: ONNX CUDA Tests
-    runs-on:
-      group: aws-g4dn-2xlarge
+    runs-on: [single-gpu, nvidia-gpu, t4, ci]
     container:
       image: diffusers/diffusers-onnxruntime-cuda
       options: --shm-size "16gb" --ipc host -v /mnt/cache/.cache/huggingface:/mnt/cache/ --gpus 0
@@ -253,12 +305,11 @@ jobs:
   run_torch_compile_tests:
     name: PyTorch Compile CUDA tests
 
-    runs-on:
-      group: aws-g4dn-2xlarge
+    runs-on: [single-gpu, nvidia-gpu, t4, ci]
 
     container:
       image: diffusers/diffusers-pytorch-compile-cuda
-      options: --gpus 0 --shm-size "16gb" --ipc host
+      options: --gpus 0 --shm-size "16gb" --ipc host -v /mnt/cache/.cache/huggingface:/mnt/cache/
 
     steps:
     - name: Checkout diffusers
@@ -279,7 +330,6 @@ jobs:
     - name: Run example tests on GPU
       env:
         HF_TOKEN: ${{ secrets.HF_TOKEN }}
-        RUN_COMPILE: yes
       run: |
         python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile -s -v -k "compile" --make-reports=tests_torch_compile_cuda tests/
     - name: Failure short reports
@@ -296,12 +346,11 @@ jobs:
   run_xformers_tests:
     name: PyTorch xformers CUDA tests
 
-    runs-on:
-      group: aws-g4dn-2xlarge
+    runs-on: [single-gpu, nvidia-gpu, t4, ci]
 
     container:
       image: diffusers/diffusers-pytorch-xformers-cuda
-      options: --gpus 0 --shm-size "16gb" --ipc host
+      options: --gpus 0 --shm-size "16gb" --ipc host -v /mnt/cache/.cache/huggingface:/mnt/cache/
 
     steps:
     - name: Checkout diffusers
@@ -338,12 +387,11 @@ jobs:
   run_examples_tests:
     name: Examples PyTorch CUDA tests on Ubuntu
 
-    runs-on:
-      group: aws-g4dn-2xlarge
+    runs-on: [single-gpu, nvidia-gpu, t4, ci]
 
     container:
       image: diffusers/diffusers-pytorch-cuda
-      options: --gpus 0 --shm-size "16gb" --ipc host
+      options: --gpus 0 --shm-size "16gb" --ipc host -v /mnt/cache/.cache/huggingface:/mnt/cache/
 
     steps:
     - name: Checkout diffusers

.github/workflows/push_tests_fast.yml

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

.github/workflows/run_tests_from_a_pr.yml

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

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

@@ -1,40 +0,0 @@
-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 GPU runners
+name: SSH into runners
 
 on:
   workflow_dispatch:
@@ -22,8 +22,7 @@ env:
 jobs:
   ssh_runner:
     name: "SSH"
-    runs-on:
-      group: "${{ github.event.inputs.runner_type }}"
+    runs-on: [single-gpu, nvidia-gpu, "${{ github.event.inputs.runner_type }}", ci]
     container:
       image: ${{ github.event.inputs.docker_image }}
       options: --shm-size "16gb" --ipc host -v /mnt/cache/.cache/huggingface/diffusers:/mnt/cache/ --gpus 0 --privileged

.github/workflows/trufflehog.yml

@@ -1,15 +0,0 @@
-on:
-  push:
-
-name: Secret Leaks
-
-jobs:
-  trufflehog:
-    runs-on: ubuntu-latest
-    steps:
-    - name: Checkout code
-      uses: actions/checkout@v4
-      with:
-        fetch-depth: 0
-    - name: Secret Scanning
-      uses: trufflesecurity/trufflehog@main

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-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.
+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.
 
 **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.
@@ -245,7 +245,7 @@ The official training examples are maintained by the Diffusers' core maintainers
 This is because of the same reasons put forward in [6. Contribute a community pipeline](#6-contribute-a-community-pipeline) for official pipelines vs. community pipelines: It is not feasible for the core maintainers to maintain all possible training methods for diffusion models.
 If the Diffusers core maintainers and the community consider a certain training paradigm to be too experimental or not popular enough, the corresponding training code should be put in the `research_projects` folder and maintained by the author.
 
-Both official training and research examples consist of a directory that contains one or more training scripts, a `requirements.txt` file, and a `README.md` file. In order for the user to make use of the
+Both official training and research examples consist of a directory that contains one or more training scripts, a requirements.txt file, and a README.md file. In order for the user to make use of the
 training examples, it is required to clone the repository:
 
 ```bash
@@ -255,8 +255,7 @@ git clone https://github.com/huggingface/diffusers
 as well as to install all additional dependencies required for training:
 
 ```bash
-cd diffusers
-pip install -r examples/<your-example-folder>/requirements.txt
+pip install -r /examples/<your-example-folder>/requirements.txt
 ```
 
 Therefore when adding an example, the `requirements.txt` file shall define all pip dependencies required for your training example so that once all those are installed, the user can run the example's training script. See, for example, the [DreamBooth `requirements.txt` file](https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/requirements.txt).

PHILOSOPHY.md

@@ -70,7 +70,7 @@ The following design principles are followed:
 - Pipelines should be used **only** for inference.
 - Pipelines should be very readable, self-explanatory, and easy to tweak.
 - Pipelines should be designed to build on top of each other and be easy to integrate into higher-level APIs.
-- Pipelines are **not** intended to be feature-complete user interfaces. For feature-complete user interfaces one should rather have a look at [InvokeAI](https://github.com/invoke-ai/InvokeAI), [Diffuzers](https://github.com/abhishekkrthakur/diffuzers), and [lama-cleaner](https://github.com/Sanster/lama-cleaner).
+- Pipelines are **not** intended to be feature-complete user interfaces. For future complete user interfaces one should rather have a look at [InvokeAI](https://github.com/invoke-ai/InvokeAI), [Diffuzers](https://github.com/abhishekkrthakur/diffuzers), and [lama-cleaner](https://github.com/Sanster/lama-cleaner).
 - Every pipeline should have one and only one way to run it via a `__call__` method. The naming of the `__call__` arguments should be shared across all pipelines.
 - Pipelines should be named after the task they are intended to solve.
 - In almost all cases, novel diffusion pipelines shall be implemented in a new pipeline folder/file.
@@ -81,7 +81,7 @@ Models are designed as configurable toolboxes that are natural extensions of [Py
 
 The following design principles are followed:
 - Models correspond to **a type of model architecture**. *E.g.* the [`UNet2DConditionModel`] class is used for all UNet variations that expect 2D image inputs and are conditioned on some context.
-- All models can be found in [`src/diffusers/models`](https://github.com/huggingface/diffusers/tree/main/src/diffusers/models) and every model architecture shall be defined in its file, e.g. [`unets/unet_2d_condition.py`](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/unets/unet_2d_condition.py), [`transformers/transformer_2d.py`](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/transformers/transformer_2d.py), etc...
+- All models can be found in [`src/diffusers/models`](https://github.com/huggingface/diffusers/tree/main/src/diffusers/models) and every model architecture shall be defined in its file, e.g. [`unet_2d_condition.py`](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/unet_2d_condition.py), [`transformer_2d.py`](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/transformer_2d.py), etc...
 - Models **do not** follow the single-file policy and should make use of smaller model building blocks, such as [`attention.py`](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention.py), [`resnet.py`](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/resnet.py), [`embeddings.py`](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/embeddings.py), etc... **Note**: This is in stark contrast to Transformers' modeling files and shows that models do not really follow the single-file policy.
 - Models intend to expose complexity, just like PyTorch's `Module` class, and give clear error messages.
 - Models all inherit from `ModelMixin` and `ConfigMixin`.
@@ -90,7 +90,7 @@ The following design principles are followed:
 - To integrate new model checkpoints whose general architecture can be classified as an architecture that already exists in Diffusers, the existing model architecture shall be adapted to make it work with the new checkpoint. One should only create a new file if the model architecture is fundamentally different.
 - Models should be designed to be easily extendable to future changes. This can be achieved by limiting public function arguments, configuration arguments, and "foreseeing" future changes, *e.g.* it is usually better to add `string` "...type" arguments that can easily be extended to new future types instead of boolean `is_..._type` arguments. Only the minimum amount of changes shall be made to existing architectures to make a new model checkpoint work.
 - The model design is a difficult trade-off between keeping code readable and concise and supporting many model checkpoints. For most parts of the modeling code, classes shall be adapted for new model checkpoints, while there are some exceptions where it is preferred to add new classes to make sure the code is kept concise and
-readable long-term, such as [UNet blocks](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/unets/unet_2d_blocks.py) and [Attention processors](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_processor.py).
+readable long-term, such as [UNet blocks](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/unet_2d_blocks.py) and [Attention processors](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_processor.py).
 
 ### Schedulers
 

README.md

@@ -20,11 +20,21 @@ limitations under the License.
     <br>
 <p>
 <p align="center">
-    <a href="https://github.com/huggingface/diffusers/blob/main/LICENSE"><img alt="GitHub" src="https://img.shields.io/github/license/huggingface/datasets.svg?color=blue"></a>
-    <a href="https://github.com/huggingface/diffusers/releases"><img alt="GitHub release" src="https://img.shields.io/github/release/huggingface/diffusers.svg"></a>
-    <a href="https://pepy.tech/project/diffusers"><img alt="GitHub release" src="https://static.pepy.tech/badge/diffusers/month"></a>
-    <a href="CODE_OF_CONDUCT.md"><img alt="Contributor Covenant" src="https://img.shields.io/badge/Contributor%20Covenant-2.1-4baaaa.svg"></a>
-    <a href="https://twitter.com/diffuserslib"><img alt="X account" src="https://img.shields.io/twitter/url/https/twitter.com/diffuserslib.svg?style=social&label=Follow%20%40diffuserslib"></a>
+    <a href="https://github.com/huggingface/diffusers/blob/main/LICENSE">
+        <img alt="GitHub" src="https://img.shields.io/github/license/huggingface/datasets.svg?color=blue">
+    </a>
+    <a href="https://github.com/huggingface/diffusers/releases">
+        <img alt="GitHub release" src="https://img.shields.io/github/release/huggingface/diffusers.svg">
+    </a>
+    <a href="https://pepy.tech/project/diffusers">
+        <img alt="GitHub release" src="https://static.pepy.tech/badge/diffusers/month">
+    </a>
+    <a href="CODE_OF_CONDUCT.md">
+        <img alt="Contributor Covenant" src="https://img.shields.io/badge/Contributor%20Covenant-2.1-4baaaa.svg">
+    </a>
+    <a href="https://twitter.com/diffuserslib">
+        <img alt="X account" src="https://img.shields.io/twitter/url/https/twitter.com/diffuserslib.svg?style=social&label=Follow%20%40diffuserslib">
+    </a>
 </p>
 
 🤗 Diffusers is the go-to library for state-of-the-art pretrained diffusion models for generating images, audio, and even 3D structures of molecules. Whether you're looking for a simple inference solution or training your own diffusion models, 🤗 Diffusers is a modular toolbox that supports both. Our library is designed with a focus on [usability over performance](https://huggingface.co/docs/diffusers/conceptual/philosophy#usability-over-performance), [simple over easy](https://huggingface.co/docs/diffusers/conceptual/philosophy#simple-over-easy), and [customizability over abstractions](https://huggingface.co/docs/diffusers/conceptual/philosophy#tweakable-contributorfriendly-over-abstraction).
@@ -67,7 +77,7 @@ 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 30,000+ 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 25.000+ checkpoints):
 
 ```python
 from diffusers import DiffusionPipeline
@@ -209,7 +219,7 @@ 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
-- +14,000 other amazing GitHub repositories 💪
+- +11.000 other amazing GitHub repositories 💪
 
 Thank you for using us ❤️.
 

benchmarks/run_all.py

@@ -40,7 +40,7 @@ def main():
         print(f"****** Running file: {file} ******")
 
         # Run with canonical settings.
-        if file != "benchmark_text_to_image.py" and file != "benchmark_ip_adapters.py":
+        if file != "benchmark_text_to_image.py":
             command = f"python {file}"
             run_command(command.split())
 
@@ -49,10 +49,6 @@ def main():
 
     # Run variants.
     for file in python_files:
-        # See: https://github.com/pytorch/pytorch/issues/129637
-        if file == "benchmark_ip_adapters.py":
-            continue
-
         if file == "benchmark_text_to_image.py":
             for ckpt in ALL_T2I_CKPTS:
                 command = f"python {file} --ckpt {ckpt}"

docker/diffusers-doc-builder/Dockerfile

@@ -42,7 +42,7 @@ RUN python3.10 -m pip install --no-cache-dir --upgrade pip uv==0.1.11 && \
         huggingface-hub \
         Jinja2 \
         librosa \
-        numpy==1.26.4 \
+        numpy \
         scipy \
         tensorboard \
         transformers \

docker/diffusers-flax-cpu/Dockerfile

@@ -40,7 +40,7 @@ RUN python3 -m pip install --no-cache-dir --upgrade pip uv==0.1.11 && \
         huggingface-hub \
         Jinja2 \
         librosa \
-        numpy==1.26.4 \
+        numpy \
         scipy \
         tensorboard \
         transformers

docker/diffusers-flax-tpu/Dockerfile

@@ -42,7 +42,7 @@ RUN python3 -m pip install --no-cache-dir --upgrade pip uv==0.1.11 && \
         huggingface-hub \
         Jinja2 \
         librosa \        
-        numpy==1.26.4 \
+        numpy \
         scipy \
         tensorboard \
         transformers

docker/diffusers-onnxruntime-cpu/Dockerfile

@@ -40,7 +40,7 @@ RUN python3 -m pip install --no-cache-dir --upgrade pip uv==0.1.11 && \
         huggingface-hub \
         Jinja2 \
         librosa \
-        numpy==1.26.4 \
+        numpy \
         scipy \
         tensorboard \
         transformers

docker/diffusers-onnxruntime-cuda/Dockerfile

@@ -38,10 +38,9 @@ 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 \
+        numpy \
         scipy \
         tensorboard \
         transformers

docker/diffusers-pytorch-compile-cuda/Dockerfile

@@ -17,7 +17,6 @@ RUN apt install -y bash \
     libsndfile1-dev \
     libgl1 \
     python3.10 \
-    python3.10-dev \
     python3-pip \
     python3.10-venv && \
     rm -rf /var/lib/apt/lists
@@ -38,10 +37,9 @@ 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 \
+    numpy \
     scipy \
     tensorboard \
     transformers

docker/diffusers-pytorch-cpu/Dockerfile

@@ -16,7 +16,6 @@ RUN apt install -y bash \
                    ca-certificates \
                    libsndfile1-dev \
                    python3.10 \
-                   python3.10-dev \
                    python3-pip \
                    libgl1 \
                    python3.10-venv && \
@@ -41,7 +40,7 @@ RUN python3.10 -m pip install --no-cache-dir --upgrade pip uv==0.1.11 && \
         huggingface-hub \
         Jinja2 \
         librosa \
-        numpy==1.26.4 \
+        numpy \
         scipy \
         tensorboard \
         transformers matplotlib

docker/diffusers-pytorch-cuda/Dockerfile

@@ -17,7 +17,6 @@ RUN apt install -y bash \
     libsndfile1-dev \
     libgl1 \
     python3.10 \
-    python3.10-dev \
     python3-pip \
     python3.10-venv && \
     rm -rf /var/lib/apt/lists
@@ -38,10 +37,9 @@ 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 \
+    numpy \
     scipy \
     tensorboard \
     transformers \

docker/diffusers-pytorch-xformers-cuda/Dockerfile

@@ -17,7 +17,6 @@ RUN apt install -y bash \
                    libsndfile1-dev \
                    libgl1 \
                    python3.10 \
-                   python3.10-dev \
                    python3-pip \
                    python3.10-venv && \
     rm -rf /var/lib/apt/lists
@@ -38,10 +37,9 @@ 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 \
+        numpy \
         scipy \
         tensorboard \
         transformers \

docs/source/en/_toctree.yml

@@ -21,8 +21,6 @@
     title: Load LoRAs for inference
   - local: tutorials/fast_diffusion
     title: Accelerate inference of text-to-image diffusion models
-  - local: tutorials/inference_with_big_models
-    title: Working with big models
   title: Tutorials
 - sections:
   - local: using-diffusers/loading
@@ -83,8 +81,6 @@
     title: Kandinsky
   - local: using-diffusers/ip_adapter
     title: IP-Adapter
-  - local: using-diffusers/pag
-    title: PAG
   - local: using-diffusers/controlnet
     title: ControlNet
   - local: using-diffusers/t2i_adapter
@@ -111,8 +107,7 @@
     title: Create a dataset for training
   - local: training/adapt_a_model
     title: Adapt a model to a new task
-  - isExpanded: false
-    sections:
+  - sections:
     - local: training/unconditional_training
       title: Unconditional image generation
     - local: training/text2image
@@ -130,8 +125,8 @@
     - local: training/instructpix2pix
       title: InstructPix2Pix
     title: Models
-  - isExpanded: false
-    sections:
+    isExpanded: false
+  - sections:
     - local: training/text_inversion
       title: Textual Inversion
     - local: training/dreambooth
@@ -145,6 +140,7 @@
     - local: training/ddpo
       title: Reinforcement learning training with DDPO
     title: Methods
+    isExpanded: false
   title: Training
 - sections:
   - local: optimization/fp16
@@ -191,12 +187,7 @@
     title: Evaluating Diffusion Models
   title: Conceptual Guides
 - sections:
-  - local: community_projects
-    title: Projects built with Diffusers
-  title: Community Projects
   - sections:
-  - isExpanded: false
-    sections:
     - local: api/configuration
       title: Configuration
     - local: api/logging
@@ -204,8 +195,8 @@
     - local: api/outputs
       title: Outputs
     title: Main Classes
-  - isExpanded: false
-    sections:
+    isExpanded: false
+  - sections:
     - local: api/loaders/ip_adapter
       title: IP-Adapter
     - local: api/loaders/lora
@@ -219,8 +210,8 @@
     - local: api/loaders/peft
       title: PEFT
     title: Loaders
-  - isExpanded: false
-    sections:
+    isExpanded: false
+  - sections:
     - local: api/models/overview
       title: Overview
     - local: api/models/unet
@@ -239,16 +230,10 @@
       title: VQModel
     - local: api/models/autoencoderkl
       title: AutoencoderKL
-    - local: api/models/autoencoderkl_cogvideox
-      title: AutoencoderKLCogVideoX
     - local: api/models/asymmetricautoencoderkl
       title: AsymmetricAutoencoderKL
-    - local: api/models/stable_cascade_unet
-      title: StableCascadeUNet
     - local: api/models/autoencoder_tiny
       title: Tiny AutoEncoder
-    - local: api/models/autoencoder_oobleck
-      title: Oobleck AutoEncoder
     - local: api/models/consistency_decoder_vae
       title: ConsistencyDecoderVAE
     - local: api/models/transformer2d
@@ -259,35 +244,15 @@
       title: DiTTransformer2DModel
     - local: api/models/hunyuan_transformer2d
       title: HunyuanDiT2DModel
-    - local: api/models/aura_flow_transformer2d
-      title: AuraFlowTransformer2DModel
-    - local: api/models/flux_transformer
-      title: FluxTransformer2DModel
-    - local: api/models/latte_transformer3d
-      title: LatteTransformer3DModel
-    - local: api/models/cogvideox_transformer3d
-      title: CogVideoXTransformer3DModel
-    - local: api/models/lumina_nextdit2d
-      title: LuminaNextDiT2DModel
     - local: api/models/transformer_temporal
       title: TransformerTemporalModel
-    - local: api/models/sd3_transformer2d
-      title: SD3Transformer2DModel
-    - local: api/models/stable_audio_transformer
-      title: StableAudioDiTModel
     - 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
-    - local: api/models/controlnet_sparsectrl
-      title: SparseControlNetModel
     title: Models
-  - isExpanded: false
-    sections:
+    isExpanded: false
+  - sections:
     - local: api/pipelines/overview
       title: Overview
     - local: api/pipelines/amused
@@ -300,22 +265,14 @@
       title: AudioLDM
     - local: api/pipelines/audioldm2
       title: AudioLDM 2
-    - local: api/pipelines/aura_flow
-      title: AuraFlow
     - local: api/pipelines/auto_pipeline
       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
       title: ControlNet
-    - local: api/pipelines/controlnet_hunyuandit
-      title: ControlNet with Hunyuan-DiT
-    - local: api/pipelines/controlnet_sd3
-      title: ControlNet with Stable Diffusion 3
     - local: api/pipelines/controlnet_sdxl
       title: ControlNet with Stable Diffusion XL
     - local: api/pipelines/controlnetxs
@@ -334,8 +291,6 @@
       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
@@ -348,26 +303,18 @@
       title: Kandinsky 2.2
     - local: api/pipelines/kandinsky3
       title: Kandinsky 3
-    - local: api/pipelines/kolors
-      title: Kolors
     - local: api/pipelines/latent_consistency_models
       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
-      title: Lumina-T2X
     - local: api/pipelines/marigold
       title: Marigold
     - local: api/pipelines/panorama
       title: MultiDiffusion
     - local: api/pipelines/musicldm
       title: MusicLDM
-    - local: api/pipelines/pag
-      title: PAG
     - local: api/pipelines/paint_by_example
       title: Paint by Example
     - local: api/pipelines/pia
@@ -382,8 +329,6 @@
       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:
@@ -405,8 +350,6 @@
         title: Safe Stable Diffusion
       - local: api/pipelines/stable_diffusion/stable_diffusion_2
         title: Stable Diffusion 2
-      - local: api/pipelines/stable_diffusion/stable_diffusion_3
-        title: Stable Diffusion 3
       - local: api/pipelines/stable_diffusion/stable_diffusion_xl
         title: Stable Diffusion XL
       - local: api/pipelines/stable_diffusion/sdxl_turbo
@@ -439,16 +382,14 @@
     - local: api/pipelines/wuerstchen
       title: Wuerstchen
     title: Pipelines
-  - isExpanded: false
-    sections:
+    isExpanded: false
+  - sections:
     - local: api/schedulers/overview
       title: Overview
     - local: api/schedulers/cm_stochastic_iterative
       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
@@ -473,10 +414,6 @@
       title: EulerAncestralDiscreteScheduler
     - local: api/schedulers/euler
       title: EulerDiscreteScheduler
-    - local: api/schedulers/flow_match_euler_discrete
-      title: FlowMatchEulerDiscreteScheduler
-    - local: api/schedulers/flow_match_heun_discrete
-      title: FlowMatchHeunDiscreteScheduler
     - local: api/schedulers/heun
       title: HeunDiscreteScheduler
     - local: api/schedulers/ipndm
@@ -506,8 +443,8 @@
     - local: api/schedulers/vq_diffusion
       title: VQDiffusionScheduler
     title: Schedulers
-  - isExpanded: false
-    sections:
+    isExpanded: false
+  - sections:
     - local: api/internal_classes_overview
       title: Overview
     - local: api/attnprocessor
@@ -523,4 +460,5 @@
     - local: api/video_processor
       title: Video Processor
     title: Internal classes
+    isExpanded: false
   title: API

docs/source/en/api/attnprocessor.md

@@ -41,6 +41,12 @@ An attention processor is a class for applying different types of attention mech
 ## FusedAttnProcessor2_0
 [[autodoc]] models.attention_processor.FusedAttnProcessor2_0
 
+## LoRAAttnAddedKVProcessor
+[[autodoc]] models.attention_processor.LoRAAttnAddedKVProcessor
+
+## LoRAXFormersAttnProcessor
+[[autodoc]] models.attention_processor.LoRAXFormersAttnProcessor
+
 ## SlicedAttnProcessor
 [[autodoc]] models.attention_processor.SlicedAttnProcessor
 

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

@@ -12,13 +12,10 @@ 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 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:
+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:
 
-- [`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.
+- [`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.
 
