[don't merge] Test hfh v0.23.0.rc0

.github/ISSUE_TEMPLATE/bug-report.yml

@@ -57,50 +57,50 @@ body:
       description: |
         Your issue will be replied to more quickly if you can figure out the right person to tag with @.
         If you know how to use git blame, that is the easiest way, otherwise, here is a rough guide of **who to tag**.
-
+        
         All issues are read by one of the core maintainers, so if you don't know who to tag, just leave this blank and
         a core maintainer will ping the right person.
-
+        
         Please tag a maximum of 2 people.
 
         Questions on DiffusionPipeline (Saving, Loading, From pretrained, ...):
 
         Questions on pipelines:
-        - Stable Diffusion @yiyixuxu @DN6 @sayakpaul
-        - Stable Diffusion XL @yiyixuxu @sayakpaul @DN6
-        - Kandinsky @yiyixuxu
-        - ControlNet @sayakpaul @yiyixuxu @DN6
-        - T2I Adapter @sayakpaul @yiyixuxu @DN6
-        - IF @DN6
-        - Text-to-Video / Video-to-Video @DN6 @sayakpaul
-        - Wuerstchen @DN6
+        - Stable Diffusion @yiyixuxu @DN6 @sayakpaul 
+        - Stable Diffusion XL @yiyixuxu @sayakpaul @DN6 
+        - Kandinsky @yiyixuxu 
+        - ControlNet @sayakpaul @yiyixuxu @DN6 
+        - T2I Adapter @sayakpaul @yiyixuxu @DN6 
+        - IF @DN6 
+        - Text-to-Video / Video-to-Video @DN6 @sayakpaul 
+        - Wuerstchen @DN6 
         - Other: @yiyixuxu @DN6
 
         Questions on models:
-        - UNet @DN6 @yiyixuxu @sayakpaul
-        - VAE @sayakpaul @DN6 @yiyixuxu
-        - Transformers/Attention @DN6 @yiyixuxu @sayakpaul @DN6
+        - UNet @DN6 @yiyixuxu @sayakpaul 
+        - VAE @sayakpaul @DN6 @yiyixuxu 
+        - Transformers/Attention @DN6 @yiyixuxu @sayakpaul @DN6 
 
-        Questions on Schedulers: @yiyixuxu
+        Questions on Schedulers: @yiyixuxu 
 
-        Questions on LoRA: @sayakpaul
+        Questions on LoRA: @sayakpaul 
 
-        Questions on Textual Inversion: @sayakpaul
+        Questions on Textual Inversion: @sayakpaul 
 
-        Questions on Training:
-        - DreamBooth @sayakpaul
-        - Text-to-Image Fine-tuning @sayakpaul
-        - Textual Inversion @sayakpaul
-        - ControlNet @sayakpaul
+        Questions on Training: 
+        - DreamBooth @sayakpaul 
+        - Text-to-Image Fine-tuning @sayakpaul 
+        - Textual Inversion @sayakpaul 
+        - ControlNet @sayakpaul 
 
-        Questions on Tests: @DN6 @sayakpaul @yiyixuxu
+        Questions on Tests: @DN6 @sayakpaul @yiyixuxu 
 
         Questions on Documentation: @stevhliu
 
         Questions on JAX- and MPS-related things: @pcuenca
 
-        Questions on audio pipelines: @DN6
-
-
+        Questions on audio pipelines: @DN6 
+        
 
+        
       placeholder: "@Username ..."

.github/PULL_REQUEST_TEMPLATE.md

@@ -38,9 +38,9 @@ members/contributors who may be interested in your PR.
 
 Core library:
 
-- Schedulers: @yiyixuxu
+- Schedulers: @yiyixuxu 
 - Pipelines:  @sayakpaul @yiyixuxu @DN6
-- Training examples: @sayakpaul
+- Training examples: @sayakpaul 
 - Docs: @stevhliu and @sayakpaul
 - JAX and MPS: @pcuenca
 - Audio: @sanchit-gandhi

.github/workflows/benchmark.yml

@@ -39,7 +39,7 @@ jobs:
           python utils/print_env.py
       - name: Diffusers Benchmarking
         env:
-            HF_TOKEN: ${{ secrets.DIFFUSERS_BOT_TOKEN }}
+            HUGGING_FACE_HUB_TOKEN: ${{ secrets.DIFFUSERS_BOT_TOKEN }}
             BASE_PATH: benchmark_outputs
         run: |
           export TOTAL_GPU_MEMORY=$(python -c "import torch; print(torch.cuda.get_device_properties(0).total_memory / (1024**3))")