 <Tip>
 
@@ -26,22 +23,10 @@ To learn more about how to load LoRA weights, see the [LoRA](../../using-diffuse
 
 </Tip>
 
-## StableDiffusionLoraLoaderMixin
+## LoraLoaderMixin
 
-[[autodoc]] loaders.lora_pipeline.StableDiffusionLoraLoaderMixin
+[[autodoc]] loaders.lora.LoraLoaderMixin
 
 ## StableDiffusionXLLoraLoaderMixin
 
-[[autodoc]] loaders.lora_pipeline.StableDiffusionXLLoraLoaderMixin
-
-## SD3LoraLoaderMixin
-
-[[autodoc]] loaders.lora_pipeline.SD3LoraLoaderMixin
-
-## AmusedLoraLoaderMixin
-
-[[autodoc]] loaders.lora_pipeline.AmusedLoraLoaderMixin
-
-## LoraBaseMixin
-
-[[autodoc]] loaders.lora_base.LoraBaseMixin
+[[autodoc]] loaders.lora.StableDiffusionXLLoraLoaderMixin

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`], [`SD3Transformer2DModel`] to operate with 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`] to load an adapter.
 
 <Tip>
 

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

@@ -22,7 +22,6 @@ The [`~loaders.FromSingleFileMixin.from_single_file`] method allows you to load:
 
 ## Supported pipelines
 
-- [`CogVideoXPipeline`]
 - [`StableDiffusionPipeline`]
 - [`StableDiffusionImg2ImgPipeline`]
 - [`StableDiffusionInpaintPipeline`]
@@ -36,7 +35,6 @@ The [`~loaders.FromSingleFileMixin.from_single_file`] method allows you to load:
 - [`StableDiffusionXLInstructPix2PixPipeline`]
 - [`StableDiffusionXLControlNetPipeline`]
 - [`StableDiffusionXLKDiffusionPipeline`]
-- [`StableDiffusion3Pipeline`]
 - [`LatentConsistencyModelPipeline`]
 - [`LatentConsistencyModelImg2ImgPipeline`]
 - [`StableDiffusionControlNetXSPipeline`]
@@ -50,10 +48,7 @@ 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.StableDiffusionLoraLoaderMixin.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.LoraLoaderMixin.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/aura_flow_transformer2d.md

@@ -1,19 +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.
--->
-
-# AuraFlowTransformer2DModel
-
-A Transformer model for image-like data from [AuraFlow](https://blog.fal.ai/auraflow/).
-
-## AuraFlowTransformer2DModel
-
-[[autodoc]] AuraFlowTransformer2DModel

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

@@ -1,38 +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.
--->
-
-# 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.md

@@ -21,7 +21,7 @@ The abstract from the paper is:
 ## Loading from the original format
 
 By default the [`AutoencoderKL`] should be loaded with [`~ModelMixin.from_pretrained`], but it can also be loaded
-from the original format using [`FromOriginalModelMixin.from_single_file`] as follows:
+from the original format using [`FromOriginalVAEMixin.from_single_file`] as follows:
 
 ```py
 from diffusers import AutoencoderKL

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

@@ -1,37 +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. -->
-
-# 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

@@ -1,30 +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. -->
-
-# 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.md

@@ -21,7 +21,7 @@ The abstract from the paper is:
 ## Loading from the original format
 
 By default the [`ControlNetModel`] should be loaded with [`~ModelMixin.from_pretrained`], but it can also be loaded
-from the original format using [`FromOriginalModelMixin.from_single_file`] as follows:
+from the original format using [`FromOriginalControlnetMixin.from_single_file`] as follows:
 
 ```py
 from diffusers import StableDiffusionControlNetPipeline, ControlNetModel

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

@@ -1,37 +0,0 @@
-<!--Copyright 2024 The HuggingFace Team and Tencent Hunyuan 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.
--->
-
-# HunyuanDiT2DControlNetModel
-
-HunyuanDiT2DControlNetModel is an implementation of ControlNet for [Hunyuan-DiT](https://arxiv.org/abs/2405.08748).
-
-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 Hunyuan-DiT generation. For example, if you provide a depth map, the ControlNet model generates an image that'll preserve the spatial information from the depth map. It is a more flexible and accurate way to control the image generation process.
-
-The abstract from the paper is:
-
-*We present ControlNet, a neural network architecture to add spatial conditioning controls to large, pretrained text-to-image diffusion models. ControlNet locks the production-ready large diffusion models, and reuses their deep and robust encoding layers pretrained with billions of images as a strong backbone to learn a diverse set of conditional controls. The neural architecture is connected with "zero convolutions" (zero-initialized convolution layers) that progressively grow the parameters from zero and ensure that no harmful noise could affect the finetuning. We test various conditioning controls, eg, edges, depth, segmentation, human pose, etc, with Stable Diffusion, using single or multiple conditions, with or without prompts. We show that the training of ControlNets is robust with small (<50k) and large (>1m) datasets. Extensive results show that ControlNet may facilitate wider applications to control image diffusion models.*
-
-This code is implemented by Tencent Hunyuan Team. You can find pre-trained checkpoints for Hunyuan-DiT ControlNets on [Tencent Hunyuan](https://huggingface.co/Tencent-Hunyuan).
-
-## Example For Loading HunyuanDiT2DControlNetModel
-
-```py
-from diffusers import HunyuanDiT2DControlNetModel
-import torch
-controlnet = HunyuanDiT2DControlNetModel.from_pretrained("Tencent-Hunyuan/HunyuanDiT-v1.1-ControlNet-Diffusers-Pose", torch_dtype=torch.float16)
-```
-
-## HunyuanDiT2DControlNetModel
-
-[[autodoc]] HunyuanDiT2DControlNetModel

docs/source/en/api/models/controlnet_sd3.md

@@ -1,42 +0,0 @@
-<!--Copyright 2024 The HuggingFace Team and The InstantX 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.
--->
-
-# SD3ControlNetModel
-
-SD3ControlNetModel is an implementation of ControlNet for Stable Diffusion 3.
-
-The ControlNet model was introduced in [Adding Conditional Control to Text-to-Image Diffusion Models](https://huggingface.co/papers/2302.05543) by Lvmin Zhang, Anyi Rao, Maneesh Agrawala. It provides a greater degree of control over text-to-image generation by conditioning the model on additional inputs such as edge maps, depth maps, segmentation maps, and keypoints for pose detection.
-
-The abstract from the paper is:
-
-*We present ControlNet, a neural network architecture to add spatial conditioning controls to large, pretrained text-to-image diffusion models. ControlNet locks the production-ready large diffusion models, and reuses their deep and robust encoding layers pretrained with billions of images as a strong backbone to learn a diverse set of conditional controls. The neural architecture is connected with "zero convolutions" (zero-initialized convolution layers) that progressively grow the parameters from zero and ensure that no harmful noise could affect the finetuning. We test various conditioning controls, eg, edges, depth, segmentation, human pose, etc, with Stable Diffusion, using single or multiple conditions, with or without prompts. We show that the training of ControlNets is robust with small (<50k) and large (>1m) datasets. Extensive results show that ControlNet may facilitate wider applications to control image diffusion models.*
-
-## Loading from the original format
-
-By default the [`SD3ControlNetModel`] should be loaded with [`~ModelMixin.from_pretrained`].
-
-```py
-from diffusers import StableDiffusion3ControlNetPipeline
-from diffusers.models import SD3ControlNetModel, SD3MultiControlNetModel
-
-controlnet = SD3ControlNetModel.from_pretrained("InstantX/SD3-Controlnet-Canny")
-pipe = StableDiffusion3ControlNetPipeline.from_pretrained("stabilityai/stable-diffusion-3-medium-diffusers", controlnet=controlnet)
-```
-
-## SD3ControlNetModel
-
-[[autodoc]] SD3ControlNetModel
-
-## SD3ControlNetOutput
-
-[[autodoc]] models.controlnet_sd3.SD3ControlNetOutput
-

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

@@ -1,46 +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. -->
-
-# 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

@@ -1,19 +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.
--->
-
-# 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/latte_transformer3d.md

@@ -1,19 +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.
--->
-
-## LatteTransformer3DModel
-
-A Diffusion Transformer model for 3D data from [Latte](https://github.com/Vchitect/Latte).
-
-## LatteTransformer3DModel
-
-[[autodoc]] LatteTransformer3DModel

docs/source/en/api/models/lumina_nextdit2d.md

@@ -1,20 +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.
--->
-
-# LuminaNextDiT2DModel
-
-A Next Version of Diffusion Transformer model for 2D data from [Lumina-T2X](https://github.com/Alpha-VLLM/Lumina-T2X).
-
-## LuminaNextDiT2DModel
-
-[[autodoc]] LuminaNextDiT2DModel
-

docs/source/en/api/models/sd3_transformer2d.md

@@ -1,19 +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.
--->
-
-# SD3 Transformer Model
-
-The Transformer model introduced in [Stable Diffusion 3](https://hf.co/papers/2403.03206). Its novelty lies in the MMDiT transformer block.
-
-## SD3Transformer2DModel
-
-[[autodoc]] SD3Transformer2DModel

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

@@ -1,19 +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.
--->
-
-# 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

@@ -1,19 +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.
--->
-
-# 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/models/transformer2d.md

@@ -38,4 +38,4 @@ It is assumed one of the input classes is the masked latent pixel. The predicted
 
 ## Transformer2DModelOutput
 
-[[autodoc]] models.modeling_outputs.Transformer2DModelOutput
+[[autodoc]] models.transformers.transformer_2d.Transformer2DModelOutput

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

@@ -25,9 +25,6 @@ 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
@@ -81,6 +78,7 @@ output = pipe(
 )
 frames = output.frames[0]
 export_to_gif(frames, "animation.gif")
+
 ```
 
 Here are some sample outputs:
@@ -103,266 +101,6 @@ 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.
@@ -565,6 +303,7 @@ output = pipe(
 )
 frames = output.frames[0]
 export_to_gif(frames, "animation.gif")
+
 ```
 
 <table>
@@ -639,6 +378,7 @@ output = pipe(
 )
 frames = output.frames[0]
 export_to_gif(frames, "animation.gif")
+
 ```
 
 <table>
@@ -823,37 +563,12 @@ export_to_gif(frames, "animatelcm-motion-lora.gif")
 </table>
 
 
-## Using `from_single_file` with the MotionAdapter
-
-`diffusers>=0.30.0` supports loading the AnimateDiff checkpoints into the `MotionAdapter` in their original format via `from_single_file`
-
-```python
-from diffusers import MotionAdapter
-
-ckpt_path = "https://huggingface.co/Lightricks/LongAnimateDiff/blob/main/lt_long_mm_32_frames.ckpt"
-
-adapter = MotionAdapter.from_single_file(ckpt_path, torch_dtype=torch.float16)
-pipe = AnimateDiffPipeline.from_pretrained("emilianJR/epiCRealism", motion_adapter=adapter)
-```
-
 ## AnimateDiffPipeline
 
 [[autodoc]] AnimateDiffPipeline
   - all
   - __call__
 
-## AnimateDiffControlNetPipeline
-
-[[autodoc]] AnimateDiffControlNetPipeline
-  - all
-  - __call__
-
-## AnimateDiffSparseControlNetPipeline
-
-[[autodoc]] AnimateDiffSparseControlNetPipeline
-  - all
-  - __call__
-
 ## AnimateDiffSDXLPipeline
 
 [[autodoc]] AnimateDiffSDXLPipeline

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

@@ -1,29 +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.
--->
-
-# AuraFlow
-
-AuraFlow is inspired by [Stable Diffusion 3](../pipelines/stable_diffusion/stable_diffusion_3.md) and is by far the largest text-to-image generation model that comes with an Apache 2.0 license. This model achieves state-of-the-art results on the [GenEval](https://github.com/djghosh13/geneval) benchmark.
-
-It was developed by the Fal team and more details about it can be found in [this blog post](https://blog.fal.ai/auraflow/).
-
-<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.
-
-</Tip>
-
-## AuraFlowPipeline
-
-[[autodoc]] AuraFlowPipeline
-	- all
-	- __call__

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

@@ -1,91 +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.
--->
-
-# 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/controlnet_hunyuandit.md

@@ -1,36 +0,0 @@
-<!--Copyright 2024 The HuggingFace Team and Tencent Hunyuan 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.
--->
-
-# ControlNet with Hunyuan-DiT
-
-HunyuanDiTControlNetPipeline is an implementation of ControlNet for [Hunyuan-DiT](https://arxiv.org/abs/2405.08748).
-
-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 Hunyuan-DiT generation. For example, if you provide a depth map, the ControlNet model generates an image that'll preserve the spatial information from the depth map. It is a more flexible and accurate way to control the image generation process.
-
-The abstract from the paper is:
-
-*We present ControlNet, a neural network architecture to add spatial conditioning controls to large, pretrained text-to-image diffusion models. ControlNet locks the production-ready large diffusion models, and reuses their deep and robust encoding layers pretrained with billions of images as a strong backbone to learn a diverse set of conditional controls. The neural architecture is connected with "zero convolutions" (zero-initialized convolution layers) that progressively grow the parameters from zero and ensure that no harmful noise could affect the finetuning. We test various conditioning controls, eg, edges, depth, segmentation, human pose, etc, with Stable Diffusion, using single or multiple conditions, with or without prompts. We show that the training of ControlNets is robust with small (<50k) and large (>1m) datasets. Extensive results show that ControlNet may facilitate wider applications to control image diffusion models.*
-
-This code is implemented by Tencent Hunyuan Team. You can find pre-trained checkpoints for Hunyuan-DiT ControlNets on [Tencent Hunyuan](https://huggingface.co/Tencent-Hunyuan).
-
-<Tip>
-
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
-
-</Tip>
-
-## HunyuanDiTControlNetPipeline
-[[autodoc]] HunyuanDiTControlNetPipeline
-	- all
-	- __call__

docs/source/en/api/pipelines/controlnet_sd3.md

@@ -1,39 +0,0 @@
-<!--Copyright 2023 The HuggingFace Team and The InstantX 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.
--->
-
-# ControlNet with Stable Diffusion 3
-
-StableDiffusion3ControlNetPipeline is an implementation of ControlNet for Stable Diffusion 3.
-
-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 a depth map, the ControlNet model generates an image that'll preserve the spatial information from the depth map. It is a more flexible and accurate way to control the image generation process.
-
-The abstract from the paper is:
-
-*We present ControlNet, a neural network architecture to add spatial conditioning controls to large, pretrained text-to-image diffusion models. ControlNet locks the production-ready large diffusion models, and reuses their deep and robust encoding layers pretrained with billions of images as a strong backbone to learn a diverse set of conditional controls. The neural architecture is connected with "zero convolutions" (zero-initialized convolution layers) that progressively grow the parameters from zero and ensure that no harmful noise could affect the finetuning. We test various conditioning controls, eg, edges, depth, segmentation, human pose, etc, with Stable Diffusion, using single or multiple conditions, with or without prompts. We show that the training of ControlNets is robust with small (<50k) and large (>1m) datasets. Extensive results show that ControlNet may facilitate wider applications to control image diffusion models.*
-
-This code is implemented by [The InstantX Team](https://huggingface.co/InstantX). You can find pre-trained checkpoints for SD3-ControlNet on [The InstantX Team](https://huggingface.co/InstantX) Hub profile.
-
-<Tip>
-
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
-
-</Tip>
-
-## StableDiffusion3ControlNetPipeline
-[[autodoc]] StableDiffusion3ControlNetPipeline
-	- all
-	- __call__
-
-## StableDiffusion3PipelineOutput
-[[autodoc]] pipelines.stable_diffusion_3.pipeline_output.StableDiffusion3PipelineOutput

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

@@ -1,165 +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.
--->
-
-# 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/hunyuandit.md

@@ -1,4 +1,4 @@
-<!--Copyright 2024 The HuggingFace Team and Tencent Hunyuan Team. All rights reserved.
+<!--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
@@ -34,12 +34,6 @@ Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers.m
 
 </Tip>
 
-<Tip>
-
-You can further improve generation quality by passing the generated image from [`HungyuanDiTPipeline`] to the [SDXL refiner](../../using-diffusers/sdxl#base-to-refiner-model) model.
-
-</Tip>
-
 ## Optimization
 
 You can optimize the pipeline's runtime and memory consumption with torch.compile and feed-forward chunking. To learn about other optimization methods, check out the [Speed up inference](../../optimization/fp16) and [Reduce memory usage](../../optimization/memory) guides. 

docs/source/en/api/pipelines/kandinsky3.md

@@ -11,7 +11,7 @@ specific language governing permissions and limitations under the License.
 
 Kandinsky 3 is created by [Vladimir Arkhipkin](https://github.com/oriBetelgeuse),[Anastasia Maltseva](https://github.com/NastyaMittseva),[Igor Pavlov](https://github.com/boomb0om),[Andrei Filatov](https://github.com/anvilarth),[Arseniy Shakhmatov](https://github.com/cene555),[Andrey Kuznetsov](https://github.com/kuznetsoffandrey),[Denis Dimitrov](https://github.com/denndimitrov), [Zein Shaheen](https://github.com/zeinsh)
 
-The description from it's GitHub page:
+The description from it's Github page:
 
 *Kandinsky 3.0 is an open-source text-to-image diffusion model built upon the Kandinsky2-x model family. In comparison to its predecessors, enhancements have been made to the text understanding and visual quality of the model, achieved by increasing the size of the text encoder and Diffusion U-Net models, respectively.*
 

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

@@ -1,107 +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.
--->
-
-# Kolors: Effective Training of Diffusion Model for Photorealistic Text-to-Image Synthesis
-
-![](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/kolors/kolors_header_collage.png)
-
-Kolors is a large-scale text-to-image generation model based on latent diffusion, developed by [the Kuaishou Kolors team](kwai-kolors@kuaishou.com). Trained on billions of text-image pairs, Kolors exhibits significant advantages over both open-source and closed-source models in visual quality, complex semantic accuracy, and text rendering for both Chinese and English characters. Furthermore, Kolors supports both Chinese and English inputs, demonstrating strong performance in understanding and generating Chinese-specific content. For more details, please refer to this [technical report](https://github.com/Kwai-Kolors/Kolors/blob/master/imgs/Kolors_paper.pdf).
-
-The abstract from the technical report is:
-
-*We present Kolors, a latent diffusion model for text-to-image synthesis, characterized by its profound understanding of both English and Chinese, as well as an impressive degree of photorealism. There are three key insights contributing to the development of Kolors. Firstly, unlike large language model T5 used in Imagen and Stable Diffusion 3, Kolors is built upon the General Language Model (GLM), which enhances its comprehension capabilities in both English and Chinese. Moreover, we employ a multimodal large language model to recaption the extensive training dataset for fine-grained text understanding. These strategies significantly improve Kolors’ ability to comprehend intricate semantics, particularly those involving multiple entities, and enable its advanced text rendering capabilities. Secondly, we divide the training of Kolors into two phases: the concept learning phase with broad knowledge and the quality improvement phase with specifically curated high-aesthetic data. Furthermore, we investigate the critical role of the noise schedule and introduce a novel schedule to optimize high-resolution image generation. These strategies collectively enhance the visual appeal of the generated high-resolution images. Lastly, we propose a category-balanced benchmark KolorsPrompts, which serves as a guide for the training and evaluation of Kolors. Consequently, even when employing the commonly used U-Net backbone, Kolors has demonstrated remarkable performance in human evaluations, surpassing the existing open-source models and achieving Midjourney-v6 level performance, especially in terms of visual appeal. We will release the code and weights of Kolors at <https://github.com/Kwai-Kolors/Kolors>, and hope that it will benefit future research and applications in the visual generation community.*
-
-## Usage Example
-
-```python
-import torch
-
-from diffusers import DPMSolverMultistepScheduler, KolorsPipeline
-
-pipe = KolorsPipeline.from_pretrained("Kwai-Kolors/Kolors-diffusers", torch_dtype=torch.float16, variant="fp16")
-pipe.to("cuda")
-pipe.scheduler = DPMSolverMultistepScheduler.from_config(pipe.scheduler.config, use_karras_sigmas=True)
-
-image = pipe(
-    prompt='一张瓢虫的照片，微距，变焦，高质量，电影，拿着一个牌子，写着"可图"',
-    negative_prompt="",
-    guidance_scale=6.5,
-    num_inference_steps=25,
-).images[0]
-
-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
-
-- all
-- __call__

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

@@ -1,77 +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. -->
-
-# 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

@@ -1,90 +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.
--->
-
-# Lumina-T2X
-![concepts](https://github.com/Alpha-VLLM/Lumina-T2X/assets/54879512/9f52eabb-07dc-4881-8257-6d8a5f2a0a5a)
-
-[Lumina-Next : Making Lumina-T2X Stronger and Faster with Next-DiT](https://github.com/Alpha-VLLM/Lumina-T2X/blob/main/assets/lumina-next.pdf) from Alpha-VLLM, OpenGVLab, Shanghai AI Laboratory.
-
-The abstract from the paper is:
-
-*Lumina-T2X is a nascent family of Flow-based Large Diffusion Transformers (Flag-DiT) that establishes a unified framework for transforming noise into various modalities, such as images and videos, conditioned on text instructions. Despite its promising capabilities, Lumina-T2X still encounters challenges including training instability, slow inference, and extrapolation artifacts. In this paper, we present Lumina-Next, an improved version of Lumina-T2X, showcasing stronger generation performance with increased training and inference efficiency. We begin with a comprehensive analysis of the Flag-DiT architecture and identify several suboptimal components, which we address by introducing the Next-DiT architecture with 3D RoPE and sandwich normalizations. To enable better resolution extrapolation, we thoroughly compare different context extrapolation methods applied to text-to-image generation with 3D RoPE, and propose Frequency- and Time-Aware Scaled RoPE tailored for diffusion transformers. Additionally, we introduce a sigmoid time discretization schedule to reduce sampling steps in solving the Flow ODE and the Context Drop method to merge redundant visual tokens for faster network evaluation, effectively boosting the overall sampling speed. Thanks to these improvements, Lumina-Next not only improves the quality and efficiency of basic text-to-image generation but also demonstrates superior resolution extrapolation capabilities and multilingual generation using decoder-based LLMs as the text encoder, all in a zero-shot manner. To further validate Lumina-Next as a versatile generative framework, we instantiate it on diverse tasks including visual recognition, multi-view, audio, music, and point cloud generation, showcasing strong performance across these domains. By releasing all codes and model weights at https://github.com/Alpha-VLLM/Lumina-T2X, we aim to advance the development of next-generation generative AI capable of universal modeling.*
-
-**Highlights**: Lumina-Next is a next-generation Diffusion Transformer that significantly enhances text-to-image generation, multilingual generation, and multitask performance by introducing the Next-DiT architecture, 3D RoPE, and frequency- and time-aware RoPE, among other improvements.
-
-Lumina-Next has the following components:
-* It improves sampling efficiency with fewer and faster Steps.
-* It uses a Next-DiT as a transformer backbone with Sandwichnorm 3D RoPE, and Grouped-Query Attention.
-* It uses a Frequency- and Time-Aware Scaled RoPE.
-
----
-
-[Lumina-T2X: Transforming Text into Any Modality, Resolution, and Duration via Flow-based Large Diffusion Transformers](https://arxiv.org/abs/2405.05945) from Alpha-VLLM, OpenGVLab, Shanghai AI Laboratory.
-
-The abstract from the paper is:
-
-*Sora unveils the potential of scaling Diffusion Transformer for generating photorealistic images and videos at arbitrary resolutions, aspect ratios, and durations, yet it still lacks sufficient implementation details. In this technical report, we introduce the Lumina-T2X family - a series of Flow-based Large Diffusion Transformers (Flag-DiT) equipped with zero-initialized attention, as a unified framework designed to transform noise into images, videos, multi-view 3D objects, and audio clips conditioned on text instructions. By tokenizing the latent spatial-temporal space and incorporating learnable placeholders such as [nextline] and [nextframe] tokens, Lumina-T2X seamlessly unifies the representations of different modalities across various spatial-temporal resolutions. This unified approach enables training within a single framework for different modalities and allows for flexible generation of multimodal data at any resolution, aspect ratio, and length during inference. Advanced techniques like RoPE, RMSNorm, and flow matching enhance the stability, flexibility, and scalability of Flag-DiT, enabling models of Lumina-T2X to scale up to 7 billion parameters and extend the context window to 128K tokens. This is particularly beneficial for creating ultra-high-definition images with our Lumina-T2I model and long 720p videos with our Lumina-T2V model. Remarkably, Lumina-T2I, powered by a 5-billion-parameter Flag-DiT, requires only 35% of the training computational costs of a 600-million-parameter naive DiT. Our further comprehensive analysis underscores Lumina-T2X's preliminary capability in resolution extrapolation, high-resolution editing, generating consistent 3D views, and synthesizing videos with seamless transitions. We expect that the open-sourcing of Lumina-T2X will further foster creativity, transparency, and diversity in the generative AI community.*
-
-
-You can find the original codebase at [Alpha-VLLM](https://github.com/Alpha-VLLM/Lumina-T2X) and all the available checkpoints at [Alpha-VLLM Lumina Family](https://huggingface.co/collections/Alpha-VLLM/lumina-family-66423205bedb81171fd0644b).
-
-**Highlights**: Lumina-T2X supports Any Modality, Resolution, and Duration.
-
-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.
-
-</Tip>
-
-### Inference (Text-to-Image)
-
-Use [`torch.compile`](https://huggingface.co/docs/diffusers/main/en/tutorials/fast_diffusion#torchcompile) to reduce the inference latency.
-
-First, load the pipeline:
-
-```python
-from diffusers import LuminaText2ImgPipeline
-import torch
-
-pipeline = LuminaText2ImgPipeline.from_pretrained(
-	"Alpha-VLLM/Lumina-Next-SFT-diffusers", torch_dtype=torch.bfloat16
-).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, mode="max-autotune", fullgraph=True)
-pipeline.vae.decode = torch.compile(pipeline.vae.decode, mode="max-autotune", fullgraph=True)
-
-image = pipeline(prompt="Upper body of a young woman in a Victorian-era outfit with brass goggles and leather straps. Background shows an industrial revolution cityscape with smoky skies and tall, metal structures").images[0]
-```
-
-## LuminaText2ImgPipeline
-
-[[autodoc]] LuminaText2ImgPipeline
-	- all
-	- __call__
-

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

@@ -71,7 +71,6 @@ 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

@@ -1,91 +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.
--->
-
-# Perturbed-Attention Guidance
-
-[Perturbed-Attention Guidance (PAG)](https://ku-cvlab.github.io/Perturbed-Attention-Guidance/) is a new diffusion sampling guidance that improves sample quality across both unconditional and conditional settings, achieving this without requiring further training or the integration of external modules.
-
-PAG was introduced in [Self-Rectifying Diffusion Sampling with Perturbed-Attention Guidance](https://huggingface.co/papers/2403.17377) by Donghoon Ahn, Hyoungwon Cho, Jaewon Min, Wooseok Jang, Jungwoo Kim, SeonHwa Kim, Hyun Hee Park, Kyong Hwan Jin and Seungryong Kim.
-
-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
-	- __call__
-
-## StableDiffusionControlNetPAGPipeline
-[[autodoc]] StableDiffusionControlNetPAGPipeline
-	- all
-	- __call__
-
-## StableDiffusionXLPAGPipeline
-[[autodoc]] StableDiffusionXLPAGPipeline
-	- all
-	- __call__
-
-## StableDiffusionXLPAGImg2ImgPipeline
-[[autodoc]] StableDiffusionXLPAGImg2ImgPipeline
-	- all
-	- __call__
-
-## StableDiffusionXLPAGInpaintPipeline
-[[autodoc]] StableDiffusionXLPAGInpaintPipeline
-	- all
-	- __call__
-
-## StableDiffusionXLControlNetPAGPipeline
-[[autodoc]] StableDiffusionXLControlNetPAGPipeline
-	- all
-	- __call__
-
-
-## StableDiffusion3PAGPipeline
-[[autodoc]] StableDiffusion3PAGPipeline
-	- all
-	- __call__
-
-
-## PixArtSigmaPAGPipeline
-[[autodoc]] PixArtSigmaPAGPipeline
-	- all
-	- __call__

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

@@ -37,12 +37,6 @@ Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers)
 
 </Tip>
 
-<Tip>
-
-You can further improve generation quality by passing the generated image from [`PixArtSigmaPipeline`] to the [SDXL refiner](../../using-diffusers/sdxl#base-to-refiner-model) model.
-
-</Tip>
-
 ## Inference with under 8GB GPU VRAM
 
 Run the [`PixArtSigmaPipeline`] with under 8GB GPU VRAM by loading the text encoder in 8-bit precision. Let's walk through a full-fledged example.

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

@@ -1,42 +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.
--->
-
-# 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-tool](https://github.com/Stability-AI/stable-audio-tool).
-
-## 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/pipelines/stable_diffusion/stable_diffusion_2.md

@@ -48,7 +48,7 @@ from diffusers import DiffusionPipeline, DPMSolverMultistepScheduler
 import torch
 
 repo_id = "stabilityai/stable-diffusion-2-base"
-pipe = DiffusionPipeline.from_pretrained(repo_id, torch_dtype=torch.float16, variant="fp16")
+pipe = DiffusionPipeline.from_pretrained(repo_id, torch_dtype=torch.float16, revision="fp16")
 
 pipe.scheduler = DPMSolverMultistepScheduler.from_config(pipe.scheduler.config)
 pipe = pipe.to("cuda")
@@ -72,7 +72,7 @@ init_image = load_image(img_url).resize((512, 512))
 mask_image = load_image(mask_url).resize((512, 512))
 
 repo_id = "stabilityai/stable-diffusion-2-inpainting"
-pipe = DiffusionPipeline.from_pretrained(repo_id, torch_dtype=torch.float16, variant="fp16")
+pipe = DiffusionPipeline.from_pretrained(repo_id, torch_dtype=torch.float16, revision="fp16")
 
 pipe.scheduler = DPMSolverMultistepScheduler.from_config(pipe.scheduler.config)
 pipe = pipe.to("cuda")

docs/source/en/api/pipelines/stable_diffusion/stable_diffusion_3.md

@@ -1,315 +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.
--->
-
-# Stable Diffusion 3
-
-Stable Diffusion 3 (SD3) was proposed in [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://arxiv.org/pdf/2403.03206.pdf) by Patrick Esser, Sumith Kulal, Andreas Blattmann, Rahim Entezari, Jonas Muller, Harry Saini, Yam Levi, Dominik Lorenz, Axel Sauer, Frederic Boesel, Dustin Podell, Tim Dockhorn, Zion English, Kyle Lacey, Alex Goodwin, Yannik Marek, and Robin Rombach.
-
-The abstract from the paper is:
-
-*Diffusion models create data from noise by inverting the forward paths of data towards noise and have emerged as a powerful generative modeling technique for high-dimensional, perceptual data such as images and videos. Rectified flow is a recent generative model formulation that connects data and noise in a straight line. Despite its better theoretical properties and conceptual simplicity, it is not yet decisively established as standard practice. In this work, we improve existing noise sampling techniques for training rectified flow models by biasing them towards perceptually relevant scales. Through a large-scale study, we demonstrate the superior performance of this approach compared to established diffusion formulations for high-resolution text-to-image synthesis. Additionally, we present a novel transformer-based architecture for text-to-image generation that uses separate weights for the two modalities and enables a bidirectional flow of information between image and text tokens, improving text comprehension typography, and human preference ratings. We demonstrate that this architecture follows predictable scaling trends and correlates lower validation loss to improved text-to-image synthesis as measured by various metrics and human evaluations.*
-
-
-## Usage Example
-
-_As the model is gated, before using it with diffusers you first need to go to the [Stable Diffusion 3 Medium Hugging Face page](https://huggingface.co/stabilityai/stable-diffusion-3-medium-diffusers), fill in the form and accept the gate. Once you are in, you need to login so that your system knows you’ve accepted the gate._
-
-Use the command below to log in:
-
-```bash
-huggingface-cli login
-```
-
-<Tip>
-
-The SD3 pipeline uses three text encoders to generate an image. Model offloading is necessary in order for it to run on most commodity hardware. Please use the `torch.float16` data type for additional memory savings.
-
-</Tip>
-
-```python
-import torch
-from diffusers import StableDiffusion3Pipeline
-
-pipe = StableDiffusion3Pipeline.from_pretrained("stabilityai/stable-diffusion-3-medium-diffusers", torch_dtype=torch.float16)
-pipe.to("cuda")
-
-image = pipe(
-    prompt="a photo of a cat holding a sign that says hello world",
-    negative_prompt="",
-    num_inference_steps=28,
-    height=1024,
-    width=1024,
-    guidance_scale=7.0,
-).images[0]
-
-image.save("sd3_hello_world.png")
-```
-
-## Memory Optimisations for SD3
-
-SD3 uses three text encoders, one if which is the very large T5-XXL model. This makes it challenging to run the model on GPUs with less than 24GB of VRAM, even when using `fp16` precision. The following section outlines a few memory optimizations in Diffusers that make it easier to run SD3 on low resource hardware.
-
-### Running Inference with Model Offloading
-
-The most basic memory optimization available in Diffusers allows you to offload the components of the model to CPU during inference in order to save memory, while seeing a slight increase in inference latency. Model offloading will only move a model component onto the GPU when it needs to be executed, while keeping the remaining components on the CPU.
-
-```python
-import torch
-from diffusers import StableDiffusion3Pipeline
-
-pipe = StableDiffusion3Pipeline.from_pretrained("stabilityai/stable-diffusion-3-medium-diffusers", torch_dtype=torch.float16)
-pipe.enable_model_cpu_offload()
-
-image = pipe(
-    prompt="a photo of a cat holding a sign that says hello world",
-    negative_prompt="",
-    num_inference_steps=28,
-    height=1024,
-    width=1024,
-    guidance_scale=7.0,
-).images[0]
-
-image.save("sd3_hello_world.png")
-```
-
-### Dropping the T5 Text Encoder during Inference
-
-Removing the memory-intensive 4.7B parameter T5-XXL text encoder during inference can significantly decrease the memory requirements for SD3 with only a slight loss in performance.
-
-```python
-import torch
-from diffusers import StableDiffusion3Pipeline
-
-pipe = StableDiffusion3Pipeline.from_pretrained(
-    "stabilityai/stable-diffusion-3-medium-diffusers",
-    text_encoder_3=None,
-    tokenizer_3=None,
-    torch_dtype=torch.float16
-)
-pipe.to("cuda")
-
-image = pipe(
-    prompt="a photo of a cat holding a sign that says hello world",
-    negative_prompt="",
-    num_inference_steps=28,
-    height=1024,
-    width=1024,
-    guidance_scale=7.0,
-).images[0]
-
-image.save("sd3_hello_world-no-T5.png")
-```
-
-### Using a Quantized Version of the T5 Text Encoder
-
-We can leverage the `bitsandbytes` library to load and quantize the T5-XXL text encoder to 8-bit precision. This allows you to keep using all three text encoders while only slightly impacting performance.
-
-First install the `bitsandbytes` library.
-
-```shell
-pip install bitsandbytes
-```
-
-Then load the T5-XXL model using the `BitsAndBytesConfig`.
-
-```python
-import torch
-from diffusers import StableDiffusion3Pipeline
-from transformers import T5EncoderModel, BitsAndBytesConfig
-
-quantization_config = BitsAndBytesConfig(load_in_8bit=True)
-
-model_id = "stabilityai/stable-diffusion-3-medium-diffusers"
-text_encoder = T5EncoderModel.from_pretrained(
-    model_id,
-    subfolder="text_encoder_3",
-    quantization_config=quantization_config,
-)
-pipe = StableDiffusion3Pipeline.from_pretrained(
-    model_id,
-    text_encoder_3=text_encoder,
-    device_map="balanced",
-    torch_dtype=torch.float16
-)
-
-image = pipe(
-    prompt="a photo of a cat holding a sign that says hello world",
-    negative_prompt="",
-    num_inference_steps=28,
-    height=1024,
-    width=1024,
-    guidance_scale=7.0,
-).images[0]
-
-image.save("sd3_hello_world-8bit-T5.png")
-```
-
-You can find the end-to-end script [here](https://gist.github.com/sayakpaul/82acb5976509851f2db1a83456e504f1).
-
-## Performance Optimizations for SD3
-
-### Using Torch Compile to Speed Up Inference
-
-Using compiled components in the SD3 pipeline can speed up inference by as much as 4X. The following code snippet demonstrates how to compile the Transformer and VAE components of the SD3 pipeline.
-
-```python
-import torch
-from diffusers import StableDiffusion3Pipeline
-
-torch.set_float32_matmul_precision("high")
-
-torch._inductor.config.conv_1x1_as_mm = True
-torch._inductor.config.coordinate_descent_tuning = True
-torch._inductor.config.epilogue_fusion = False
-torch._inductor.config.coordinate_descent_check_all_directions = True
-
-pipe = StableDiffusion3Pipeline.from_pretrained(
-    "stabilityai/stable-diffusion-3-medium-diffusers",
-    torch_dtype=torch.float16
-).to("cuda")
-pipe.set_progress_bar_config(disable=True)
-
-pipe.transformer.to(memory_format=torch.channels_last)
-pipe.vae.to(memory_format=torch.channels_last)
-
-pipe.transformer = torch.compile(pipe.transformer, mode="max-autotune", fullgraph=True)
-pipe.vae.decode = torch.compile(pipe.vae.decode, mode="max-autotune", fullgraph=True)
-
-# Warm Up
-prompt = "a photo of a cat holding a sign that says hello world"
-for _ in range(3):
-    _ = pipe(prompt=prompt, generator=torch.manual_seed(1))
-
-# Run Inference
-image = pipe(prompt=prompt, generator=torch.manual_seed(1)).images[0]
-image.save("sd3_hello_world.png")
-```
-
-Check out the full script [here](https://gist.github.com/sayakpaul/508d89d7aad4f454900813da5d42ca97).
-
-## Using Long Prompts with the T5 Text Encoder
-
-By default, the T5 Text Encoder prompt uses a maximum sequence length of `256`. This can be adjusted by setting the `max_sequence_length` to accept fewer or more tokens. Keep in mind that longer sequences require additional resources and result in longer generation times, such as during batch inference.
-
-```python
-prompt = "A whimsical and creative image depicting a hybrid creature that is a mix of a waffle and a hippopotamus, basking in a river of melted butter amidst a breakfast-themed landscape. It features the distinctive, bulky body shape of a hippo. However, instead of the usual grey skin, the creature’s body resembles a golden-brown, crispy waffle fresh off the griddle. The skin is textured with the familiar grid pattern of a waffle, each square filled with a glistening sheen of syrup. The environment combines the natural habitat of a hippo with elements of a breakfast table setting, a river of warm, melted butter, with oversized utensils or plates peeking out from the lush, pancake-like foliage in the background, a towering pepper mill standing in for a tree.  As the sun rises in this fantastical world, it casts a warm, buttery glow over the scene. The creature, content in its butter river, lets out a yawn. Nearby, a flock of birds take flight"
-
-image = pipe(
-    prompt=prompt,
-    negative_prompt="",
-    num_inference_steps=28,
-    guidance_scale=4.5,
-    max_sequence_length=512,
-).images[0]
-```
-
-### Sending a different prompt to the T5 Text Encoder
-
-You can send a different prompt to the CLIP Text Encoders and the T5 Text Encoder to prevent the prompt from being truncated by the CLIP Text Encoders and to improve generation.
-
-<Tip>
-
-The prompt with the CLIP Text Encoders is still truncated to the 77 token limit.
-
-</Tip>
-
-```python
-prompt = "A whimsical and creative image depicting a hybrid creature that is a mix of a waffle and a hippopotamus, basking in a river of melted butter amidst a breakfast-themed landscape. A river of warm, melted butter, pancake-like foliage in the background, a towering pepper mill standing in for a tree."
-
-prompt_3 = "A whimsical and creative image depicting a hybrid creature that is a mix of a waffle and a hippopotamus, basking in a river of melted butter amidst a breakfast-themed landscape. It features the distinctive, bulky body shape of a hippo. However, instead of the usual grey skin, the creature’s body resembles a golden-brown, crispy waffle fresh off the griddle. The skin is textured with the familiar grid pattern of a waffle, each square filled with a glistening sheen of syrup. The environment combines the natural habitat of a hippo with elements of a breakfast table setting, a river of warm, melted butter, with oversized utensils or plates peeking out from the lush, pancake-like foliage in the background, a towering pepper mill standing in for a tree.  As the sun rises in this fantastical world, it casts a warm, buttery glow over the scene. The creature, content in its butter river, lets out a yawn. Nearby, a flock of birds take flight"
-
-image = pipe(
-    prompt=prompt,
-    prompt_3=prompt_3,
-    negative_prompt="",
-    num_inference_steps=28,
-    guidance_scale=4.5,
-    max_sequence_length=512,
-).images[0]
-```
-
-## Tiny AutoEncoder for Stable Diffusion 3
-
-Tiny AutoEncoder for Stable Diffusion (TAESD3) is a tiny distilled version of Stable Diffusion 3's VAE by [Ollin Boer Bohan](https://github.com/madebyollin/taesd) that can decode [`StableDiffusion3Pipeline`] latents almost instantly.
-
-To use with Stable Diffusion 3:
-
-```python
-import torch
-from diffusers import StableDiffusion3Pipeline, AutoencoderTiny
-
-pipe = StableDiffusion3Pipeline.from_pretrained(
-    "stabilityai/stable-diffusion-3-medium-diffusers", torch_dtype=torch.float16
-)
-pipe.vae = AutoencoderTiny.from_pretrained("madebyollin/taesd3", torch_dtype=torch.float16)
-pipe = pipe.to("cuda")
-
-prompt = "slice of delicious New York-style berry cheesecake"
-image = pipe(prompt, num_inference_steps=25).images[0]
-image.save("cheesecake.png")
-```
-
-## Loading the original checkpoints via `from_single_file`
-
-The `SD3Transformer2DModel` and `StableDiffusion3Pipeline` classes support loading the original checkpoints via the `from_single_file` method. This method allows you to load the original checkpoint files that were used to train the models.
-
-## Loading the original checkpoints for the `SD3Transformer2DModel`
-
-```python
-from diffusers import SD3Transformer2DModel
-
-model = SD3Transformer2DModel.from_single_file("https://huggingface.co/stabilityai/stable-diffusion-3-medium/blob/main/sd3_medium.safetensors")
-```
-
-## Loading the single checkpoint for the `StableDiffusion3Pipeline`
-
-### Loading the single file checkpoint without T5
-
-```python
-import torch
-from diffusers import StableDiffusion3Pipeline
-
-pipe = StableDiffusion3Pipeline.from_single_file(
-    "https://huggingface.co/stabilityai/stable-diffusion-3-medium/blob/main/sd3_medium_incl_clips.safetensors",
-    torch_dtype=torch.float16,
-    text_encoder_3=None
-)
-pipe.enable_model_cpu_offload()
-
-image = pipe("a picture of a cat holding a sign that says hello world").images[0]
-image.save('sd3-single-file.png')
-```
-
-### Loading the single file checkpoint with T5
-
-> [!TIP]
-> The following example loads a checkpoint stored in a 8-bit floating point format which requires PyTorch 2.3 or later.
-
-```python
-import torch
-from diffusers import StableDiffusion3Pipeline
-
-pipe = StableDiffusion3Pipeline.from_single_file(
-    "https://huggingface.co/stabilityai/stable-diffusion-3-medium/blob/main/sd3_medium_incl_clips_t5xxlfp8.safetensors",
-    torch_dtype=torch.float16,
-)
-pipe.enable_model_cpu_offload()
-
-image = pipe("a picture of a cat holding a sign that says hello world").images[0]
-image.save('sd3-single-file-t5-fp8.png')
-```
-
-## StableDiffusion3Pipeline
-
-[[autodoc]] StableDiffusion3Pipeline
-	- all
-	- __call__

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

@@ -1,24 +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.
--->
-
-# 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/api/schedulers/flow_match_euler_discrete.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.
--->
-
-# FlowMatchEulerDiscreteScheduler
-
-`FlowMatchEulerDiscreteScheduler` is based on the flow-matching sampling introduced in [Stable Diffusion 3](https://arxiv.org/abs/2403.03206).
-
-## FlowMatchEulerDiscreteScheduler
-[[autodoc]] FlowMatchEulerDiscreteScheduler

docs/source/en/api/schedulers/flow_match_heun_discrete.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.
--->
-
-# FlowMatchHeunDiscreteScheduler
-
-`FlowMatchHeunDiscreteScheduler` is based on the flow-matching sampling introduced in [EDM](https://arxiv.org/abs/2403.03206).
-
-## FlowMatchHeunDiscreteScheduler
-[[autodoc]] FlowMatchHeunDiscreteScheduler

docs/source/en/community_projects.md

@@ -1,78 +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.
--->
-
-# 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/conceptual/contribution.md

@@ -22,13 +22,14 @@ We enormously value feedback from the community, so please do not be afraid to s
 
 ## Overview
 
-You can contribute in many ways ranging from answering questions on issues and discussions to adding new diffusion models to the core library.
+You can contribute in many ways ranging from answering questions on issues to adding new diffusion models to
+the core library.
 
 In the following, we give an overview of different ways to contribute, ranked by difficulty in ascending order. All of them are valuable to the community.
 
 * 1. Asking and answering questions on [the Diffusers discussion forum](https://discuss.huggingface.co/c/discussion-related-to-httpsgithubcomhuggingfacediffusers) or on [Discord](https://discord.gg/G7tWnz98XR).
-* 2. Opening new issues on [the GitHub Issues tab](https://github.com/huggingface/diffusers/issues/new/choose) or new discussions on [the GitHub Discussions tab](https://github.com/huggingface/diffusers/discussions/new/choose).
-* 3. Answering issues on [the GitHub Issues tab](https://github.com/huggingface/diffusers/issues) or discussions on [the GitHub Discussions tab](https://github.com/huggingface/diffusers/discussions).
+* 2. Opening new issues on [the GitHub Issues tab](https://github.com/huggingface/diffusers/issues/new/choose).
+* 3. Answering issues on [the GitHub Issues tab](https://github.com/huggingface/diffusers/issues).
 * 4. Fix a simple issue, marked by the "Good first issue" label, see [here](https://github.com/huggingface/diffusers/issues?q=is%3Aopen+is%3Aissue+label%3A%22good+first+issue%22).
 * 5. Contribute to the [documentation](https://github.com/huggingface/diffusers/tree/main/docs/source).
 * 6. Contribute a [Community Pipeline](https://github.com/huggingface/diffusers/issues?q=is%3Aopen+is%3Aissue+label%3Acommunity-examples).
@@ -62,7 +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-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.
+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.
 
 **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.
@@ -98,7 +99,7 @@ This means in more detail:
 - Format your code.
 - Do not include any external libraries except for Diffusers depending on them.
 - **Always** provide all necessary information about your environment; for this, you can run: `diffusers-cli env` in your shell and copy-paste the displayed information to the issue.
-- Explain the issue. If the reader doesn't know what the issue is and why it is an issue, (s)he cannot solve it.
+- Explain the issue. If the reader doesn't know what the issue is and why it is an issue, she cannot solve it.
 - **Always** make sure the reader can reproduce your issue with as little effort as possible. If your code snippet cannot be run because of missing libraries or undefined variables, the reader cannot help you. Make sure your reproducible code snippet is as minimal as possible and can be copy-pasted into a simple Python shell.
 - If in order to reproduce your issue a model and/or dataset is required, make sure the reader has access to that model or dataset. You can always upload your model or dataset to the [Hub](https://huggingface.co) to make it easily downloadable. Try to keep your model and dataset as small as possible, to make the reproduction of your issue as effortless as possible.
 
@@ -287,7 +288,7 @@ The official training examples are maintained by the Diffusers' core maintainers
 This is because of the same reasons put forward in [6. Contribute a community pipeline](#6-contribute-a-community-pipeline) for official pipelines vs. community pipelines: It is not feasible for the core maintainers to maintain all possible training methods for diffusion models.
 If the Diffusers core maintainers and the community consider a certain training paradigm to be too experimental or not popular enough, the corresponding training code should be put in the `research_projects` folder and maintained by the author.
 
-Both official training and research examples consist of a directory that contains one or more training scripts, a `requirements.txt` file, and a `README.md` file. In order for the user to make use of the
+Both official training and research examples consist of a directory that contains one or more training scripts, a requirements.txt file, and a README.md file. In order for the user to make use of the
 training examples, it is required to clone the repository:
 
 ```bash
@@ -297,8 +298,7 @@ git clone https://github.com/huggingface/diffusers
 as well as to install all additional dependencies required for training:
 
 ```bash
-cd diffusers
-pip install -r examples/<your-example-folder>/requirements.txt
+pip install -r /examples/<your-example-folder>/requirements.txt
 ```
 
 Therefore when adding an example, the `requirements.txt` file shall define all pip dependencies required for your training example so that once all those are installed, the user can run the example's training script. See, for example, the [DreamBooth `requirements.txt` file](https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/requirements.txt).
@@ -316,7 +316,7 @@ Once an example script works, please make sure to add a comprehensive `README.md
 - A link to some training results (logs, models, etc.) that show what the user can expect as shown [here](https://api.wandb.ai/report/patrickvonplaten/xm6cd5q5).
 - If you are adding a non-official/research training example, **please don't forget** to add a sentence that you are maintaining this training example which includes your git handle as shown [here](https://github.com/huggingface/diffusers/tree/main/examples/research_projects/intel_opts#diffusers-examples-with-intel-optimizations).
 