.github/workflows/build_docker_images.yml

@@ -25,17 +25,17 @@ jobs:
     steps:
       - name: Set up Docker Buildx
         uses: docker/setup-buildx-action@v1
-
+      
       - name: Check out code
         uses: actions/checkout@v3
-
+      
       - name: Find Changed Dockerfiles
         id: file_changes
         uses: jitterbit/get-changed-files@v1
         with:
           format: 'space-delimited'
           token: ${{ secrets.GITHUB_TOKEN }}
-
+      
       - name: Build Changed Docker Images
         run: |
           CHANGED_FILES="${{ steps.file_changes.outputs.all }}"
@@ -52,7 +52,7 @@ jobs:
   build-and-push-docker-images:
     runs-on: [ self-hosted, intel-cpu, 8-cpu, ci ]
     if: github.event_name != 'pull_request'
-
+    
     permissions:
       contents: read
       packages: write
@@ -69,7 +69,6 @@ jobs:
           - diffusers-flax-tpu
           - diffusers-onnxruntime-cpu
           - diffusers-onnxruntime-cuda
-          - diffusers-doc-builder
 
     steps:
       - name: Checkout repository
@@ -91,11 +90,24 @@ jobs:
 
       - name: Post to a Slack channel
         id: slack
-        uses: huggingface/hf-workflows/.github/actions/post-slack@main
+        uses: slackapi/slack-github-action@6c661ce58804a1a20f6dc5fbee7f0381b469e001
         with:
           # Slack channel id, channel name, or user id to post message.
           # See also: https://api.slack.com/methods/chat.postMessage#channels
-          slack_channel: ${{ env.CI_SLACK_CHANNEL }}
-          title: "🤗 Results of the ${{ matrix.image-name }} Docker Image build"
-          status: ${{ job.status }}
-          slack_token: ${{ secrets.SLACK_CIFEEDBACK_BOT_TOKEN }}
+          channel-id: ${{ env.CI_SLACK_CHANNEL }}
+          # For posting a rich message using Block Kit
+          payload: |
+            {
+              "text": "${{ matrix.image-name }} Docker Image build result: ${{ job.status }}\n${{ github.event.head_commit.url }}",
+              "blocks": [
+                {
+                  "type": "section",
+                  "text": {
+                    "type": "mrkdwn",
+                    "text": "${{ matrix.image-name }} Docker Image build result: ${{ job.status }}\n${{ github.event.head_commit.url }}"
+                  }
+                }
+              ]
+            }
+        env:
+          SLACK_BOT_TOKEN: ${{ secrets.SLACK_CIFEEDBACK_BOT_TOKEN }}

.github/workflows/build_documentation.yml

@@ -21,7 +21,7 @@ jobs:
       package: diffusers
       notebook_folder: diffusers_doc
       languages: en ko zh ja pt
-      custom_container: diffusers/diffusers-doc-builder
+
     secrets:
       token: ${{ secrets.HUGGINGFACE_PUSH }}
       hf_token: ${{ secrets.HF_DOC_BUILD_PUSH }}

.github/workflows/build_pr_documentation.yml

@@ -20,4 +20,3 @@ jobs:
       install_libgl1: true
       package: diffusers
       languages: en ko zh ja pt
-      custom_container: diffusers/diffusers-doc-builder