-If you are contributing to the official training examples, please also make sure to add a test to its folder such as [examples/dreambooth/test_dreambooth.py](https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/test_dreambooth.py). This is not necessary for non-official training examples.
+If you are contributing to the official training examples, please also make sure to add a test to [examples/test_examples.py](https://github.com/huggingface/diffusers/blob/main/examples/test_examples.py). This is not necessary for non-official training examples.
 
 ### 8. Fixing a "Good second issue"
 
@@ -418,7 +418,7 @@ You will need basic `git` proficiency to be able to contribute to
 manual. Type `git --help` in a shell and enjoy. If you prefer books, [Pro
 Git](https://git-scm.com/book/en/v2) is a very good reference.
 
-Follow these steps to start contributing ([supported Python versions](https://github.com/huggingface/diffusers/blob/83bc6c94eaeb6f7704a2a428931cf2d9ad973ae9/setup.py#L270)):
+Follow these steps to start contributing ([supported Python versions](https://github.com/huggingface/diffusers/blob/main/setup.py#L244)):
 
 1. Fork the [repository](https://github.com/huggingface/diffusers) by
 clicking on the 'Fork' button on the repository's page. This creates a copy of the code

docs/source/en/conceptual/philosophy.md

@@ -81,7 +81,7 @@ Models are designed as configurable toolboxes that are natural extensions of [Py
 
 The following design principles are followed:
 - Models correspond to **a type of model architecture**. *E.g.* the [`UNet2DConditionModel`] class is used for all UNet variations that expect 2D image inputs and are conditioned on some context.
-- All models can be found in [`src/diffusers/models`](https://github.com/huggingface/diffusers/tree/main/src/diffusers/models) and every model architecture shall be defined in its file, e.g. [`unets/unet_2d_condition.py`](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/unets/unet_2d_condition.py), [`transformers/transformer_2d.py`](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/transformers/transformer_2d.py), etc...
+- All models can be found in [`src/diffusers/models`](https://github.com/huggingface/diffusers/tree/main/src/diffusers/models) and every model architecture shall be defined in its file, e.g. [`unet_2d_condition.py`](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/unet_2d_condition.py), [`transformer_2d.py`](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/transformer_2d.py), etc...
 - Models **do not** follow the single-file policy and should make use of smaller model building blocks, such as [`attention.py`](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention.py), [`resnet.py`](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/resnet.py), [`embeddings.py`](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/embeddings.py), etc... **Note**: This is in stark contrast to Transformers' modeling files and shows that models do not really follow the single-file policy.
 - Models intend to expose complexity, just like PyTorch's `Module` class, and give clear error messages.
 - Models all inherit from `ModelMixin` and `ConfigMixin`.
@@ -90,7 +90,7 @@ The following design principles are followed:
 - To integrate new model checkpoints whose general architecture can be classified as an architecture that already exists in Diffusers, the existing model architecture shall be adapted to make it work with the new checkpoint. One should only create a new file if the model architecture is fundamentally different.
 - Models should be designed to be easily extendable to future changes. This can be achieved by limiting public function arguments, configuration arguments, and "foreseeing" future changes, *e.g.* it is usually better to add `string` "...type" arguments that can easily be extended to new future types instead of boolean `is_..._type` arguments. Only the minimum amount of changes shall be made to existing architectures to make a new model checkpoint work.
 - The model design is a difficult trade-off between keeping code readable and concise and supporting many model checkpoints. For most parts of the modeling code, classes shall be adapted for new model checkpoints, while there are some exceptions where it is preferred to add new classes to make sure the code is kept concise and
-readable long-term, such as [UNet blocks](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/unets/unet_2d_blocks.py) and [Attention processors](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_processor.py).
+readable long-term, such as [UNet blocks](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/unet_2d_blocks.py) and [Attention processors](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_processor.py).
 
 ### Schedulers
 
@@ -102,7 +102,7 @@ The following design principles are followed:
 - One scheduler Python file corresponds to one scheduler algorithm (as might be defined in a paper).
 - If schedulers share similar functionalities, we can make use of the `#Copied from` mechanism.
 - Schedulers all inherit from `SchedulerMixin` and `ConfigMixin`.
-- Schedulers can be easily swapped out with the [`ConfigMixin.from_config`](https://huggingface.co/docs/diffusers/main/en/api/configuration#diffusers.ConfigMixin.from_config) method as explained in detail [here](../using-diffusers/schedulers).
+- Schedulers can be easily swapped out with the [`ConfigMixin.from_config`](https://huggingface.co/docs/diffusers/main/en/api/configuration#diffusers.ConfigMixin.from_config) method as explained in detail [here](../using-diffusers/schedulers.md).
 - Every scheduler has to have a `set_num_inference_steps`, and a `step` function. `set_num_inference_steps(...)` has to be called before every denoising process, *i.e.* before `step(...)` is called.
 - Every scheduler exposes the timesteps to be "looped over" via a `timesteps` attribute, which is an array of timesteps the model will be called upon.
 - The `step(...)` function takes a predicted model output and the "current" sample (x_t) and returns the "previous", slightly more denoised sample (x_t-1).

docs/source/en/training/controlnet.md

@@ -349,7 +349,7 @@ control_image = load_image("./conditioning_image_1.png")
 prompt = "pale golden rod circle with old lace background"
 
 generator = torch.manual_seed(0)
-image = pipeline(prompt, num_inference_steps=20, generator=generator, image=control_image).images[0]
+image = pipe(prompt, num_inference_steps=20, generator=generator, image=control_image).images[0]
 image.save("./output.png")
 ```
 

docs/source/en/training/distributed_inference.md

@@ -52,6 +52,76 @@ To learn more, take a look at the [Distributed Inference with 🤗 Accelerate](h
 
 </Tip>
 
+### Device placement
+
+> [!WARNING]
+> This feature is experimental and its APIs might change in the future. 
+
+With Accelerate, you can use the `device_map` to determine how to distribute the models of a pipeline across multiple devices. This is useful in situations where you have more than one GPU.
+
+For example, if you have two 8GB GPUs, then using [`~DiffusionPipeline.enable_model_cpu_offload`] may not work so well because:
+
+* it only works on a single GPU
+* a single model might not fit on a single GPU ([`~DiffusionPipeline.enable_sequential_cpu_offload`] might work but it will be extremely slow and it is also limited to a single GPU)
+
+To make use of both GPUs, you can use the "balanced" device placement strategy which splits the models across all available GPUs.
+
+> [!WARNING]
+> Only the "balanced" strategy is supported at the moment, and we plan to support additional mapping strategies in the future.
+
+```diff
+from diffusers import DiffusionPipeline
+import torch
+
+pipeline = DiffusionPipeline.from_pretrained(
+-    "runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16, use_safetensors=True,
++    "runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16, use_safetensors=True, device_map="balanced"
+)
+image = pipeline("a dog").images[0]
+image
+```
+
+You can also pass a dictionary to enforce the maximum GPU memory that can be used on each device:
+
+```diff
+from diffusers import DiffusionPipeline
+import torch
+
+max_memory = {0:"1GB", 1:"1GB"}
+pipeline = DiffusionPipeline.from_pretrained(
+    "runwayml/stable-diffusion-v1-5",
+    torch_dtype=torch.float16, 
+    use_safetensors=True, 
+    device_map="balanced",
++   max_memory=max_memory
+)
+image = pipeline("a dog").images[0]
+image
+```
+
+If a device is not present in `max_memory`, then it will be completely ignored and will not participate in the device placement. 
+
+By default, Diffusers uses the maximum memory of all devices. If the models don't fit on the GPUs, they are offloaded to the CPU. If the CPU doesn't have enough memory, then you might see an error. In that case, you could defer to using [`~DiffusionPipeline.enable_sequential_cpu_offload`] and [`~DiffusionPipeline.enable_model_cpu_offload`].
+
+Call [`~DiffusionPipeline.reset_device_map`] to reset the `device_map` of a pipeline. This is also necessary if you want to use methods like `to()`, [`~DiffusionPipeline.enable_sequential_cpu_offload`], and [`~DiffusionPipeline.enable_model_cpu_offload`] on a pipeline that was device-mapped.
+
+```py
+pipeline.reset_device_map()
+```
+
+Once a pipeline has been device-mapped, you can also access its device map via `hf_device_map`:
+
+```py
+print(pipeline.hf_device_map)
+```
+
+An example device map would look like so:
+
+
+```bash
+{'unet': 1, 'vae': 1, 'safety_checker': 0, 'text_encoder': 0}
+```
+
 ## PyTorch Distributed
 
 PyTorch supports [`DistributedDataParallel`](https://pytorch.org/docs/stable/generated/torch.nn.parallel.DistributedDataParallel.html) which enables data parallelism.
@@ -106,6 +176,3 @@ Once you've completed the inference script, use the `--nproc_per_node` argument
 ```bash
 torchrun run_distributed.py --nproc_per_node=2
 ```
-
-> [!TIP]
-> You can use `device_map` within a [`DiffusionPipeline`] to distribute its model-level components on multiple devices. Refer to the [Device placement](../tutorials/inference_with_big_models#device-placement) guide to learn more.

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 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 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):

docs/source/en/training/text2image.md

@@ -181,7 +181,7 @@ accelerate launch --mixed_precision="fp16"  train_text_to_image.py \
   --max_train_steps=15000 \
   --learning_rate=1e-05 \
   --max_grad_norm=1 \
-  --enable_xformers_memory_efficient_attention \
+  --enable_xformers_memory_efficient_attention
   --lr_scheduler="constant" --lr_warmup_steps=0 \
   --output_dir="sd-naruto-model" \
   --push_to_hub

docs/source/en/tutorials/basic_training.md

@@ -340,7 +340,6 @@ Now you can wrap all these components together in a training loop with 🤗 Acce
 ...                 loss = F.mse_loss(noise_pred, noise)
 ...                 accelerator.backward(loss)
 
-...                 if accelerator.sync_gradients:
 ...                 accelerator.clip_grad_norm_(model.parameters(), 1.0)
 ...                 optimizer.step()
 ...                 lr_scheduler.step()

docs/source/en/tutorials/fast_diffusion.md

@@ -34,10 +34,13 @@ Install [PyTorch nightly](https://pytorch.org/) to benefit from the latest and f
 pip3 install --pre torch --index-url https://download.pytorch.org/whl/nightly/cu121
 ```
 
-> [!TIP]
-> 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).
+<Tip>
 
+The results reported below are from a 80GB 400W A100 with its clock rate set to the maximum. <br>
+
+If you're interested in the full benchmarking code, take a look at [huggingface/diffusion-fast](https://github.com/huggingface/diffusion-fast).
+
+</Tip>
 
 ## Baseline
 
@@ -167,9 +170,6 @@ Using SDPA attention and compiling both the UNet and VAE cuts the latency from 3
     <img src="https://huggingface.co/datasets/sayakpaul/sample-datasets/resolve/main/progressive-acceleration-sdxl/SDXL%2C_Batch_Size%3A_1%2C_Steps%3A_30_3.png" width=500>
 </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.
-
 ### Prevent graph breaks
 
 Specifying `fullgraph=True` ensures there are no graph breaks in the underlying model to take full advantage of `torch.compile` without any performance degradation. For the UNet and VAE, this means changing how you access the return variables.

docs/source/en/tutorials/inference_with_big_models.md

@@ -1,139 +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.
--->
-
-# Working with big models
-
-A modern diffusion model, like [Stable Diffusion XL (SDXL)](../using-diffusers/sdxl), is not just a single model, but a collection of multiple models. SDXL has four different model-level components:
-
-* A variational autoencoder (VAE)
-* Two text encoders
-* A UNet for denoising
-
-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.
-
-> [!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.
-
-For example, let's save a sharded checkpoint for the [SDXL UNet](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/tree/main/unet):
-
-```python
-from diffusers import UNet2DConditionModel
-
-unet = UNet2DConditionModel.from_pretrained(
-    "stabilityai/stable-diffusion-xl-base-1.0", subfolder="unet"
-)
-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
-import torch
-
-unet = UNet2DConditionModel.from_pretrained(
-    "sayakpaul/sdxl-unet-sharded", torch_dtype=torch.float16
-)
-pipeline = StableDiffusionXLPipeline.from_pretrained(
-    "stabilityai/stable-diffusion-xl-base-1.0", unet=unet, torch_dtype=torch.float16
-).to("cuda")
-
-image = pipeline("a cute dog running on the grass", num_inference_steps=30).images[0]
-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:
-
-```diff
-- pipeline.to("cuda")
-+ pipeline.enable_model_cpu_offload()
-```
-
-In general, we recommend sharding when a checkpoint is more than 5GB (in fp32).
-
-## Device placement
-
-On distributed setups, you can run inference across multiple GPUs with Accelerate.
-
-> [!WARNING]
-> This feature is experimental and its APIs might change in the future.
-
-With Accelerate, you can use the `device_map` to determine how to distribute the models of a pipeline across multiple devices. This is useful in situations where you have more than one GPU.
-
-For example, if you have two 8GB GPUs, then using [`~DiffusionPipeline.enable_model_cpu_offload`] may not work so well because:
-
-* it only works on a single GPU
-* a single model might not fit on a single GPU ([`~DiffusionPipeline.enable_sequential_cpu_offload`] might work but it will be extremely slow and it is also limited to a single GPU)
-
-To make use of both GPUs, you can use the "balanced" device placement strategy which splits the models across all available GPUs.
-
-> [!WARNING]
-> Only the "balanced" strategy is supported at the moment, and we plan to support additional mapping strategies in the future.
-
-```diff
-from diffusers import DiffusionPipeline
-import torch
-
-pipeline = DiffusionPipeline.from_pretrained(
--    "runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16, use_safetensors=True,
-+    "runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16, use_safetensors=True, device_map="balanced"
-)
-image = pipeline("a dog").images[0]
-image
-```
-
-You can also pass a dictionary to enforce the maximum GPU memory that can be used on each device:
-
-```diff
-from diffusers import DiffusionPipeline
-import torch
-
-max_memory = {0:"1GB", 1:"1GB"}
-pipeline = DiffusionPipeline.from_pretrained(
-    "runwayml/stable-diffusion-v1-5",
-    torch_dtype=torch.float16,
-    use_safetensors=True,
-    device_map="balanced",
-+   max_memory=max_memory
-)
-image = pipeline("a dog").images[0]
-image
-```
-
-If a device is not present in `max_memory`, then it will be completely ignored and will not participate in the device placement.
-
-By default, Diffusers uses the maximum memory of all devices. If the models don't fit on the GPUs, they are offloaded to the CPU. If the CPU doesn't have enough memory, then you might see an error. In that case, you could defer to using [`~DiffusionPipeline.enable_sequential_cpu_offload`] and [`~DiffusionPipeline.enable_model_cpu_offload`].
-
-Call [`~DiffusionPipeline.reset_device_map`] to reset the `device_map` of a pipeline. This is also necessary if you want to use methods like `to()`, [`~DiffusionPipeline.enable_sequential_cpu_offload`], and [`~DiffusionPipeline.enable_model_cpu_offload`] on a pipeline that was device-mapped.
-
-```py
-pipeline.reset_device_map()
-```
-
-Once a pipeline has been device-mapped, you can also access its device map via `hf_device_map`:
-
-```py
-print(pipeline.hf_device_map)
-```
-
-An example device map would look like so:
-
-
-```bash
-{'unet': 1, 'vae': 1, 'safety_checker': 0, 'text_encoder': 0}
-```

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 lets 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 let's 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.StableDiffusionLoraLoaderMixin.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.LoraLoaderMixin.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.StableDiffusionLoraLoaderMixin.get_list_adapters`]:
+You can also get the active adapters of each pipeline component with [`~diffusers.loaders.LoraLoaderMixin.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 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 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 its 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 it's 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 CLIPImageProcessor
+from transformers import CLIPFeatureExtractor
 
-feature_extractor = CLIPImageProcessor.from_pretrained(pipe_id, subfolder="feature_extractor")
+feature_extractor = CLIPFeatureExtractor.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.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.
+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.
 
 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.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.
+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.
 
 > [!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.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.
+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.
 
 ```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.StableDiffusionLoraLoaderMixin.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.LoraLoaderMixin.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.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.
+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.
 
 ```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.StableDiffusionLoraLoaderMixin.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.LoraLoaderMixin.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.StableDiffusionLoraLoaderMixin.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.LoraLoaderMixin.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 DPTImageProcessor, DPTForDepthEstimation
+from transformers import DPTFeatureExtractor, 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 = DPTImageProcessor.from_pretrained("Intel/dpt-hybrid-midas")
+feature_extractor = DPTFeatureExtractor.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.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:
+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:
 
 ```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.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 [`~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 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.StableDiffusionLoraLoaderMixin.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.LoraLoaderMixin.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.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 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 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.
+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.
 ```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.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.
+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.
 
 </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.StableDiffusionLoraLoaderMixin.load_lora_weights`] method, and specify the filename in the `weight_name` parameter:
+Load the LoRA checkpoint with the [`~loaders.LoraLoaderMixin.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.StableDiffusionLoraLoaderMixin.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.LoraLoaderMixin.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.StableDiffusionLoraLoaderMixin.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.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.
 
-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.StableDiffusionLoraLoaderMixin.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]() 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.
 
 ```py
 from diffusers import DiffusionPipeline
@@ -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.StableDiffusionLoraLoaderMixin.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.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.
 
-You can use PEFT to easily fuse/unfuse multiple adapters directly into the model weights (both UNet and text encoder) using the [`~loaders.StableDiffusionLoraLoaderMixin.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.LoraLoaderMixin.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.StableDiffusionLoraLoaderMixin.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.StableDiffusionLoraLoaderMixin.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.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.
 
 ```py
 pipeline.fuse_lora(adapter_names=["ikea", "feng"], lora_scale=1.0)
 ```
 
-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.
+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.
 
 ```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.StableDiffusionLoraLoaderMixin.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.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.
 
 ```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.StableDiffusionLoraLoaderMixin.load_lora_weights`] method.
+LoRAs are loaded into a base model with the [`~loaders.LoraLoaderMixin.load_lora_weights`] method.
 
 ```py
 from diffusers import StableDiffusionXLPipeline
@@ -418,7 +418,7 @@ my_local_checkpoint_path = hf_hub_download(
 
 my_local_config_path = snapshot_download(
     repo_id="segmind/SSD-1B",
-    allow_patterns=["*.json", "**/*.json", "*.txt", "**/*.txt"]
+    allowed_patterns=["*.json", "**/*.json", "*.txt", "**/*.txt"]
 )
 
 pipeline = StableDiffusionXLPipeline.from_single_file(my_local_checkpoint_path, config=my_local_config_path, local_files_only=True)
@@ -438,7 +438,7 @@ my_local_checkpoint_path = hf_hub_download(
 
 my_local_config_path = snapshot_download(
     repo_id="segmind/SSD-1B",
-    allow_patterns=["*.json", "**/*.json", "*.txt", "**/*.txt"]
+    allowed_patterns=["*.json", "**/*.json", "*.txt", "**/*.txt"]
     local_dir="my_local_config"
 )
 
@@ -468,10 +468,11 @@ print("My local checkpoint: ", my_local_checkpoint_path)
 
 my_local_config_path = snapshot_download(
     repo_id="segmind/SSD-1B",
-    allow_patterns=["*.json", "**/*.json", "*.txt", "**/*.txt"]
+    allowed_patterns=["*.json", "**/*.json", "*.txt", "**/*.txt"]
     local_dir_use_symlinks=False,
 )
 print("My local config: ", my_local_config_path)
+
 ```
 
 Then you can pass the local paths to the `pretrained_model_link_or_path` and `config` parameters.

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

@@ -1,351 +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.
--->
-
-# Perturbed-Attention Guidance
-
-[Perturbed-Attention Guidance (PAG)](https://ku-cvlab.github.io/Perturbed-Attention-Guidance/) is a new diffusion sampling guidance that improves sample quality across both unconditional and conditional settings, achieving this without requiring further training or the integration of external modules. PAG is designed to progressively enhance the structure of synthesized samples throughout the denoising process by considering the self-attention mechanisms' ability to capture structural information. It involves generating intermediate samples with degraded structure by substituting selected self-attention maps in diffusion U-Net with an identity matrix, and guiding the denoising process away from these degraded samples.
-
-This guide will show you how to use PAG for various tasks and use cases.
-
-
-## General tasks
-
-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 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">
-
-```py
-from diffusers import AutoPipelineForText2Image
-from diffusers.utils import load_image
-import torch
-
-pipeline = AutoPipelineForText2Image.from_pretrained(
-    "stabilityai/stable-diffusion-xl-base-1.0",
-    enable_pag=True,
-    pag_applied_layers=["mid"],
-    torch_dtype=torch.float16
-)
-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).
-
-```py
-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)
-```
-
-To generate an image, you will also need to pass a `pag_scale`. When `pag_scale` increases, images gain more semantically coherent structures and exhibit fewer artifacts. However overly large guidance scale can lead to smoother textures and slight saturation in the images, similarly to CFG. `pag_scale=3.0` is used in the official demo and works well in most of the use cases, but feel free to experiment and select the appropriate value according to your needs! PAG is disabled when `pag_scale=0`.
-
-```py
-prompt = "an insect robot preparing a delicious meal, anime style"
-
-for pag_scale in [0.0, 3.0]:
-    generator = torch.Generator(device="cpu").manual_seed(0)
-    images = pipeline(
-        prompt=prompt,
-        num_inference_steps=25,
-        guidance_scale=7.0,
-        generator=generator,
-        pag_scale=pag_scale,
-    ).images
-```
-
-<div class="flex flex-row gap-4">
-  <div class="flex-1">
-    <img class="rounded-xl" src="https://huggingface.co/datasets/YiYiXu/testing-images/resolve/main/pag_0.0_cfg_7.0_mid.png"/>
-    <figcaption class="mt-2 text-center text-sm text-gray-500">generated image without PAG</figcaption>
-  </div>
-  <div class="flex-1">
-    <img class="rounded-xl" src="https://huggingface.co/datasets/YiYiXu/testing-images/resolve/main/pag_3.0_cfg_7.0_mid.png"/>
-    <figcaption class="mt-2 text-center text-sm text-gray-500">generated image with PAG</figcaption>
-  </div>
-</div>
-
-</hfoption>
-<hfoption id="Image-to-image">
-
-You can use PAG with image-to-image pipelines.
-
-```py
-from diffusers import AutoPipelineForImage2Image
-from diffusers.utils import load_image
-import torch
-
-pipeline = AutoPipelineForImage2Image.from_pretrained(
-    "stabilityai/stable-diffusion-xl-base-1.0",
-    enable_pag=True,
-    pag_applied_layers=["mid"],
-    torch_dtype=torch.float16
-)
-pipeline.enable_model_cpu_offload()
-```
-
-If you already have a image-to-image pipeline and would like enable PAG on it, you can run this
-
-```py
-pipeline_t2i = AutoPipelineForImage2Image.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.float16)
-pipeline = AutoPipelineForImage2Image.from_pipe(pipeline_t2i, enable_pag=True)
-```
-
-It is also very easy to directly switch from a text-to-image pipeline to PAG enabled image-to-image pipeline
-
-```py
-pipeline_pag = AutoPipelineForText2Image.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.float16)
-pipeline = AutoPipelineForImage2Image.from_pipe(pipeline_t2i, enable_pag=True)
-```
-
-If you have a PAG enabled text-to-image pipeline, you can directly switch to a image-to-image pipeline with PAG still enabled
-
-```py
-pipeline_pag = AutoPipelineForText2Image.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", enable_pag=True, torch_dtype=torch.float16)
-pipeline = AutoPipelineForImage2Image.from_pipe(pipeline_t2i)
-```
-
-Now let's generate an image!
-
-```py
-pag_scales =  4.0
-guidance_scales = 7.0
-
-url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/sdxl-text2img.png"
-init_image = load_image(url)
-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,
-    pag_scale=pag_scale,
-    generator=generator).images[0]
-```
-
-</hfoption>
-<hfoption id="Inpainting">
-
-```py
-from diffusers import AutoPipelineForInpainting
-from diffusers.utils import load_image
-import torch
-
-pipeline = AutoPipelineForInpainting.from_pretrained(
-    "stabilityai/stable-diffusion-xl-base-1.0",
-    enable_pag=True,
-    torch_dtype=torch.float16
-)
-pipeline.enable_model_cpu_offload()
-```
-
-You can enable PAG on an exisiting inpainting pipeline like this
-
-```py
-pipeline_inpaint = AutoPipelineForInpaiting.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.float16)
-pipeline = AutoPipelineForInpaiting.from_pipe(pipeline_inpaint, enable_pag=True)
-```
-
-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!
-
-```py
-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 = load_image(img_url).convert("RGB")
-mask_image = load_image(mask_url).convert("RGB")
-
-prompt = "A majestic tiger sitting on a bench"
-
-pag_scales =  3.0
-guidance_scales = 7.5
-
-generator = torch.Generator(device="cpu").manual_seed(1)
-images = pipeline(
-    prompt=prompt,
-    image=init_image,
-    mask_image=mask_image,
-    strength=0.8,
-    num_inference_steps=50,
-    guidance_scale=guidance_scale,
-    generator=generator,
-    pag_scale=pag_scale,
-).images
-images[0]
-```
-</hfoption>
-</hfoptions>
-
-## PAG with ControlNet
-
-To use PAG with ControlNet, first create a `controlnet`. Then, pass the `controlnet` and other PAG arguments to the `from_pretrained` method of the AutoPipeline for the specified task.
-
-```py
-from diffusers import AutoPipelineForText2Image, ControlNetModel
-import torch
-
-controlnet = ControlNetModel.from_pretrained(
-    "diffusers/controlnet-canny-sdxl-1.0", torch_dtype=torch.float16
-)
-
-pipeline = AutoPipelineForText2Image.from_pretrained(
-    "stabilityai/stable-diffusion-xl-base-1.0",
-    controlnet=controlnet,
-    enable_pag=True,
-    pag_applied_layers="mid",
-    torch_dtype=torch.float16
-)
-pipeline.enable_model_cpu_offload()
-```
-
-<Tip>
-
-If you already have a controlnet pipeline and want to enable PAG, you can use the `from_pipe` API: `AutoPipelineForText2Image.from_pipe(pipeline_controlnet, enable_pag=True)`
-
-</Tip>
-
-You can use the pipeline in the same way you normally use ControlNet pipelines, with the added option to specify a `pag_scale` parameter. Note that PAG works well for unconditional generation. In this example, we will generate an image without a prompt.
-
-```py
-from diffusers.utils import load_image
-canny_image = load_image(
-    "https://huggingface.co/datasets/YiYiXu/testing-images/resolve/main/pag_control_input.png"
-)
-
-for pag_scale in [0.0, 3.0]:
-    generator = torch.Generator(device="cpu").manual_seed(1)
-    images = pipeline(
-        prompt="",
-        controlnet_conditioning_scale=controlnet_conditioning_scale,
-        image=canny_image,
-        num_inference_steps=50,
-        guidance_scale=0,
-        generator=generator,
-        pag_scale=pag_scale,
-    ).images
-    images[0]
-```
-
-<div class="flex flex-row gap-4">
-  <div class="flex-1">
-    <img class="rounded-xl" src="https://huggingface.co/datasets/YiYiXu/testing-images/resolve/main/pag_0.0_controlnet.png"/>
-    <figcaption class="mt-2 text-center text-sm text-gray-500">generated image without PAG</figcaption>
-  </div>
-  <div class="flex-1">
-    <img class="rounded-xl" src="https://huggingface.co/datasets/YiYiXu/testing-images/resolve/main/pag_3.0_controlnet.png"/>
-    <figcaption class="mt-2 text-center text-sm text-gray-500">generated image with PAG</figcaption>
-  </div>
-</div>
-
-## 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.
-
-```py
-from diffusers import AutoPipelineForText2Image
-from diffusers.utils import load_image
-from transformers import CLIPVisionModelWithProjection
-import torch
-
-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,
-    enable_pag=True,
-    torch_dtype=torch.float16
-).to("cuda")
-
-pipeline.load_ip_adapter("h94/IP-Adapter", subfolder="sdxl_models", weight_name="ip-adapter-plus_sdxl_vit-h.bin")
-
-pag_scales = 5.0
-ip_adapter_scales = 0.8
-
-image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/ip_adapter_diner.png")
-
-pipeline.set_ip_adapter_scale(ip_adapter_scale)
-generator = torch.Generator(device="cpu").manual_seed(0)
-images = pipeline(
-    prompt="a polar bear sitting in a chair drinking a milkshake",
-    ip_adapter_image=image,
-    negative_prompt="deformed, ugly, wrong proportion, low res, bad anatomy, worst quality, low quality",
-    num_inference_steps=25,
-    guidance_scale=3.0,
-    generator=generator,
-    pag_scale=pag_scale,
-).images
-images[0]
-
-```
-
-PAG reduces artifacts and improves the overall compposition.
-
-<div class="flex flex-row gap-4">
-  <div class="flex-1">
-    <img class="rounded-xl" src="https://huggingface.co/datasets/YiYiXu/testing-images/resolve/main/pag_0.0_ipa_0.8.png"/>
-    <figcaption class="mt-2 text-center text-sm text-gray-500">generated image without PAG</figcaption>
-  </div>
-  <div class="flex-1">
-    <img class="rounded-xl" src="https://huggingface.co/datasets/YiYiXu/testing-images/resolve/main/pag_5.0_ipa_0.8.png"/>
-    <figcaption class="mt-2 text-center text-sm text-gray-500">generated image with PAG</figcaption>
-  </div>
-</div>
-
-
-## Configure parameters
-
-### pag_applied_layers
-
-The `pag_applied_layers` argument allows you to specify which layers PAG is applied to. By default, it applies only to the mid blocks. Changing this setting will significantly impact the output. You can use the `set_pag_applied_layers` method to adjust the PAG layers after the pipeline is created, helping you find the optimal layers for your model.
-
-As an example, here is the images generated with `pag_layers = ["down.block_2"]` and `pag_layers = ["down.block_2", "up.block_1.attentions_0"]`
-
-```py
-prompt = "an insect robot preparing a delicious meal, anime style"
-pipeline.set_pag_applied_layers(pag_layers)
-generator = torch.Generator(device="cpu").manual_seed(0)
-images = pipeline(
-    prompt=prompt,
-    num_inference_steps=25,
-    guidance_scale=guidance_scale,
-    generator=generator,
-    pag_scale=pag_scale,
-).images
-images[0]
-```
-
-<div class="flex flex-row gap-4">
-  <div class="flex-1">
-    <img class="rounded-xl" src="https://huggingface.co/datasets/YiYiXu/testing-images/resolve/main/pag_3.0_cfg_7.0_down2_up1a0.png"/>
-    <figcaption class="mt-2 text-center text-sm text-gray-500">down.block_2 + up.block1.attentions_0</figcaption>
-  </div>
-  <div class="flex-1">
-    <img class="rounded-xl" src="https://huggingface.co/datasets/YiYiXu/testing-images/resolve/main/pag_3.0_cfg_7.0_down2.png"/>
-    <figcaption class="mt-2 text-center text-sm text-gray-500">down.block_2</figcaption>
-  </div>
-</div>

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

@@ -186,7 +186,7 @@ scheduler, scheduler_state = FlaxDPMSolverMultistepScheduler.from_pretrained(
 pipeline, params = FlaxStableDiffusionPipeline.from_pretrained(
     "runwayml/stable-diffusion-v1-5",
     scheduler=scheduler,
-    variant="bf16",
+    revision="bf16",
     dtype=jax.numpy.bfloat16,
 )
 params["scheduler"] = scheduler_state

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

@@ -285,12 +285,6 @@ refiner = DiffusionPipeline.from_pretrained(
 ).to("cuda")
 ```
 
-<Tip warning={true}>
-
-You can use SDXL refiner with a different base model. For example, you can use the [Hunyuan-DiT](../../api/pipelines/hunyuandit) or [PixArt-Sigma](../../api/pipelines/pixart_sigma) pipelines to generate images with better prompt adherence. Once you have generated an image, you can pass it to the SDXL refiner model to enhance final generation quality.
-
-</Tip>
-
 Generate an image from the base model, and set the model output to **latent** space:
 
 ```py

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

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

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

@@ -63,7 +63,7 @@ Flax is a functional framework, so models are stateless and parameters are store
 dtype = jnp.bfloat16
 pipeline, params = FlaxStableDiffusionPipeline.from_pretrained(
     "CompVis/stable-diffusion-v1-4",
-    variant="bf16",
+    revision="bf16",
     dtype=dtype,
 )
 ```

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

@@ -21,7 +21,6 @@ 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

@@ -1,109 +1,74 @@
 - 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 # tutorials/autopipeline
-    title: (번역중) AutoPipeline
+  - local: in_translation
+    title: AutoPipeline
   - local: tutorials/basic_training
     title: Diffusion 모델 학습하기
-  - 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
+  title: Tutorials
 - sections:
+  - sections:
+    - local: using-diffusers/loading_overview
+      title: 개요
     - local: using-diffusers/loading
-    title: 파이프라인 불러오기
-  - local: using-diffusers/custom_pipeline_overview
-    title: 커뮤니티 파이프라인과 컴포넌트 불러오기
+      title: 파이프라인, 모델, 스케줄러 불러오기
     - local: using-diffusers/schedulers
-    title: 스케줄러와 모델 불러오기
+      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: 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
+      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
+      title: Text-to-image 생성
     - local: using-diffusers/img2img
-    title: Image-to-image
+      title: Text-guided image-to-image
     - local: using-diffusers/inpaint
-    title: 인페인팅
-  - local: in_translation # using-diffusers/text-img2vid
-    title: (번역중) Text 또는 image-to-video
+      title: Text-guided 이미지 인페인팅
     - 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
+      title: Text-guided depth-to-image
     - 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
+    - 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
@@ -111,83 +76,50 @@
       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: LoRA
+      title: Low-Rank Adaptation of Large Language Models (LoRA)
+    - local: training/controlnet
+      title: ControlNet
+    - local: training/instructpix2pix
+      title: InstructPix2Pix 학습
     - local: training/custom_diffusion
       title: Custom Diffusion
-    - 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
+    title: Training
+  title: Diffusers 사용하기
 - sections:
+  - local: optimization/opt_overview
+    title: 개요
   - local: optimization/fp16
-    title: 추론 스피드업
-  - local: in_translation # optimization/memory
-    title: (번역중) 메모리 사용량 줄이기
+    title: 메모리와 속도
   - local: optimization/torch2.0
-    title: PyTorch 2.0
+    title: Torch2.0 지원
   - local: optimization/xformers
     title: xFormers
-  - local: optimization/tome
-    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)
+    title: MPS
   - local: optimization/habana
     title: Habana Gaudi
-    title: 최적화된 하드웨어
-  title: 추론 가속화와 메모리 줄이기
+  - local: optimization/tome
+    title: Token Merging
+  title: 최적화/특수 하드웨어
 - sections:
-  - local: conceptual/philosophy
-    title: 철학
   - local: using-diffusers/controlling_generation
     title: 제어된 생성
-  - local: conceptual/contribution
-    title: 어떻게 기여하나요?
-  - local: conceptual/ethical_guidelines
-    title: Diffusers의 윤리적 가이드라인
-  - local: conceptual/evaluation
+  - local: in_translation
     title: Diffusion Models 평가하기
   title: 개념 가이드
 - sections:

docs/source/ko/conceptual/contribution.md

@@ -1,512 +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.
--->
-
-# Diffusers에 기여하는 방법 🧨
-
-오픈 소스 커뮤니티에서의 기여를 환영합니다! 누구나 참여할 수 있으며, 코드뿐만 아니라 질문에 답변하거나 문서를 개선하는 등 모든 유형의 참여가 가치 있고 감사히 여겨집니다. 질문에 답변하고 다른 사람들을 도와주며 소통하고 문서를 개선하는 것은 모두 커뮤니티에게 큰 도움이 됩니다. 따라서 관심이 있다면 두려워하지 말고 참여해보세요!
-
-누구나 우리의 공개 Discord 채널에서 👋 인사하며 시작할 수 있도록 장려합니다. 우리는 diffusion 모델의 최신 동향을 논의하고 질문을 하며 개인 프로젝트를 자랑하고 기여에 대해 서로 도와주거나 그냥 어울리기 위해 모이는 곳입니다☕. <a href="https://Discord.gg/G7tWnz98XR"><img alt="Join us on Discord" src="https://img.shields.io/discord/823813159592001537?color=5865F2&logo=discord&logoColor=white"></a>
-
-어떤 방식으로든 기여하려는 경우, 우리는 개방적이고 환영하며 친근한 커뮤니티의 일부가 되기 위해 노력하고 있습니다. 우리의 [행동 강령](https://github.com/huggingface/diffusers/blob/main/CODE_OF_CONDUCT.md)을 읽고 상호 작용 중에 이를 존중하도록 주의해주시기 바랍니다. 또한 프로젝트를 안내하는 [윤리 지침](https://huggingface.co/docs/diffusers/conceptual/ethical_guidelines)에 익숙해지고 동일한 투명성과 책임성의 원칙을 준수해주시기를 부탁드립니다.
-
-우리는 커뮤니티로부터의 피드백을 매우 중요하게 생각하므로, 라이브러리를 개선하는 데 도움이 될 가치 있는 피드백이 있다고 생각되면 망설이지 말고 의견을 제시해주세요 - 모든 메시지, 댓글, 이슈, 풀 리퀘스트(PR)는 읽히고 고려됩니다.
-
-## 개요
-
-이슈에 있는 질문에 답변하는 것에서부터 코어 라이브러리에 새로운 diffusion 모델을 추가하는 것까지 다양한 방법으로 기여를 할 수 있습니다.
-
-이어지는 부분에서 우리는 다양한 방법의 기여에 대한 개요를 난이도에 따라 오름차순으로 정리하였습니다. 모든 기여는 커뮤니티에게 가치가 있습니다.
-
-1. [Diffusers 토론 포럼](https://discuss.huggingface.co/c/discussion-related-to-httpsgithubcomhuggingfacediffusers)이나 [Discord](https://discord.gg/G7tWnz98XR)에서 질문에 대답하거나 질문을 할 수 있습니다.
-2. [GitHub Issues 탭](https://github.com/huggingface/diffusers/issues/new/choose)에서 새로운 이슈를 열 수 있습니다.
-3. [GitHub Issues 탭](https://github.com/huggingface/diffusers/issues)에서 이슈에 대답할 수 있습니다.
-4. "Good first issue" 라벨이 지정된 간단한 이슈를 수정할 수 있습니다. [여기](https://github.com/huggingface/diffusers/issues?q=is%3Aopen+is%3Aissue+label%3A%22good+first+issue%22)를 참조하세요.
-5. [문서](https://github.com/huggingface/diffusers/tree/main/docs/source)에 기여할 수 있습니다.
-6. [Community Pipeline](https://github.com/huggingface/diffusers/issues?q=is%3Aopen+is%3Aissue+label%3Acommunity-examples)에 기여할 수 있습니다.
-7. [예제](https://github.com/huggingface/diffusers/tree/main/examples)에 기여할 수 있습니다.
-8. "Good second issue" 라벨이 지정된 어려운 이슈를 수정할 수 있습니다. [여기](https://github.com/huggingface/diffusers/issues?q=is%3Aopen+is%3Aissue+label%3A%22Good+second+issue%22)를 참조하세요.
-9. 새로운 파이프라인, 모델 또는 스케줄러를 추가할 수 있습니다. ["새로운 파이프라인/모델"](https://github.com/huggingface/diffusers/issues?q=is%3Aopen+is%3Aissue+label%3A%22New+pipeline%2Fmodel%22) 및 ["새로운 스케줄러"](https://github.com/huggingface/diffusers/issues?q=is%3Aopen+is%3Aissue+label%3A%22New+scheduler%22) 이슈를 참조하세요. 이 기여에 대해서는 [디자인 철학](https://github.com/huggingface/diffusers/blob/main/PHILOSOPHY.md)을 확인해주세요.
-
-앞서 말한 대로, **모든 기여는 커뮤니티에게 가치가 있습니다**. 이어지는 부분에서 각 기여에 대해 조금 더 자세히 설명하겠습니다.
-
-4부터 9까지의 모든 기여에는 PR을 열어야 합니다. [PR을 열기](#how-to-open-a-pr)에서 자세히 설명되어 있습니다.
-
-### 1. Diffusers 토론 포럼이나 Diffusers Discord에서 질문하고 답변하기
-
-Diffusers 라이브러리와 관련된 모든 질문이나 의견은 [토론 포럼](https://discuss.huggingface.co/c/discussion-related-to-httpsgithubcomhuggingfacediffusers/63)이나 [Discord](https://discord.gg/G7tWnz98XR)에서 할 수 있습니다. 이러한 질문과 의견에는 다음과 같은 내용이 포함됩니다(하지만 이에 국한되지는 않습니다):
-- 지식을 공유하기 위해서 훈련 또는 추론 실험에 대한 결과 보고
-- 개인 프로젝트 소개
-- 비공식 훈련 예제에 대한 질문
-- 프로젝트 제안
-- 일반적인 피드백
-- 논문 요약
-- Diffusers 라이브러리를 기반으로 하는 개인 프로젝트에 대한 도움 요청
-- 일반적인 질문
-- Diffusion 모델에 대한 윤리적 질문
-- ...
-
-포럼이나 Discord에서 질문을 하면 커뮤니티가 지식을 공개적으로 공유하도록 장려되며, 미래에 동일한 질문을 가진 초보자에게도 도움이 될 수 있습니다. 따라서 궁금한 질문은 언제든지 하시기 바랍니다.
-또한, 이러한 질문에 답변하는 것은 커뮤니티에게 매우 큰 도움이 됩니다. 왜냐하면 이렇게 하면 모두가 학습할 수 있는 공개적인 지식을 문서화하기 때문입니다.
-
-**주의**하십시오. 질문이나 답변에 투자하는 노력이 많을수록 공개적으로 문서화된 지식의 품질이 높아집니다. 마찬가지로, 잘 정의되고 잘 답변된 질문은 모두에게 접근 가능한 고품질 지식 데이터베이스를 만들어줍니다. 반면에 잘못된 질문이나 답변은 공개 지식 데이터베이스의 전반적인 품질을 낮출 수 있습니다.
-간단히 말해서, 고품질의 질문이나 답변은 *명확하고 간결하며 관련성이 있으며 이해하기 쉽고 접근 가능하며 잘 형식화되어 있어야* 합니다. 자세한 내용은 [좋은 이슈 작성 방법](#how-to-write-a-good-issue) 섹션을 참조하십시오.
-
-**채널에 대한 참고사항**:
-[*포럼*](https://discuss.huggingface.co/c/discussion-related-to-httpsgithubcomhuggingfacediffusers/63)은 구글과 같은 검색 엔진에서 더 잘 색인화됩니다. 게시물은 인기에 따라 순위가 매겨지며, 시간순으로 정렬되지 않습니다. 따라서 이전에 게시한 질문과 답변을 쉽게 찾을 수 있습니다.
-또한, 포럼에 게시된 질문과 답변은 쉽게 링크할 수 있습니다.
-반면 *Discord*는 채팅 형식으로 되어 있어 빠른 대화를 유도합니다.
-질문에 대한 답변을 빠르게 받을 수는 있겠지만, 시간이 지나면 질문이 더 이상 보이지 않습니다. 또한, Discord에서 이전에 게시된 정보를 찾는 것은 훨씬 어렵습니다. 따라서 포럼을 사용하여 고품질의 질문과 답변을 하여 커뮤니티를 위한 오래 지속되는 지식을 만들기를 권장합니다. Discord에서의 토론이 매우 흥미로운 답변과 결론을 이끌어내는 경우, 해당 정보를 포럼에 게시하여 미래 독자들에게 더 쉽게 액세스할 수 있도록 권장합니다.
-
-### 2. GitHub 이슈 탭에서 새로운 이슈 열기
-
-🧨 Diffusers 라이브러리는 사용자들이 마주치는 문제를 알려주는 덕분에 견고하고 신뢰할 수 있습니다. 따라서 이슈를 보고해주셔서 감사합니다.
-
-기억해주세요, GitHub 이슈는 Diffusers 라이브러리와 직접적으로 관련된 기술적인 질문, 버그 리포트, 기능 요청 또는 라이브러리 디자인에 대한 피드백에 사용됩니다.
-
-간단히 말해서, Diffusers 라이브러리의 **코드와 관련되지 않은** 모든 것(문서 포함)은 GitHub가 아닌 [포럼](https://discuss.huggingface.co/c/discussion-related-to-httpsgithubcomhuggingfacediffusers/63)이나 [Discord](https://discord.gg/G7tWnz98XR)에서 질문해야 합니다.
-
-**새로운 이슈를 열 때 다음 가이드라인을 고려해주세요**:
-- 이미 같은 이슈가 있는지 검색했는지 확인해주세요(GitHub의 이슈 탭에서 검색 기능을 사용하세요).
-- 다른(관련된) 이슈에 새로운 이슈를 보고하지 말아주세요. 다른 이슈와 관련이 높다면, 새로운 이슈를 열고 관련 이슈에 링크를 걸어주세요.
-- 이슈를 영어로 작성해주세요. 영어에 익숙하지 않다면, [DeepL](https://www.deepl.com/translator)과 같은 뛰어난 무료 온라인 번역 서비스를 사용하여 모국어에서 영어로 번역해주세요.
-- 이슈가 최신 Diffusers 버전으로 업데이트하면 해결될 수 있는지 확인해주세요. 이슈를 게시하기 전에 `python -c "import diffusers; print(diffusers.__version__)"` 명령을 실행하여 현재 사용 중인 Diffusers 버전이 최신 버전과 일치하거나 더 높은지 확인해주세요.
-- 새로운 이슈를 열 때 투자하는 노력이 많을수록 답변의 품질이 높아지고 Diffusers 이슈 전체의 품질도 향상됩니다.
-
-#### 2.1 재현가능하고 최소한인 버그 리포트
-
-새로운 이슈는 일반적으로 다음과 같은 내용을 포함합니다.
-
-버그 보고서는 항상 재현 가능한 코드 조각을 포함하고 가능한 한 최소한이어야 하며 간결해야 합니다.
-자세히 말하면:
-- 버그를 가능한 한 좁혀야 합니다. **전체 코드 파일을 그냥 던지지 마세요**.
-- 코드의 서식을 지정해야 합니다.
-- Diffusers가 의존하는 외부 라이브러리를 제외한 다른 외부 라이브러리는 포함하지 마십시오.
-- **반드시** 환경에 대한 모든 필요한 정보를 제공해야 합니다. 이를 위해 쉘에서 `diffusers-cli env`를 실행하고 표시된 정보를 이슈에 복사하여 붙여넣을 수 있습니다.
-- 이슈를 설명해야 합니다. 독자가 문제가 무엇이며 왜 문제인지 모르면 해결할 수 없습니다.
-- **항상** 독자가 가능한 한 적은 노력으로 문제를 재현할 수 있도록 해야 합니다. 코드 조각이 라이브러리가 없거나 정의되지 않은 변수 때문에 실행되지 않는 경우 독자가 도움을 줄 수 없습니다. 재현 가능한 코드 조각이 가능한 한 최소화되고 간단한 Python 셸에 복사하여 붙여넣을 수 있도록 해야 합니다.
-- 문제를 재현하기 위해 모델과/또는 데이터셋이 필요한 경우 독자가 해당 모델이나 데이터셋에 접근할 수 있도록 해야 합니다. 모델이나 데이터셋을 [Hub](https://huggingface.co)에 업로드하여 쉽게 다운로드할 수 있도록 할 수 있습니다. 문제 재현을 가능한 한 쉽게하기 위해 모델과 데이터셋을 가능한 한 작게 유지하려고 노력하세요.
-
-자세한 내용은 [좋은 이슈 작성 방법](#how-to-write-a-good-issue) 섹션을 참조하세요.
-
-버그 보고서를 열려면 [여기](https://github.com/huggingface/diffusers/issues/new?assignees=&labels=bug&projects=&template=bug-report.yml)를 클릭하세요.
-
-
-#### 2.2. 기능 요청
-
-세계적인 기능 요청은 다음 사항을 다룹니다:
-
-1. 먼저 동기부여:
-* 라이브러리와 관련된 문제/불만이 있는가요? 그렇다면 왜 그런지 설명해주세요. 문제를 보여주는 코드 조각을 제공하는 것이 가장 좋습니다.
-* 프로젝트에 필요한 기능인가요? 우리는 그에 대해 듣고 싶습니다!
-* 커뮤니티에 도움이 될 수 있는 것을 작업했고 그것에 대해 생각하고 있는가요? 멋지네요! 어떤 문제를 해결했는지 알려주세요.
-2. 기능을 *상세히 설명하는* 문단을 작성해주세요;
-3. 미래 사용을 보여주는 **코드 조각**을 제공해주세요;
-4. 이것이 논문과 관련된 경우 링크를 첨부해주세요;
-5. 도움이 될 수 있는 추가 정보(그림, 스크린샷 등)를 첨부해주세요.
-
-기능 요청은 [여기](https://github.com/huggingface/diffusers/issues/new?assignees=&labels=&template=feature_request.md&title=)에서 열 수 있습니다.
-
-#### 2.3 피드백
-
-라이브러리 디자인과 그것이 왜 좋은지 또는 나쁜지에 대한 이유에 대한 피드백은 핵심 메인테이너가 사용자 친화적인 라이브러리를 만드는 데 엄청난 도움이 됩니다. 현재 디자인 철학을 이해하려면 [여기](https://huggingface.co/docs/diffusers/conceptual/philosophy)를 참조해 주세요. 특정 디자인 선택이 현재 디자인 철학과 맞지 않는다고 생각되면, 그 이유와 어떻게 변경되어야 하는지 설명해 주세요. 반대로 특정 디자인 선택이 디자인 철학을 너무 따르기 때문에 사용 사례를 제한한다고 생각되면, 그 이유와 어떻게 변경되어야 하는지 설명해 주세요. 특정 디자인 선택이 매우 유용하다고 생각되면, 미래의 디자인 결정에 큰 도움이 되므로 이에 대한 의견을 남겨 주세요.
-
-피드백에 관한 이슈는 [여기](https://github.com/huggingface/diffusers/issues/new?assignees=&labels=&template=feedback.md&title=)에서 열 수 있습니다.
-
-#### 2.4 기술적인 질문
-
-기술적인 질문은 주로 라이브러리의 특정 코드가 왜 특정 방식으로 작성되었는지 또는 코드의 특정 부분이 무엇을 하는지에 대한 질문입니다. 질문하신 코드 부분에 대한 링크를 제공하고 해당 코드 부분이 이해하기 어려운 이유에 대한 자세한 설명을 해주시기 바랍니다.
-
-기술적인 질문에 관한 이슈를 [여기](https://github.com/huggingface/diffusers/issues/new?assignees=&labels=bug&template=bug-report.yml)에서 열 수 있습니다.
-
-#### 2.5 새로운 모델, 스케줄러 또는 파이프라인 추가 제안
-
-만약 diffusion 모델 커뮤니티에서 Diffusers 라이브러리에 추가하고 싶은 새로운 모델, 파이프라인 또는 스케줄러가 있다면, 다음 정보를 제공해주세요:
-
-* Diffusion 파이프라인, 모델 또는 스케줄러에 대한 간단한 설명과 논문 또는 공개된 버전의 링크
-* 해당 모델의 오픈 소스 구현에 대한 링크
-* 모델 가중치가 있는 경우, 가중치의 링크
-
-모델에 직접 기여하고자 하는 경우, 최선의 안내를 위해 우리에게 알려주세요. 또한, 가능하다면 구성 요소(모델, 스케줄러, 파이프라인 등)의 원래 저자를 GitHub 핸들로 태그하는 것을 잊지 마세요.
-
-모델/파이프라인/스케줄러에 대한 요청을 [여기](https://github.com/huggingface/diffusers/issues/new?assignees=&labels=New+model%2Fpipeline%2Fscheduler&template=new-model-addition.yml)에서 열 수 있습니다.
-
-### 3. GitHub 이슈 탭에서 문제에 대한 답변하기
-
-GitHub에서 이슈에 대한 답변을 하기 위해서는 Diffusers에 대한 기술적인 지식이 필요할 수 있지만, 정확한 답변이 아니더라도 모두가 시도해기를 권장합니다. 이슈에 대한 고품질 답변을 제공하기 위한 몇 가지 팁:
-- 가능한 한 간결하고 최소한으로 유지합니다.
-- 주제에 집중합니다. 이슈에 대한 답변은 해당 이슈에 관련된 내용에만 집중해야 합니다.
-- 코드, 논문 또는 다른 소스를 제공하여 답변을 증명하거나 지지합니다.
-- 코드로 답변합니다. 간단한 코드 조각이 이슈에 대한 답변이거나 이슈를 해결하는 방법을 보여준다면, 완전히 재현 가능한 코드 조각을 제공해주세요.
-
-또한, 많은 이슈들은 단순히 주제와 무관하거나 다른 이슈의 중복이거나 관련이 없는 경우가 많습니다. 이러한 이슈들에 대한 답변을 제공하고, 이슈 작성자에게 더 정확한 정보를 제공하거나, 중복된 이슈에 대한 링크를 제공하거나, [포럼](https://discuss.huggingface.co/c/discussion-related-to-httpsgithubcomhuggingfacediffusers/63) 이나 [Discord](https://discord.gg/G7tWnz98XR)로 리디렉션하는 것은 메인테이너에게 큰 도움이 됩니다.
-
-이슈가 올바른 버그 보고서이고 소스 코드에서 수정이 필요하다고 확인한 경우, 다음 섹션을 살펴보세요.
-
-다음 모든 기여에 대해서는 PR을 열여야 합니다. [PR 열기](#how-to-open-a-pr) 섹션에서 자세히 설명되어 있습니다.
-
-### 4. "Good first issue" 고치기
-
-*Good first issues*는 [Good first issue](https://github.com/huggingface/diffusers/issues?q=is%3Aopen+is%3Aissue+label%3A%22good+first+issue%22) 라벨로 표시됩니다. 일반적으로, 이슈는 이미 잠재적인 해결책이 어떻게 보이는지 설명하고 있어서 수정하기 쉽습니다.
-만약 이슈가 아직 닫히지 않았고 이 문제를 해결해보고 싶다면, "이 이슈를 해결해보고 싶습니다."라는 메시지를 남기면 됩니다. 일반적으로 세 가지 시나리오가 있습니다:
-- a.) 이슈 설명이 이미 해결책을 제안합니다. 이 경우, 해결책이 이해되고 합리적으로 보인다면, PR 또는 드래프트 PR을 열어서 수정할 수 있습니다.
-- b.) 이슈 설명이 해결책을 제안하지 않습니다. 이 경우, 어떤 해결책이 가능할지 물어볼 수 있고, Diffusers 팀의 누군가가 곧 답변해줄 것입니다. 만약 어떻게 수정할지 좋은 아이디어가 있다면, 직접 PR을 열어도 됩니다.
-- c.) 이미 이 문제를 해결하기 위해 열린 PR이 있지만, 이슈가 아직 닫히지 않았습니다. PR이 더 이상 진행되지 않았다면, 새로운 PR을 열고 이전 PR에 링크를 걸면 됩니다. PR은 종종 원래 기여자가 갑자기 시간을 내지 못해 더 이상 진행하지 못하는 경우에 더 이상 진행되지 않게 됩니다. 이는 오픈 소스에서 자주 발생하는 일이며 매우 정상적인 상황입니다. 이 경우, 커뮤니티는 새로 시도하고 기존 PR의 지식을 활용해주면 매우 기쁠 것입니다. 이미 PR이 있고 활성화되어 있다면, 제안을 해주거나 PR을 검토하거나 PR에 기여할 수 있는지 물어보는 등 작성자를 도와줄 수 있습니다.
-
-
-### 5. 문서에 기여하기
-
-좋은 라이브러리는 항상 좋은 문서를 갖고 있습니다! 공식 문서는 라이브러리를 처음 사용하는 사용자들에게 첫 번째 접점 중 하나이며, 따라서 문서에 기여하는 것은 매우 가치 있는 기여입니다.
-
-라이브러리에 기여하는 방법은 다양합니다:
-
-- 맞춤법이나 문법 오류를 수정합니다.
-- 공식 문서가 이상하게 표시되거나 링크가 깨진 경우, 올바르게 수정하는 데 시간을 내주시면 매우 기쁠 것입니다.
-- 문서의 입력 또는 출력 텐서의 모양이나 차원을 수정합니다.
-- 이해하기 어렵거나 잘못된 문서를 명확하게 합니다.
-- 오래된 코드 예제를 업데이트합니다.
-- 문서를 다른 언어로 번역합니다.
-
-[공식 Diffusers 문서 페이지](https://huggingface.co/docs/diffusers/index)에 표시된 모든 내용은 공식 문서의 일부이며, 해당 [문서 소스](https://github.com/huggingface/diffusers/tree/main/docs/source)에서 수정할 수 있습니다.
-
-문서에 대한 변경 사항을 로컬에서 확인하는 방법은 [이 페이지](https://github.com/huggingface/diffusers/tree/main/docs)를 참조해주세요.
-
-
-### 6. 커뮤니티 파이프라인에 기여하기
-
-> [!TIP]
-> 커뮤니티 파이프라인에 대해 자세히 알아보려면 [커뮤니티 파이프라인](../using-diffusers/custom_pipeline_overview#community-pipelines) 가이드를 읽어보세요. 커뮤니티 파이프라인이 왜 필요한지 궁금하다면 GitHub 이슈 [#841](https://github.com/huggingface/diffusers/issues/841)를 확인해보세요 (기본적으로, 우리는 diffusion 모델이 추론에 사용될 수 있는 모든 방법을 유지할 수 없지만 커뮤니티가 이를 구축하는 것을 방해하고 싶지 않습니다).
-
-커뮤니티 파이프라인에 기여하는 것은 창의성과 작업을 커뮤니티와 공유하는 좋은 방법입니다. [`DiffusionPipeline`]을 기반으로 빌드하여 `custom_pipeline` 매개변수를 설정함으로써 누구나 로드하고 사용할 수 있도록 할 수 있습니다. 이 섹션에서는 UNet이 단일 순방향 패스만 수행하고 스케줄러를 한 번 호출하는 간단한 파이프라인 (단계별 파이프라인)을 만드는 방법을 안내합니다.
-
-1. 커뮤니티 파이프라인을 위한 one_step_unet.py 파일을 생성하세요. 이 파일은 사용자에 의해 설치되는 패키지를 포함할 수 있지만, [`DiffusionPipeline`]에서 모델 가중치와 스케줄러 구성을 로드하기 위해 하나의 파이프라인 클래스만 있어야 합니다. `__init__` 함수에 UNet과 스케줄러를 추가하세요.
-
-    또한 [`~DiffusionPipeline.save_pretrained`]를 사용하여 파이프라인과 그 구성 요소를 저장할 수 있도록 `register_modules` 함수를 추가해야 합니다.
-
-```py
-from diffusers import DiffusionPipeline
-import torch
-
-class UnetSchedulerOneForwardPipeline(DiffusionPipeline):
-    def __init__(self, unet, scheduler):
-        super().__init__()
-
-        self.register_modules(unet=unet, scheduler=scheduler)
-```
-
-1. forward 패스에서 (`__call__`로 정의하는 것을 추천합니다), 원하는 어떤 기능이든 추가할 수 있습니다. "one-step" 파이프라인의 경우, 무작위 이미지를 생성하고 `timestep=1`로 설정하여 UNet과 스케줄러를 한 번 호출합니다.
-
-```py
-  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
-```
-
-이제 UNet과 스케줄러를 전달하여 파이프라인을 실행하거나, 파이프라인 구조가 동일한 경우 사전 학습된 가중치를 로드할 수 있습니다.
-
-```py
-from diffusers import DDPMScheduler, UNet2DModel
-
-scheduler = DDPMScheduler()
-unet = UNet2DModel()
-
-pipeline = UnetSchedulerOneForwardPipeline(unet=unet, scheduler=scheduler)
-output = pipeline()
-# load pretrained weights
-pipeline = UnetSchedulerOneForwardPipeline.from_pretrained("google/ddpm-cifar10-32", use_safetensors=True)
-output = pipeline()
-```
-
-파이프라인을 GitHub 커뮤니티 파이프라인 또는 Hub 커뮤니티 파이프라인으로 공유할 수 있습니다.
-
-<hfoptions id="pipeline type">
-<hfoption id="GitHub pipeline">
-
-GitHub 파이프라인을 공유하려면 Diffusers [저장소](https://github.com/huggingface/diffusers)에서 PR을 열고 one_step_unet.py 파일을 [examples/community](https://github.com/huggingface/diffusers/tree/main/examples/community) 하위 폴더에 추가하세요.
-
-</hfoption>
-<hfoption id="Hub pipeline">
-
-Hub 파이프라인을 공유하려면, 허브에 모델 저장소를 생성하고 one_step_unet.py 파일을 업로드하세요.
-
-</hfoption>
-</hfoptions>
-
-### 7. 훈련 예제에 기여하기
-
-Diffusers 예제는 [examples](https://github.com/huggingface/diffusers/tree/main/examples) 폴더에 있는 훈련 스크립트의 모음입니다.
-
-두 가지 유형의 훈련 예제를 지원합니다:
-
-- 공식 훈련 예제
-- 연구용 훈련 예제
-
-연구용 훈련 예제는 [examples/research_projects](https://github.com/huggingface/diffusers/tree/main/examples/research_projects)에 위치하며, 공식 훈련 예제는 `research_projects` 및 `community` 폴더를 제외한 [examples](https://github.com/huggingface/diffusers/tree/main/examples)의 모든 폴더를 포함합니다.
-공식 훈련 예제는 Diffusers의 핵심 메인테이너가 유지 관리하며, 연구용 훈련 예제는 커뮤니티가 유지 관리합니다.
-이는 공식 파이프라인 vs 커뮤니티 파이프라인에 대한 [6. 커뮤니티 파이프라인 기여하기](#6-contribute-a-community-pipeline)에서 제시한 이유와 동일합니다: 핵심 메인테이너가 diffusion 모델의 모든 가능한 훈련 방법을 유지 관리하는 것은 현실적으로 불가능합니다.
-Diffusers 핵심 메인테잉너와 커뮤니티가 특정 훈련 패러다임을 너무 실험적이거나 충분히 인기 없는 것으로 간주하는 경우, 해당 훈련 코드는 `research_projects` 폴더에 넣고 작성자가 유지 관리해야 합니다.
-
-공식 훈련 및 연구 예제는 하나 이상의 훈련 스크립트, requirements.txt 파일 및 README.md 파일을 포함하는 디렉토리로 구성됩니다. 사용자가 훈련 예제를 사용하려면 리포지토리를 복제해야 합니다:
-
-```bash
-git clone https://github.com/huggingface/diffusers
-```
-
-그리고 훈련에 필요한 모든 추가적인 의존성도 설치해야 합니다:
-
-```bash
-pip install -r /examples/<your-example-folder>/requirements.txt
-```
-
-따라서 예제를 추가할 때, `requirements.txt` 파일은 훈련 예제에 필요한 모든 pip 종속성을 정의해야 합니다. 이렇게 설치된 모든 종속성을 사용하여 사용자가 예제의 훈련 스크립트를 실행할 수 있어야 합니다. 예를 들어, [DreamBooth `requirements.txt` 파일](https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/requirements.txt)을 참조하세요.
-
-Diffusers 라이브러리의 훈련 예제는 다음 철학을 따라야 합니다:
-- 예제를 실행하는 데 필요한 모든 코드는 하나의 Python 파일에 있어야 합니다.
-- 사용자는 명령 줄에서 `python <your-example>.py --args`와 같이 예제를 실행할 수 있어야 합니다.
-- 예제는 간단하게 유지되어야 하며, Diffusers를 사용한 훈련 방법을 보여주는 **예시**로 사용되어야 합니다. 예제 스크립트의 목적은 최첨단 diffusion 모델을 만드는 것이 아니라, 너무 많은 사용자 정의 로직을 추가하지 않고 이미 알려진 훈련 방법을 재현하는 것입니다. 이 점의 부산물로서, 예제는 좋은 교육 자료로써의 역할을 하기 위해 노력합니다.
-
-예제에 기여하기 위해서는, 이미 존재하는 예제인 [dreambooth](https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/train_dreambooth.py)와 같은 예제를 참고하여 어떻게 보여야 하는지에 대한 아이디어를 얻는 것이 매우 권장됩니다.
-Diffusers와 긴밀하게 통합되어 있기 때문에, 기여자들이 [Accelerate 라이브러리](https://github.com/huggingface/accelerate)를 사용하는 것을 강력히 권장합니다.
-예제 스크립트가 작동하는 경우, 반드시 예제를 정확하게 사용하는 방법을 설명하는 포괄적인 `README.md`를 추가해야 합니다. 이 README에는 다음이 포함되어야 합니다:
-- [여기](https://github.com/huggingface/diffusers/tree/main/examples/dreambooth#running-locally-with-pytorch)에 표시된 예제 스크립트를 실행하는 방법에 대한 예제 명령어.
-- [여기](https://api.wandb.ai/report/patrickvonplaten/xm6cd5q5)에 표시된 훈련 결과 (로그, 모델 등)에 대한 링크로 사용자가 기대할 수 있는 내용을 보여줍니다.
-- 비공식/연구용 훈련 예제를 추가하는 경우, **반드시** git 핸들을 포함하여 이 훈련 예제를 유지 관리할 것임을 명시하는 문장을 추가해야 합니다. [여기](https://github.com/huggingface/diffusers/tree/main/examples/research_projects/intel_opts#diffusers-examples-with-intel-optimizations)에 표시된 것과 같습니다.
-
-만약 공식 훈련 예제에 기여하는 경우, [examples/test_examples.py](https://github.com/huggingface/diffusers/blob/main/examples/test_examples.py)에 테스트를 추가하는 것도 확인해주세요. 비공식 훈련 예제에는 이 작업이 필요하지 않습니다.
-
-### 8. "Good second issue" 고치기
-
-"Good second issue"는 [Good second issue](https://github.com/huggingface/diffusers/issues?q=is%3Aopen+is%3Aissue+label%3A%22Good+second+issue%22) 라벨로 표시됩니다. Good second issue는 [Good first issues](https://github.com/huggingface/diffusers/issues?q=is%3Aopen+is%3Aissue+label%3A%22good+first+issue%22)보다 해결하기가 더 복잡합니다.
-이슈 설명은 일반적으로 이슈를 해결하는 방법에 대해 덜 구체적이며, 관심 있는 기여자는 라이브러리에 대한 꽤 깊은 이해가 필요합니다.
-Good second issue를 해결하고자 하는 경우, 해당 이슈를 해결하기 위해 PR을 열고 PR을 이슈에 링크하세요. 이미 해당 이슈에 대한 PR이 열려있지만 병합되지 않은 경우, 왜 병합되지 않았는지 이해하기 위해 살펴보고 개선된 PR을 열어보세요.
-Good second issue는 일반적으로 Good first issue 이슈보다 병합하기가 더 어려우므로, 핵심 메인테이너에게 도움을 요청하는 것이 좋습니다. PR이 거의 완료된 경우, 핵심 메인테이너는 PR에 참여하여 커밋하고 병합을 진행할 수 있습니다.
-
-### 9. 파이프라인, 모델, 스케줄러 추가하기
-
-파이프라인, 모델, 스케줄러는 Diffusers 라이브러리에서 가장 중요한 부분입니다.
-이들은 최첨단 diffusion 기술에 쉽게 접근하도록 하며, 따라서 커뮤니티가 강력한 생성형 AI 애플리케이션을 만들 수 있도록 합니다.
-
-새로운 모델, 파이프라인 또는 스케줄러를 추가함으로써, 사용자 인터페이스에 새로운 강력한 사용 사례를 활성화할 수 있으며, 이는 전체 생성형 AI 생태계에 매우 중요한 가치를 제공할 수 있습니다.
-
-Diffusers에는 세 가지 구성 요소에 대한 여러 개발 요청이 있습니다. 특정 구성 요소를 아직 정확히 어떤 것을 추가하고 싶은지 모르는 경우, 다음 링크를 참조하세요:
-- [모델 또는 파이프라인](https://github.com/huggingface/diffusers/issues?q=is%3Aopen+is%3Aissue+label%3A%22New+pipeline%2Fmodel%22)
-- [스케줄러](https://github.com/huggingface/diffusers/issues?q=is%3Aopen+is%3Aissue+label%3A%22New+scheduler%22)
-
-
-세 가지 구성 요소를 추가하기 전에, [철학 가이드](philosophy)를 읽어보는 것을 강력히 권장합니다. 세 가지 구성 요소 중 어느 것을 추가하든, 디자인 철학과 관련된 API 일관성을 유지하기 위해 우리의 디자인 철학과 크게 다른 구성 요소는 병합할 수 없습니다. 디자인 선택에 근본적으로 동의하지 않는 경우, [피드백 이슈](https://github.com/huggingface/diffusers/issues/new?assignees=&labels=&template=feedback.md&title=)를 열어 해당 디자인 패턴/선택이 라이브러리 전체에서 변경되어야 하는지, 디자인 철학을 업데이트해야 하는지에 대해 논의할 수 있습니다. 라이브러리 전체의 일관성은 우리에게 매우 중요합니다.
-
-PR에 원본 코드베이스/논문 링크를 추가하고, 가능하면 PR에서 원래 작성자에게 직접 알림을 보내어 진행 상황을 따라갈 수 있도록 해주세요.
-
-PR에서 막힌 경우나 도움이 필요한 경우, 첫 번째 리뷰나 도움을 요청하는 메시지를 남기는 것을 주저하지 마세요.
-
-#### Copied from mechanism
-
-`# Copied from mechanism` 은 파이프라인, 모델 또는 스케줄러 코드를 추가할 때 이해해야 할 독특하고 중요한 기능입니다. Diffusers 코드베이스 전체에서 이를 자주 볼 수 있는데, 이를 사용하는 이유는 코드베이스를 이해하기 쉽고 유지 관리하기 쉽게 유지하기 위함입니다. `# Copied from mechanism` 으로 표시된 코드는 복사한 코드와 정확히 동일하도록 강제됩니다. 이를 통해 `make fix-copies`를 실행할 때 많은 파일에 걸쳐 변경 사항을 쉽게 업데이트하고 전파할 수 있습니다.
-
-예를 들어, 아래 코드 예제에서 [`~diffusers.pipelines.stable_diffusion.StableDiffusionPipelineOutput`]은 원래 코드이며, `AltDiffusionPipelineOutput`은 `# Copied from mechanism`을 사용하여 복사합니다. 유일한 차이점은 클래스 접두사를 `Stable`에서 `Alt`로 변경한 것입니다.
-
-```py
-# Copied from diffusers.pipelines.stable_diffusion.pipeline_output.StableDiffusionPipelineOutput with Stable->Alt
-class AltDiffusionPipelineOutput(BaseOutput):
-    """
-    Output class for Alt Diffusion pipelines.
-
-    Args:
-        images (`List[PIL.Image.Image]` or `np.ndarray`)
-            List of denoised PIL images of length `batch_size` or NumPy array of shape `(batch_size, height, width,
-            num_channels)`.
-        nsfw_content_detected (`List[bool]`)
-            List indicating whether the corresponding generated image contains "not-safe-for-work" (nsfw) content or
-            `None` if safety checking could not be performed.
-    """
-```
-
-더 자세히 알고 싶다면 [~Don't~ Repeat Yourself*](https://huggingface.co/blog/transformers-design-philosophy#4-machine-learning-models-are-static) 블로그 포스트의 이 섹션을 읽어보세요.
-
-## 좋은 이슈 작성 방법
-
-**이슈를 잘 작성할수록 빠르게 해결될 가능성이 높아집니다.**
-
-1. 이슈에 적절한 템플릿을 사용했는지 확인하세요. [새 이슈를 열 때](https://github.com/huggingface/diffusers/issues/new/choose) 올바른 템플릿을 선택해야 합니다. *버그 보고서*, *기능 요청*, *API 디자인에 대한 피드백*, *새로운 모델/파이프라인/스케줄러 추가*, *포럼*, 또는 빈 이슈 중에서 선택하세요. 이슈를 열 때 올바른 템플릿을 선택하는 것이 중요합니다.
-2. **명확성**: 이슈에 적합한 제목을 지정하세요. 이슈 설명을 가능한 간단하게 작성하세요. 이슈를 이해하고 해결하는 데 걸리는 시간을 줄이기 위해 가능한 한 명확하게 작성하세요. 하나의 이슈에 대해 여러 문제를 포함하지 않도록 주의하세요. 여러 문제를 발견한 경우, 각각의 이슈를 개별적으로 열어주세요. 버그인 경우, 어떤 버그인지 가능한 한 정확하게 설명해야 합니다. "diffusers에서 오류"와 같이 간단히 작성하지 마세요.
-3. **재현 가능성**: 재현 가능한 코드 조각이 없으면 해결할 수 없습니다. 버그를 발견한 경우, 유지 관리자는 그 버그를 재현할 수 있어야 합니다. 이슈에 재현 가능한 코드 조각을 포함해야 합니다. 코드 조각은 Python 인터프리터에 복사하여 붙여넣을 수 있는 형태여야 합니다. 코드 조각이 작동해야 합니다. 즉, 누락된 import나 이미지에 대한 링크가 없어야 합니다. 이슈에는 오류 메시지와 정확히 동일한 오류 메시지를 재현하기 위해 수정하지 않고 복사하여 붙여넣을 수 있는 코드 조각이 포함되어야 합니다. 이슈에 사용자의 로컬 모델 가중치나 로컬 데이터를 사용하는 경우, 독자가 액세스할 수 없는 경우 이슈를 해결할 수 없습니다. 데이터나 모델을 공유할 수 없는 경우, 더미 모델이나 더미 데이터를 만들어 사용해보세요.
-4. **간결성**: 가능한 한 간결하게 유지하여 독자가 문제를 빠르게 이해할 수 있도록 도와주세요. 문제와 관련이 없는 코드나 정보는 모두 제거해주세요. 버그를 발견한 경우, 문제를 설명하는 가장 간단한 코드 예제를 만들어보세요. 버그를 발견한 후에는 작업 흐름 전체를 문제에 던지는 것이 아니라, 에러가 발생하는 훈련 코드의 어느 부분이 문제인지 먼저 이해하고 몇 줄로 재현해보세요. 전체 데이터셋 대신 더미 데이터를 사용해보세요.
-5. 링크 추가하기. 특정한 이름, 메서드, 또는 모델을 참조하는 경우, 독자가 더 잘 이해할 수 있도록 링크를 제공해주세요. 특정 PR이나 이슈를 참조하는 경우, 해당 이슈에 링크를 걸어주세요. 독자가 무엇을 말하는지 알고 있다고 가정하지 마세요. 이슈에 링크를 추가할수록 좋습니다.
-6. 포맷팅. 파이썬 코드 구문으로 코드를 포맷팅하고, 일반 코드 구문으로 에러 메시지를 포맷팅해주세요. 자세한 내용은 [공식 GitHub 포맷팅 문서](https://docs.github.com/en/get-started/writing-on-github/getting-started-with-writing-and-formatting-on-github/basic-writing-and-formatting-syntax)를 참조하세요.
-7. 이슈를 해결해야 하는 티켓이 아니라, 잘 작성된 백과사전 항목으로 생각해보세요. 추가된 이슈는 공개적으로 사용 가능한 지식에 기여하는 것입니다. 잘 작성된 이슈를 추가함으로써 메인테이너가 문제를 해결하는 데 도움을 주는 것뿐만 아니라, 전체 커뮤니티가 라이브러리의 특정 측면을 더 잘 이해할 수 있도록 도움을 주는 것입니다.
-
-## 좋은 PR 작성 방법
-
-1. 카멜레온이 되세요. 기존의 디자인 패턴과 구문을 이해하고, 코드 추가가 기존 코드베이스에 매끄럽게 흐르도록 해야 합니다. 기존 디자인 패턴이나 사용자 인터페이스와 크게 다른 PR은 병합되지 않습니다.
-2. 초점을 맞추세요. 하나의 문제만 해결하는 PR을 작성해야 합니다. "추가하면서 다른 문제도 해결하기"에 빠지지 않도록 주의하세요. 여러 개의 관련 없는 문제를 해결하는 PR을 작성하는 것은 리뷰하기가 훨씬 어렵습니다.
-3. 도움이 되는 경우, 추가한 내용이 어떻게 사용되는지 예제 코드 조각을 추가해보세요.
-4. PR의 제목은 기여 내용을 요약해야 합니다.
-5. PR이 이슈를 해결하는 경우, PR 설명에 이슈 번호를 언급하여 연결되도록 해주세요 (이슈를 참조하는 사람들이 작업 중임을 알 수 있도록).
-6. 진행 중인 작업을 나타내려면 제목에 `[WIP]`를 접두사로 붙여주세요. 이는 중복 작업을 피하고, 병합 준비가 된 PR과 구분할 수 있도록 도움이 됩니다.
-7. [좋은 이슈를 작성하는 방법](#how-to-write-a-good-issue)에 설명된 대로 텍스트를 구성하고 형식을 지정해보세요.
-8. 기존 테스트가 통과하는지 확인하세요
-9. 높은 커버리지를 가진 테스트를 추가하세요. 품질 테스트가 없으면 병합할 수 없습니다.
-- 새로운 `@slow` 테스트를 추가하는 경우, 다음 명령을 사용하여 통과하는지 확인하세요.
-`RUN_SLOW=1 python -m pytest tests/test_my_new_model.py`.
-CircleCI는 느린 테스트를 실행하지 않지만, GitHub Actions는 매일 실행합니다!
-10. 모든 공개 메서드는 마크다운과 잘 작동하는 정보성 docstring을 가져야 합니다. 예시로 [`pipeline_latent_diffusion.py`](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/latent_diffusion/pipeline_latent_diffusion.py)를 참조하세요.
-11. 레포지토리가 빠르게 성장하고 있기 때문에, 레포지토리에 큰 부담을 주는 파일이 추가되지 않도록 주의해야 합니다. 이미지, 비디오 및 기타 텍스트가 아닌 파일을 포함합니다. 이러한 파일을 배치하기 위해 hf.co 호스팅 `dataset`인 [`hf-internal-testing`](https://huggingface.co/hf-internal-testing) 또는 [huggingface/documentation-images](https://huggingface.co/datasets/huggingface/documentation-images)를 활용하는 것이 우선입니다.
-외부 기여인 경우, 이미지를 PR에 추가하고 Hugging Face 구성원에게 이미지를 이 데이터셋으로 이동하도록 요청하세요.
-
-## PR을 열기 위한 방법
-
-코드를 작성하기 전에, 이미 누군가가 같은 작업을 하고 있는지 확인하기 위해 기존의 PR이나 이슈를 검색하는 것이 좋습니다. 확실하지 않은 경우, 피드백을 받기 위해 이슈를 열어보는 것이 항상 좋은 아이디어입니다.
-
-🧨 Diffusers에 기여하기 위해서는 기본적인 `git` 사용법을 알아야 합니다. `git`은 가장 쉬운 도구는 아니지만, 가장 훌륭한 매뉴얼을 가지고 있습니다. 셸에서 `git --help`을 입력하고 즐기세요. 책을 선호하는 경우, [Pro Git](https://git-scm.com/book/en/v2)은 매우 좋은 참고 자료입니다.
-
-다음 단계를 따라 기여를 시작하세요 ([지원되는 Python 버전](https://github.com/huggingface/diffusers/blob/main/setup.py#L244)):
-
-1. 저장소 페이지에서 'Fork' 버튼을 클릭하여 [저장소](https://github.com/huggingface/diffusers)를 포크합니다. 이렇게 하면 코드의 사본이 GitHub 사용자 계정에 생성됩니다.
-
-2. 포크한 저장소를 로컬 디스크에 클론하고, 기본 저장소를 원격으로 추가하세요:
-
- ```bash
- $ git clone git@github.com:<your GitHub handle>/diffusers.git
- $ cd diffusers
- $ git remote add upstream https://github.com/huggingface/diffusers.git
- ```
-
-3. 개발 변경 사항을 보관할 새로운 브랜치를 생성하세요:
-
- ```bash
- $ git checkout -b a-descriptive-name-for-my-changes
- ```
-
-`main` 브랜치 위에서 **절대** 작업하지 마세요.
-
-1. 가상 환경에서 다음 명령을 실행하여 개발 환경을 설정하세요:
-
- ```bash
- $ pip install -e ".[dev]"
- ```
-
-만약 저장소를 이미 클론한 경우, 가장 최신 변경 사항을 가져오기 위해 `git pull`을 실행해야 할 수도 있습니다.
-
-5. 기능을 브랜치에서 개발하세요.
-
-기능을 작업하는 동안 테스트 스위트가 통과되는지 확인해야 합니다. 다음과 같이 변경 사항에 영향을 받는 테스트를 실행해야 합니다:
-
- ```bash
- $ pytest tests/<TEST_TO_RUN>.py
- ```
-
-테스트를 실행하기 전에 테스트를 위해 필요한 의존성들을 설치하였는지 확인하세요. 다음의 커맨드를 통해서 확인할 수 있습니다:
-
- ```bash
- $ pip install -e ".[test]"
- ```
-
-다음 명령어로 전체 테스트 묶음 실행할 수도 있지만, Diffusers가 많이 성장하였기 때문에 결과를 적당한 시간 내에 생성하기 위해서는 강력한 컴퓨터가 필요합니다. 다음은 해당 명령어입니다:
-
- ```bash
- $ make test
- ```
-
-🧨 Diffusers는 소스 코드를 일관되게 포맷팅하기 위해 `black`과 `isort`를 사용합니다. 변경 사항을 적용한 후에는 다음과 같이 자동 스타일 수정 및 코드 검증을 적용할 수 있습니다:
-
-
- ```bash
- $ make style
- ```
-
-🧨 Diffusers `ruff`와 몇개의 커스텀 스크립트를 이용하여 코딩 실수를 확인합니다. 품질 제어는 CI에서 작동하지만, 동일한 검사를 다음을 통해서도 할 수 있습니다:
-
- ```bash
- $ make quality
- ```
-
-변경사항에 대해 만족한다면 `git add`를 사용하여 변경된 파일을 추가하고 `git commit`을 사용하여 변경사항에 대해 로컬상으로 저장한다:
-
- ```bash
- $ git add modified_file.py
- $ git commit -m "A descriptive message about your changes."
- ```
-
-코드를 정기적으로 원본 저장소와 동기화하는 것은 좋은 아이디어입니다. 이렇게 하면 변경 사항을 빠르게 반영할 수 있습니다:
-
- ```bash
- $ git pull upstream main
- ```
-
-변경 사항을 계정에 푸시하려면 다음을 사용하세요:
-
- ```bash
- $ git push -u origin a-descriptive-name-for-my-changes
- ```
-
-6. 만족하셨다면, GitHub에서 포크한 웹페이지로 이동하여 'Pull request'를 클릭하여 변경사항을 프로젝트 메인테이너에게 검토를 요청합니다.
-
-7. 메인테이너가 변경 사항을 요청하는 것은 괜찮습니다. 핵심 기여자들에게도 일어나는 일입니다! 따라서 변경 사항을 Pull request에서 볼 수 있도록 로컬 브랜치에서 작업하고 변경 사항을 포크에 푸시하면 자동으로 Pull request에 나타납니다.
-
-### 테스트
-
-라이브러리 동작과 여러 예제를 테스트하기 위해 포괄적인 테스트 묶음이 포함되어 있습니다. 라이브러리 테스트는 [tests 폴더](https://github.com/huggingface/diffusers/tree/main/tests)에서 찾을 수 있습니다.
-
-`pytest`와 `pytest-xdist`를 선호하는 이유는 더 빠르기 때문입니다. 루트 디렉토리에서 라이브러리를 위해 `pytest`로 테스트를 실행하는 방법은 다음과 같습니다:
-
-```bash
-$ python -m pytest -n auto --dist=loadfile -s -v ./tests/
-```
-
-사실, `make test`는 이렇게 구현되어 있습니다!
-
-작업 중인 기능만 테스트하기 위해 더 작은 테스트 세트를 지정할 수 있습니다.
-
-기본적으로 느린 테스트는 건너뜁니다. `RUN_SLOW` 환경 변수를 `yes`로 설정하여 실행할 수 있습니다. 이는 많은 기가바이트의 모델을 다운로드합니다. 충분한 디스크 공간과 좋은 인터넷 연결 또는 많은 인내심이 필요합니다!
-
-```bash
-$ RUN_SLOW=yes python -m pytest -n auto --dist=loadfile -s -v ./tests/
-```
-
-`unittest`는 완전히 지원됩니다. 다음은 `unittest`를 사용하여 테스트를 실행하는 방법입니다:
-
-```bash
-$ python -m unittest discover -s tests -t . -v
-$ python -m unittest discover -s examples -t examples -v
-```
-
-### upstream(main)과 forked main 동기화하기
-
-upstream 저장소에 불필요한 참조 노트를 추가하고 관련 개발자에게 알림을 보내는 것을 피하기 위해,
-forked 저장소의 main 브랜치를 동기화할 때 다음 단계를 따르세요:
-1. 가능한 경우, forked 저장소에서 브랜치와 PR을 사용하여 upstream과 동기화하는 것을 피하세요. 대신 forked main으로 직접 병합하세요.
-2. PR이 절대적으로 필요한 경우, 브랜치를 체크아웃한 후 다음 단계를 사용하세요:
-```bash
-$ git checkout -b your-branch-for-syncing
-$ git pull --squash --no-commit upstream main
-$ git commit -m '<your message without GitHub references>'
-$ git push --set-upstream origin your-branch-for-syncing
-```
-
-### 스타일 가이드
-
-Documentation string에 대해서는, 🧨 Diffusers는 [Google 스타일](https://google.github.io/styleguide/pyguide.html)을 따릅니다.

docs/source/ko/conceptual/ethical_guidelines.md

@@ -1,64 +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.
--->
-
-# 🧨 Diffusers의 윤리 지침 [[-diffusers-ethical-guidelines]]
-
-## 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.
-
-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 [[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 [[ethical-guidelines]]
-
-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.
-
-- **일관성**: 우리는 프로젝트 관리에서 사용자들에게 동일한 수준의 관심을 보장하고 기술적으로 안정되고 일관된 상태를 유지할 것을 약속합니다.
-
-- **간결성**: Diffusers 라이브러리를 사용하고 활용하기 쉽게 만들기 위해, 프로젝트의 목표를 간결하고 일관성 있게 유지할 것을 약속합니다.
-
-- **접근성**: Diffusers 프로젝트는 기술적 전문 지식 없어도 프로젝트 운영에 참여할 수 있는 기여자의 진입장벽을 낮춥니다. 이를 통해 연구 결과물이 커뮤니티에 더 잘 접근할 수 있게 됩니다.
-
-- **재현성**: 우리는 Diffusers 라이브러리를 통해 제공되는 업스트림(upstream) 코드, 모델 및 데이터셋의 재현성에 대해 투명하게 공개할 것을 목표로 합니다.
-
-- **책임**: 우리는 커뮤니티와 팀워크를 통해, 이 기술의 잠재적인 위험과 위험을 예측하고 완화하는 데 대한 공동 책임을 가지고 있습니다.
-
-
-## 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.
-
-- [**커뮤니티 탭**](https://huggingface.co/docs/hub/repositories-pull-requests-discussions): 이를 통해 커뮤니티는 프로젝트에 대해 토론하고 더 나은 협력을 할 수 있습니다.
-
-- **편향 탐색 및 평가**: Hugging Face 팀은 Stable Diffusion 모델의 편향성을 대화형으로 보여주는 [space](https://huggingface.co/spaces/society-ethics/DiffusionBiasExplorer)을 제공합니다. 이런 의미에서, 우리는 편향 탐색 및 평가를 지원하고 장려합니다.
-
-- **배포에서의 안전 유도**
-
-  - [**안전한 Stable Diffusion**](https://huggingface.co/docs/diffusers/main/en/api/pipelines/stable_diffusion/stable_diffusion_safe): 이는 필터되지 않은 웹 크롤링 데이터셋으로 훈련된 Stable Diffusion과 같은 모델이 부적절한 변질에 취약한 문제를 완화합니다. 관련 논문: [Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models](https://arxiv.org/abs/2211.05105).
-
-  - [**안전 검사기**](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/stable_diffusion/safety_checker.py): 이미지가 생성된 후에 이미자가 임베딩 공간에서 일련의 하드코딩된 유해 개념의 클래스일 확률을 확인하고 비교합니다. 유해 개념은 역공학을 방지하기 위해 의도적으로 숨겨져 있습니다.
-
-- **Hub에서의 단계적인 배포**: 특히 민감한 상황에서는 일부 리포지토리에 대한 접근을 제한해야 합니다. 이 단계적인 배포는 중간 단계로, 리포지토리 작성자가 사용에 대한 더 많은 통제력을 갖게 합니다.
-
-- **라이선싱**: [OpenRAILs](https://huggingface.co/blog/open_rail)와 같은 새로운 유형의 라이선싱을 통해 자유로운 접근을 보장하면서도 더 책임 있는 사용을 위한 일련의 제한을 둘 수 있습니다.

docs/source/ko/conceptual/evaluation.md

@@ -1,554 +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.
--->
-
-# Diffusion 모델 평가하기[[evaluating-diffusion-models]]
-
-<a target="_blank" href="https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/evaluation.ipynb">
-    <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>
-</a>
-
-[Stable Diffusion](https://huggingface.co/docs/diffusers/stable_diffusion)와 같은 생성 모델의 평가는 주관적인 성격을 가지고 있습니다. 그러나 실무자와 연구자로서 우리는 종종 다양한 가능성 중에서 신중한 선택을 해야 합니다. 그래서 다양한 생성 모델 (GAN, Diffusion 등)을 사용할 때 어떻게 선택해야 할까요?
-
-정성적인 평가는 모델의 이미지 품질에 대한 주관적인 평가이므로 오류가 발생할 수 있고 결정에 잘못된 영향을 미칠 수 있습니다. 반면, 정량적인 평가는 이미지 품질과 직접적인 상관관계를 갖지 않을 수 있습니다. 따라서 일반적으로 정성적 평가와 정량적 평가를 모두 고려하는 것이 더 강력한 신호를 제공하여 모델 선택에 도움이 됩니다.
-
-이 문서에서는 Diffusion 모델을 평가하기 위한 정성적 및 정량적 방법에 대해 상세히 설명합니다. 정량적 방법에 대해서는 특히 `diffusers`와 함께 구현하는 방법에 초점을 맞추었습니다.
-
-이 문서에서 보여진 방법들은 기반 생성 모델을 고정시키고 다양한 [노이즈 스케줄러](https://huggingface.co/docs/diffusers/main/en/api/schedulers/overview)를 평가하는 데에도 사용할 수 있습니다.
-
-## 시나리오[[scenarios]]
-다음과 같은 파이프라인을 사용하여 Diffusion 모델을 다룹니다:
-
-- 텍스트로 안내된 이미지 생성 (예: [`StableDiffusionPipeline`](https://huggingface.co/docs/diffusers/main/en/api/pipelines/stable_diffusion/text2img)).
-- 입력 이미지에 추가로 조건을 건 텍스트로 안내된 이미지 생성 (예: [`StableDiffusionImg2ImgPipeline`](https://huggingface.co/docs/diffusers/main/en/api/pipelines/stable_diffusion/img2img) 및 [`StableDiffusionInstructPix2PixPipeline`](https://huggingface.co/docs/diffusers/main/en/api/pipelines/pix2pix)).
-- 클래스 조건화된 이미지 생성 모델 (예: [`DiTPipeline`](https://huggingface.co/docs/diffusers/main/en/api/pipelines/dit)).
-
-## 정성적 평가[[qualitative-evaluation]]
-
-정성적 평가는 일반적으로 생성된 이미지의 인간 평가를 포함합니다. 품질은 구성성, 이미지-텍스트 일치, 공간 관계 등과 같은 측면에서 측정됩니다. 일반적인 프롬프트는 주관적인 지표에 대한 일정한 기준을 제공합니다.
-DrawBench와 PartiPrompts는 정성적인 벤치마킹에 사용되는 프롬프트 데이터셋입니다. DrawBench와 PartiPrompts는 각각 [Imagen](https://imagen.research.google/)과 [Parti](https://parti.research.google/)에서 소개되었습니다.
-
-[Parti 공식 웹사이트](https://parti.research.google/)에서 다음과 같이 설명하고 있습니다:
-
-> PartiPrompts (P2)는 이 작업의 일부로 공개되는 영어로 된 1600개 이상의 다양한 프롬프트 세트입니다. P2는 다양한 범주와 도전 측면에서 모델의 능력을 측정하는 데 사용할 수 있습니다.
-
-![parti-prompts](https://huggingface.co/datasets/diffusers/docs-images/resolve/main/evaluation_diffusion_models/parti-prompts.png)
-
-PartiPrompts는 다음과 같은 열을 가지고 있습니다:
-
-- 프롬프트 (Prompt)
-- 프롬프트의 카테고리 (예: "Abstract", "World Knowledge" 등)
-- 난이도를 반영한 챌린지 (예: "Basic", "Complex", "Writing & Symbols" 등)
-
-이러한 벤치마크는 서로 다른 이미지 생성 모델을 인간 평가로 비교할 수 있도록 합니다.
-
-이를 위해 🧨 Diffusers 팀은 **Open Parti Prompts**를 구축했습니다. 이는 Parti Prompts를 기반으로 한 커뮤니티 기반의 질적 벤치마크로, 최첨단 오픈 소스 확산 모델을 비교하는 데 사용됩니다:
-- [Open Parti Prompts 게임](https://huggingface.co/spaces/OpenGenAI/open-parti-prompts): 10개의 parti prompt에 대해 4개의 생성된 이미지가 제시되며, 사용자는 프롬프트에 가장 적합한 이미지를 선택합니다.
-- [Open Parti Prompts 리더보드](https://huggingface.co/spaces/OpenGenAI/parti-prompts-leaderboard): 현재 최고의 오픈 소스 diffusion 모델들을 서로 비교하는 리더보드입니다.
-
-이미지를 수동으로 비교하려면, `diffusers`를 사용하여 몇가지 PartiPrompts를 어떻게 활용할 수 있는지 알아봅시다.
-
-다음은 몇 가지 다른 도전에서 샘플링한 프롬프트를 보여줍니다: Basic, Complex, Linguistic Structures, Imagination, Writing & Symbols. 여기서는 PartiPrompts를 [데이터셋](https://huggingface.co/datasets/nateraw/parti-prompts)으로 사용합니다.
-
-```python
-from datasets import load_dataset
-
-# prompts = load_dataset("nateraw/parti-prompts", split="train")
-# prompts = prompts.shuffle()
-# sample_prompts = [prompts[i]["Prompt"] for i in range(5)]
-
-# Fixing these sample prompts in the interest of reproducibility.
-sample_prompts = [
-    "a corgi",
-    "a hot air balloon with a yin-yang symbol, with the moon visible in the daytime sky",
-    "a car with no windows",
-    "a cube made of porcupine",
-    'The saying "BE EXCELLENT TO EACH OTHER" written on a red brick wall with a graffiti image of a green alien wearing a tuxedo. A yellow fire hydrant is on a sidewalk in the foreground.',
-]
-```
-이제 이런 프롬프트를 사용하여 Stable Diffusion ([v1-4 checkpoint](https://huggingface.co/CompVis/stable-diffusion-v1-4))를 사용한 이미지 생성을 할 수 있습니다 :
-
-```python
-import torch
-
-seed = 0
-generator = torch.manual_seed(seed)
-
-images = sd_pipeline(sample_prompts, num_images_per_prompt=1, generator=generator).images
-```
-
-![parti-prompts-14](https://huggingface.co/datasets/diffusers/docs-images/resolve/main/evaluation_diffusion_models/parti-prompts-14.png)
-
-
-`num_images_per_prompt`를 설정하여 동일한 프롬프트에 대해 다른 이미지를 비교할 수도 있습니다. 다른 체크포인트([v1-5](https://huggingface.co/runwayml/stable-diffusion-v1-5))로 동일한 파이프라인을 실행하면 다음과 같은 결과가 나옵니다:
-
-![parti-prompts-15](https://huggingface.co/datasets/diffusers/docs-images/resolve/main/evaluation_diffusion_models/parti-prompts-15.png)
-
-
-다양한 모델을 사용하여 모든 프롬프트에서 생성된 여러 이미지들이 생성되면 (평가 과정에서) 이러한 결과물들은 사람 평가자들에게 점수를 매기기 위해 제시됩니다. DrawBench와 PartiPrompts 벤치마크에 대한 자세한 내용은 각각의 논문을 참조하십시오.
-
-<Tip>
-
-모델이 훈련 중일 때 추론 샘플을 살펴보는 것은 훈련 진행 상황을 측정하는 데 유용합니다. [훈련 스크립트](https://github.com/huggingface/diffusers/tree/main/examples/)에서는 TensorBoard와 Weights & Biases에 대한 추가 지원과 함께 이 유틸리티를 지원합니다.
-
-</Tip>
-
-## 정량적 평가[[quantitative-evaluation]]
-
-이 섹션에서는 세 가지 다른 확산 파이프라인을 평가하는 방법을 안내합니다:
-
-- CLIP 점수
-- CLIP 방향성 유사도
-- FID
-
-### 텍스트 안내 이미지 생성[[text-guided-image-generation]]
-
-[CLIP 점수](https://arxiv.org/abs/2104.08718)는 이미지-캡션 쌍의 호환성을 측정합니다. 높은 CLIP 점수는 높은 호환성🔼을 나타냅니다. CLIP 점수는 이미지와 캡션 사이의 의미적 유사성으로 생각할 수도 있습니다. CLIP 점수는 인간 판단과 높은 상관관계를 가지고 있습니다.
-
-[`StableDiffusionPipeline`]을 일단 로드해봅시다:
-
-```python
-from diffusers import StableDiffusionPipeline
-import torch
-
-model_ckpt = "CompVis/stable-diffusion-v1-4"
-sd_pipeline = StableDiffusionPipeline.from_pretrained(model_ckpt, torch_dtype=torch.float16).to("cuda")
-```
-
-여러 개의 프롬프트를 사용하여 이미지를 생성합니다:
-
-```python
-prompts = [
-    "a photo of an astronaut riding a horse on mars",
-    "A high tech solarpunk utopia in the Amazon rainforest",
-    "A pikachu fine dining with a view to the Eiffel Tower",
-    "A mecha robot in a favela in expressionist style",
-    "an insect robot preparing a delicious meal",
-    "A small cabin on top of a snowy mountain in the style of Disney, artstation",
-]
-
-images = sd_pipeline(prompts, num_images_per_prompt=1, output_type="np").images
-
-print(images.shape)
-# (6, 512, 512, 3)
-```
-
-그러고 나서 CLIP 점수를 계산합니다.
-
-```python
-from torchmetrics.functional.multimodal import clip_score
-from functools import partial
-
-clip_score_fn = partial(clip_score, model_name_or_path="openai/clip-vit-base-patch16")
-
-def calculate_clip_score(images, prompts):
-    images_int = (images * 255).astype("uint8")
-    clip_score = clip_score_fn(torch.from_numpy(images_int).permute(0, 3, 1, 2), prompts).detach()
-    return round(float(clip_score), 4)
-
-sd_clip_score = calculate_clip_score(images, prompts)
-print(f"CLIP score: {sd_clip_score}")
-# CLIP score: 35.7038
-```
-
-위의 예제에서는 각 프롬프트 당 하나의 이미지를 생성했습니다. 만약 프롬프트 당 여러 이미지를 생성한다면, 프롬프트 당 생성된 이미지의 평균 점수를 사용해야 합니다.
-
-이제 [`StableDiffusionPipeline`]과 호환되는 두 개의 체크포인트를 비교하려면, 파이프라인을 호출할 때 generator를 전달해야 합니다. 먼저, 고정된 시드로 [v1-4 Stable Diffusion 체크포인트](https://huggingface.co/CompVis/stable-diffusion-v1-4)를 사용하여 이미지를 생성합니다:
-
-```python
-seed = 0
-generator = torch.manual_seed(seed)
-
-images = sd_pipeline(prompts, num_images_per_prompt=1, generator=generator, output_type="np").images
-```
-
-그런 다음 [v1-5 checkpoint](https://huggingface.co/runwayml/stable-diffusion-v1-5)를 로드하여 이미지를 생성합니다:
-
-```python
-model_ckpt_1_5 = "runwayml/stable-diffusion-v1-5"
-sd_pipeline_1_5 = StableDiffusionPipeline.from_pretrained(model_ckpt_1_5, torch_dtype=weight_dtype).to(device)
-
-images_1_5 = sd_pipeline_1_5(prompts, num_images_per_prompt=1, generator=generator, output_type="np").images
-```
-
-그리고 마지막으로 CLIP 점수를 비교합니다:
-
-```python
-sd_clip_score_1_4 = calculate_clip_score(images, prompts)
-print(f"CLIP Score with v-1-4: {sd_clip_score_1_4}")
-# CLIP Score with v-1-4: 34.9102
-
-sd_clip_score_1_5 = calculate_clip_score(images_1_5, prompts)
-print(f"CLIP Score with v-1-5: {sd_clip_score_1_5}")
-# CLIP Score with v-1-5: 36.2137
-```
-
-[v1-5](https://huggingface.co/runwayml/stable-diffusion-v1-5) 체크포인트가 이전 버전보다 더 나은 성능을 보이는 것 같습니다. 그러나 CLIP 점수를 계산하기 위해 사용한 프롬프트의 수가 상당히 적습니다. 보다 실용적인 평가를 위해서는 이 수를 훨씬 높게 설정하고, 프롬프트를 다양하게 사용해야 합니다.
-
-<Tip warning={true}>
-
-이 점수에는 몇 가지 제한 사항이 있습니다. 훈련 데이터셋의 캡션은 웹에서 크롤링되어 이미지와 관련된 `alt` 및 유사한 태그에서 추출되었습니다. 이들은 인간이 이미지를 설명하는 데 사용할 수 있는 것과 일치하지 않을 수 있습니다. 따라서 여기서는 몇 가지 프롬프트를 "엔지니어링"해야 했습니다.
-
-</Tip>
-
-### 이미지 조건화된 텍스트-이미지 생성[[image-conditioned-text-to-image-generation]]
-
-이 경우, 생성 파이프라인을 입력 이미지와 텍스트 프롬프트로 조건화합니다. [`StableDiffusionInstructPix2PixPipeline`]을 예로 들어보겠습니다. 이는 편집 지시문을 입력 프롬프트로 사용하고 편집할 입력 이미지를 사용합니다.
-
-다음은 하나의 예시입니다:
-
-![edit-instruction](https://huggingface.co/datasets/diffusers/docs-images/resolve/main/evaluation_diffusion_models/edit-instruction.png)
-
-모델을 평가하는 한 가지 전략은 두 이미지 캡션 간의 변경과([CLIP-Guided Domain Adaptation of Image Generators](https://arxiv.org/abs/2108.00946)에서 보여줍니다) 함께 두 이미지 사이의 변경의 일관성을 측정하는 것입니다 ([CLIP](https://huggingface.co/docs/transformers/model_doc/clip) 공간에서). 이를 "**CLIP 방향성 유사성**"이라고 합니다.
-
-- 캡션 1은 편집할 이미지 (이미지 1)에 해당합니다.
-- 캡션 2는 편집된 이미지 (이미지 2)에 해당합니다. 편집 지시를 반영해야 합니다.
-
-다음은 그림으로 된 개요입니다:
-
-![edit-consistency](https://huggingface.co/datasets/diffusers/docs-images/resolve/main/evaluation_diffusion_models/edit-consistency.png)
-
-우리는 이 측정 항목을 구현하기 위해 미니 데이터 세트를 준비했습니다. 먼저 데이터 세트를 로드해 보겠습니다.
-
-```python
-from datasets import load_dataset
-
-dataset = load_dataset("sayakpaul/instructpix2pix-demo", split="train")
-dataset.features
-```
-
-```bash
-{'input': Value(dtype='string', id=None),
- 'edit': Value(dtype='string', id=None),
- 'output': Value(dtype='string', id=None),
- 'image': Image(decode=True, id=None)}
-```
-
-여기에는 다음과 같은 항목이 있습니다:
-
-- `input`은 `image`에 해당하는 캡션입니다.
-- `edit`은 편집 지시사항을 나타냅니다.
-- `output`은 `edit` 지시사항을 반영한 수정된 캡션입니다.
-
-샘플을 살펴보겠습니다.
-
-```python
-idx = 0
-print(f"Original caption: {dataset[idx]['input']}")
-print(f"Edit instruction: {dataset[idx]['edit']}")
-print(f"Modified caption: {dataset[idx]['output']}")
-```
-
-```bash
-Original caption: 2. FAROE ISLANDS: An archipelago of 18 mountainous isles in the North Atlantic Ocean between Norway and Iceland, the Faroe Islands has 'everything you could hope for', according to Big 7 Travel. It boasts 'crystal clear waterfalls, rocky cliffs that seem to jut out of nowhere and velvety green hills'
-Edit instruction: make the isles all white marble
-Modified caption: 2. WHITE MARBLE ISLANDS: An archipelago of 18 mountainous white marble isles in the North Atlantic Ocean between Norway and Iceland, the White Marble Islands has 'everything you could hope for', according to Big 7 Travel. It boasts 'crystal clear waterfalls, rocky cliffs that seem to jut out of nowhere and velvety green hills'
-```
-
-다음은 이미지입니다:
-
-```python
-dataset[idx]["image"]
-```
-
-![edit-dataset](https://huggingface.co/datasets/diffusers/docs-images/resolve/main/evaluation_diffusion_models/edit-dataset.png)
-
-먼저 편집 지시사항을 사용하여 데이터 세트의 이미지를 편집하고 방향 유사도를 계산합니다.
-
-[`StableDiffusionInstructPix2PixPipeline`]를 먼저 로드합니다:
-
-```python
-from diffusers import StableDiffusionInstructPix2PixPipeline
-
-instruct_pix2pix_pipeline = StableDiffusionInstructPix2PixPipeline.from_pretrained(
-    "timbrooks/instruct-pix2pix", torch_dtype=torch.float16
-).to(device)
-```
-
-이제 편집을 수행합니다:
-
-```python
-import numpy as np
-
-
-def edit_image(input_image, instruction):
-    image = instruct_pix2pix_pipeline(
-        instruction,
-        image=input_image,
-        output_type="np",
-        generator=generator,
-    ).images[0]
-    return image
-
-input_images = []
-original_captions = []
-modified_captions = []
-edited_images = []
-
-for idx in range(len(dataset)):
-    input_image = dataset[idx]["image"]
-    edit_instruction = dataset[idx]["edit"]
-    edited_image = edit_image(input_image, edit_instruction)
-
-    input_images.append(np.array(input_image))
-    original_captions.append(dataset[idx]["input"])
-    modified_captions.append(dataset[idx]["output"])
-    edited_images.append(edited_image)
-```
-방향 유사도를 계산하기 위해서는 먼저 CLIP의 이미지와 텍스트 인코더를 로드합니다:
-
-```python
-from transformers import (
-    CLIPTokenizer,
-    CLIPTextModelWithProjection,
-    CLIPVisionModelWithProjection,
-    CLIPImageProcessor,
-)
-
-clip_id = "openai/clip-vit-large-patch14"
-tokenizer = CLIPTokenizer.from_pretrained(clip_id)
-text_encoder = CLIPTextModelWithProjection.from_pretrained(clip_id).to(device)
-image_processor = CLIPImageProcessor.from_pretrained(clip_id)
-image_encoder = CLIPVisionModelWithProjection.from_pretrained(clip_id).to(device)
-```
-
-주목할 점은 특정한 CLIP 체크포인트인 `openai/clip-vit-large-patch14`를 사용하고 있다는 것입니다. 이는 Stable Diffusion 사전 훈련이 이 CLIP 변형체와 함께 수행되었기 때문입니다. 자세한 내용은 [문서](https://huggingface.co/docs/transformers/model_doc/clip)를 참조하세요.
-
-다음으로, 방향성 유사도를 계산하기 위해 PyTorch의 `nn.Module`을 준비합니다:
-
-```python
-import torch.nn as nn
-import torch.nn.functional as F
-
-
-class DirectionalSimilarity(nn.Module):
-    def __init__(self, tokenizer, text_encoder, image_processor, image_encoder):
-        super().__init__()
-        self.tokenizer = tokenizer
-        self.text_encoder = text_encoder
-        self.image_processor = image_processor
-        self.image_encoder = image_encoder
-
-    def preprocess_image(self, image):
-        image = self.image_processor(image, return_tensors="pt")["pixel_values"]
-        return {"pixel_values": image.to(device)}
-
-    def tokenize_text(self, text):
-        inputs = self.tokenizer(
-            text,
-            max_length=self.tokenizer.model_max_length,
-            padding="max_length",
-            truncation=True,
-            return_tensors="pt",
-        )
-        return {"input_ids": inputs.input_ids.to(device)}
-
-    def encode_image(self, image):
-        preprocessed_image = self.preprocess_image(image)
-        image_features = self.image_encoder(**preprocessed_image).image_embeds
-        image_features = image_features / image_features.norm(dim=1, keepdim=True)
-        return image_features
-
-    def encode_text(self, text):
-        tokenized_text = self.tokenize_text(text)
-        text_features = self.text_encoder(**tokenized_text).text_embeds
-        text_features = text_features / text_features.norm(dim=1, keepdim=True)
-        return text_features
-
-    def compute_directional_similarity(self, img_feat_one, img_feat_two, text_feat_one, text_feat_two):
-        sim_direction = F.cosine_similarity(img_feat_two - img_feat_one, text_feat_two - text_feat_one)
-        return sim_direction
-
-    def forward(self, image_one, image_two, caption_one, caption_two):
-        img_feat_one = self.encode_image(image_one)
-        img_feat_two = self.encode_image(image_two)
-        text_feat_one = self.encode_text(caption_one)
-        text_feat_two = self.encode_text(caption_two)
-        directional_similarity = self.compute_directional_similarity(
-            img_feat_one, img_feat_two, text_feat_one, text_feat_two
-        )
-        return directional_similarity
-```
-
-이제 `DirectionalSimilarity`를 사용해 보겠습니다.
-
-```python
-dir_similarity = DirectionalSimilarity(tokenizer, text_encoder, image_processor, image_encoder)
-scores = []
-
-for i in range(len(input_images)):
-    original_image = input_images[i]
-    original_caption = original_captions[i]
-    edited_image = edited_images[i]
-    modified_caption = modified_captions[i]
-
-    similarity_score = dir_similarity(original_image, edited_image, original_caption, modified_caption)
-    scores.append(float(similarity_score.detach().cpu()))
-
-print(f"CLIP directional similarity: {np.mean(scores)}")
-# CLIP directional similarity: 0.0797976553440094
-```
-
-CLIP 점수와 마찬가지로, CLIP 방향 유사성이 높을수록 좋습니다.
-
-`StableDiffusionInstructPix2PixPipeline`은 `image_guidance_scale`과 `guidance_scale`이라는 두 가지 인자를 노출시킵니다. 이 두 인자를 조정하여 최종 편집된 이미지의 품질을 제어할 수 있습니다. 이 두 인자의 영향을 실험해보고 방향 유사성에 미치는 영향을 확인해보기를 권장합니다.
-
-이러한 메트릭의 개념을 확장하여 원본 이미지와 편집된 버전의 유사성을 측정할 수 있습니다. 이를 위해 `F.cosine_similarity(img_feat_two, img_feat_one)`을 사용할 수 있습니다. 이러한 종류의 편집에서는 이미지의 주요 의미가 최대한 보존되어야 합니다. 즉, 높은 유사성 점수를 얻어야 합니다.
-
-[`StableDiffusionPix2PixZeroPipeline`](https://huggingface.co/docs/diffusers/main/en/api/pipelines/pix2pix_zero#diffusers.StableDiffusionPix2PixZeroPipeline)와 같은 유사한 파이프라인에도 이러한 메트릭을 사용할 수 있습니다.
-
-<Tip>
-
-CLIP 점수와 CLIP 방향 유사성 모두 CLIP 모델에 의존하기 때문에 평가가 편향될 수 있습니다
-
-</Tip>
-
-***IS, FID (나중에 설명할 예정), 또는 KID와 같은 메트릭을 확장하는 것은 어려울 수 있습니다***. 평가 중인 모델이 대규모 이미지 캡셔닝 데이터셋 (예: [LAION-5B 데이터셋](https://laion.ai/blog/laion-5b/))에서 사전 훈련되었을 때 이는 문제가 될 수 있습니다. 왜냐하면 이러한 메트릭의 기반에는 중간 이미지 특징을 추출하기 위해 ImageNet-1k 데이터셋에서 사전 훈련된 InceptionNet이 사용되기 때문입니다. Stable Diffusion의 사전 훈련 데이터셋은 InceptionNet의 사전 훈련 데이터셋과 겹치는 부분이 제한적일 수 있으므로 따라서 여기에는 좋은 후보가 아닙니다.
-
-***위의 메트릭을 사용하면 클래스 조건이 있는 모델을 평가할 수 있습니다. 예를 들어, [DiT](https://huggingface.co/docs/diffusers/main/en/api/pipelines/dit). 이는 ImageNet-1k 클래스에 조건을 걸고 사전 훈련되었습니다.***
-
-### 클래스 조건화 이미지 생성[[class-conditioned-image-generation]]
-
-클래스 조건화 생성 모델은 일반적으로 [ImageNet-1k](https://huggingface.co/datasets/imagenet-1k)와 같은 클래스 레이블이 지정된 데이터셋에서 사전 훈련됩니다. 이러한 모델을 평가하는 인기있는 지표에는 Fréchet Inception Distance (FID), Kernel Inception Distance (KID) 및 Inception Score (IS)가 있습니다. 이 문서에서는 FID ([Heusel et al.](https://arxiv.org/abs/1706.08500))에 초점을 맞추고 있습니다. [`DiTPipeline`](https://huggingface.co/docs/diffusers/api/pipelines/dit)을 사용하여 FID를 계산하는 방법을 보여줍니다. 이는 내부적으로 [DiT 모델](https://arxiv.org/abs/2212.09748)을 사용합니다.
-
-FID는 두 개의 이미지 데이터셋이 얼마나 유사한지를 측정하는 것을 목표로 합니다. [이 자료](https://mmgeneration.readthedocs.io/en/latest/quick_run.html#fid)에 따르면:
-
-> Fréchet Inception Distance는 두 개의 이미지 데이터셋 간의 유사성을 측정하는 지표입니다. 시각적 품질에 대한 인간 판단과 잘 상관되는 것으로 나타났으며, 주로 생성적 적대 신경망의 샘플 품질을 평가하는 데 사용됩니다. FID는 Inception 네트워크의 특징 표현에 맞게 적합한 두 개의 가우시안 사이의 Fréchet 거리를 계산하여 구합니다.
-
-이 두 개의 데이터셋은 실제 이미지 데이터셋과 가짜 이미지 데이터셋(우리의 경우 생성된 이미지)입니다. FID는 일반적으로 두 개의 큰 데이터셋으로 계산됩니다. 그러나 이 문서에서는 두 개의 미니 데이터셋으로 작업할 것입니다.
-
-먼저 ImageNet-1k 훈련 세트에서 몇 개의 이미지를 다운로드해 봅시다:
-
-```python
-from zipfile import ZipFile
-import requests
-
-
-def download(url, local_filepath):
-    r = requests.get(url)
-    with open(local_filepath, "wb") as f:
-        f.write(r.content)
-    return local_filepath
-
-dummy_dataset_url = "https://hf.co/datasets/sayakpaul/sample-datasets/resolve/main/sample-imagenet-images.zip"
-local_filepath = download(dummy_dataset_url, dummy_dataset_url.split("/")[-1])
-
-with ZipFile(local_filepath, "r") as zipper:
-    zipper.extractall(".")
-```
-
-```python
-from PIL import Image
-import os
-
-dataset_path = "sample-imagenet-images"
-image_paths = sorted([os.path.join(dataset_path, x) for x in os.listdir(dataset_path)])
-
-real_images = [np.array(Image.open(path).convert("RGB")) for path in image_paths]
-```
-
-다음은 ImageNet-1k classes의 이미지 10개입니다 : "cassette_player", "chain_saw" (x2), "church", "gas_pump" (x3), "parachute" (x2), 그리고 "tench".
-
-<p align="center">
-    <img src="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/evaluation_diffusion_models/real-images.png" alt="real-images"><br>
-    <em>Real images.</em>
-</p>
-
-이제 이미지가 로드되었으므로 이미지에 가벼운 전처리를 적용하여 FID 계산에 사용해 보겠습니다.
-
-```python
-from torchvision.transforms import functional as F
-
-
-def preprocess_image(image):
-    image = torch.tensor(image).unsqueeze(0)
-    image = image.permute(0, 3, 1, 2) / 255.0
-    return F.center_crop(image, (256, 256))
-
-real_images = torch.cat([preprocess_image(image) for image in real_images])
-print(real_images.shape)
-# torch.Size([10, 3, 256, 256])
-```
-
-이제 위에서 언급한 클래스에 따라 조건화 된 이미지를 생성하기 위해 [`DiTPipeline`](https://huggingface.co/docs/diffusers/api/pipelines/dit)를 로드합니다.
-
-```python
-from diffusers import DiTPipeline, DPMSolverMultistepScheduler
-
-dit_pipeline = DiTPipeline.from_pretrained("facebook/DiT-XL-2-256", torch_dtype=torch.float16)
-dit_pipeline.scheduler = DPMSolverMultistepScheduler.from_config(dit_pipeline.scheduler.config)
-dit_pipeline = dit_pipeline.to("cuda")
-
-words = [
-    "cassette player",
-    "chainsaw",
-    "chainsaw",
-    "church",
-    "gas pump",
-    "gas pump",
-    "gas pump",
-    "parachute",
-    "parachute",
-    "tench",
-]
-
-class_ids = dit_pipeline.get_label_ids(words)
-output = dit_pipeline(class_labels=class_ids, generator=generator, output_type="np")
-
-fake_images = output.images
-fake_images = torch.tensor(fake_images)
-fake_images = fake_images.permute(0, 3, 1, 2)
-print(fake_images.shape)
-# torch.Size([10, 3, 256, 256])
-```
-
-이제 [`torchmetrics`](https://torchmetrics.readthedocs.io/)를 사용하여 FID를 계산할 수 있습니다.
-
-```python
-from torchmetrics.image.fid import FrechetInceptionDistance
-
-fid = FrechetInceptionDistance(normalize=True)
-fid.update(real_images, real=True)
-fid.update(fake_images, real=False)
-
-print(f"FID: {float(fid.compute())}")
-# FID: 177.7147216796875
-```
-
-FID는 낮을수록 좋습니다. 여러 가지 요소가 FID에 영향을 줄 수 있습니다:
-
-- 이미지의 수 (실제 이미지와 가짜 이미지 모두)
-- diffusion 과정에서 발생하는 무작위성
-- diffusion 과정에서의 추론 단계 수
-- diffusion 과정에서 사용되는 스케줄러
-
-마지막 두 가지 요소에 대해서는, 다른 시드와 추론 단계에서 평가를 실행하고 평균 결과를 보고하는 것은 좋은 실천 방법입니다
-
-<Tip warning={true}>
-
-FID 결과는 많은 요소에 의존하기 때문에 취약할 수 있습니다:
-
-* 계산 중 사용되는 특정 Inception 모델.
-* 계산의 구현 정확도.
-* 이미지 형식 (PNG 또는 JPG에서 시작하는 경우가 다릅니다).
-
-이러한 사항을 염두에 두면, FID는 유사한 실행을 비교할 때 가장 유용하지만, 저자가 FID 측정 코드를 주의 깊게 공개하지 않는 한 논문 결과를 재현하기는 어렵습니다.
-
-이러한 사항은 KID 및 IS와 같은 다른 관련 메트릭에도 적용됩니다.
-
-</Tip>
-
-마지막 단계로, `fake_images`를 시각적으로 검사해 봅시다.
-
-<p align="center">
-    <img src="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/evaluation_diffusion_models/fake-images.png" alt="fake-images"><br>
-    <em>Fake images.</em>
-</p>