.github/workflows/mirror_community_pipeline.yml

@@ -1,89 +0,0 @@
-name: Mirror Community Pipeline
-
-on:
-  # Push changes on the main branch
-  push:
-    branches:
-      - main
-    paths:
-      - 'examples/community/**.py'
-
-    # And on tag creation (e.g. `v0.28.1`)
-    tags:
-      - '*'
-
-  # Manual trigger with ref input
-  workflow_dispatch:
-    inputs:
-      ref:
-        description: "Either 'main' or a tag ref"
-        required: true
-        default: 'main'
-
-jobs:
-  mirror_community_pipeline:
-    runs-on: ubuntu-latest
-    steps:
-      # Checkout to correct ref
-      #   If workflow dispatch
-      #     If ref is 'main', set:
-      #       CHECKOUT_REF=refs/heads/main
-      #       PATH_IN_REPO=main
-      #     Else it must be a tag. Set:
-      #       CHECKOUT_REF=refs/tags/{tag}
-      #       PATH_IN_REPO={tag}
-      #   If not workflow dispatch
-      #     If ref is 'refs/heads/main' => set 'main'
-      #     Else it must be a tag => set {tag}
-      - name: Set checkout_ref and path_in_repo
-        run: |
-          if [ "${{ github.event_name }}" == "workflow_dispatch" ]; then
-            if [ -z "${{ github.event.inputs.ref }}" ]; then
-              echo "Error: Missing ref input"
-              exit 1
-            elif [ "${{ github.event.inputs.ref }}" == "main" ]; then
-              echo "CHECKOUT_REF=refs/heads/main" >> $GITHUB_ENV
-              echo "PATH_IN_REPO=main" >> $GITHUB_ENV
-            else
-              echo "CHECKOUT_REF=refs/tags/${{ github.event.inputs.ref }}" >> $GITHUB_ENV
-              echo "PATH_IN_REPO=${{ github.event.inputs.ref }}" >> $GITHUB_ENV
-            fi
-          elif [ "${{ github.ref }}" == "refs/heads/main" ]; then
-            echo "CHECKOUT_REF=${{ github.ref }}" >> $GITHUB_ENV
-            echo "PATH_IN_REPO=main" >> $GITHUB_ENV
-          else
-            # e.g. refs/tags/v0.28.1 -> v0.28.1
-            echo "CHECKOUT_REF=${{ github.ref }}" >> $GITHUB_ENV
-            echo "PATH_IN_REPO=$(echo ${{ github.ref }} | sed 's/^refs\/tags\///')" >> $GITHUB_ENV
-          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 }}
-
-      # Setup + install dependencies
-      - name: Set up Python
-        uses: actions/setup-python@v4
-        with:
-          python-version: "3.10"
-      - name: Install dependencies
-        run: |
-          python -m pip install --upgrade pip
-          pip install --upgrade huggingface_hub
-
-      # Check secret is set
-      - name: whoami
-        run: huggingface-cli whoami
-        env:
-            HF_TOKEN: ${{ secrets.HF_TOKEN_MIRROR_COMMUNITY_PIPELINES }}
-
-      # Push to HF! (under subfolder based on checkout ref)
-      # https://huggingface.co/datasets/diffusers/community-pipelines-mirror
-      - name: Mirror community pipeline to HF
-        run: huggingface-cli upload diffusers/community-pipelines-mirror ./examples/community ${PATH_IN_REPO} --repo-type dataset
-        env:
-            PATH_IN_REPO: ${{ env.PATH_IN_REPO }}
-            HF_TOKEN: ${{ secrets.HF_TOKEN_MIRROR_COMMUNITY_PIPELINES }}

.github/workflows/nightly_tests.yml

@@ -19,7 +19,7 @@ env:
 jobs:
   setup_torch_cuda_pipeline_matrix:
     name: Setup Torch Pipelines Matrix
-    runs-on: diffusers/diffusers-pytorch-cpu
+    runs-on: ubuntu-latest
     outputs:
       pipeline_test_matrix: ${{ steps.fetch_pipeline_matrix.outputs.pipeline_test_matrix }}
     steps:
@@ -59,7 +59,7 @@ jobs:
     runs-on: [single-gpu, nvidia-gpu, t4, ci]
     container:
       image: diffusers/diffusers-pytorch-cuda
-      options: --shm-size "16gb" --ipc host -v /mnt/cache/.cache/huggingface/diffusers:/mnt/cache/ --gpus 0
+      options: --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/ --gpus 0
     steps:
       - name: Checkout diffusers
         uses: actions/checkout@v3
@@ -67,30 +67,30 @@ jobs:
           fetch-depth: 2
       - name: NVIDIA-SMI
         run: nvidia-smi
-
+      
       - name: Install dependencies
         run: |
           python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
           python -m uv pip install -e [quality,test]
           python -m uv pip install accelerate@git+https://github.com/huggingface/accelerate.git
           python -m uv pip install pytest-reportlog
-
+      
       - name: Environment
         run: |
           python utils/print_env.py
-
-      - name: Nightly PyTorch CUDA checkpoint (pipelines) tests
+      
+      - name: Nightly PyTorch CUDA checkpoint (pipelines) tests 
         env:
-          HF_TOKEN: ${{ secrets.HF_TOKEN }}
+          HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
           # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
           CUBLAS_WORKSPACE_CONFIG: :16:8
         run: |
           python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
             -s -v -k "not Flax and not Onnx" \
             --make-reports=tests_pipeline_${{ matrix.module }}_cuda \
-            --report-log=tests_pipeline_${{ matrix.module }}_cuda.log \
+            --report-log=tests_pipeline_${{ matrix.module }}_cuda.log \ 
             tests/pipelines/${{ matrix.module }}
-
+      
       - name: Failure short reports
         if: ${{ failure() }}
         run: |
@@ -103,7 +103,7 @@ jobs:
         with:
           name: pipeline_${{ matrix.module }}_test_reports
           path: reports
-
+      
       - name: Generate Report and Notify Channel
         if: always()
         run: |
@@ -112,7 +112,7 @@ jobs:
 
   run_nightly_tests_for_other_torch_modules:
     name: Torch Non-Pipelines CUDA Nightly Tests
-    runs-on: [single-gpu, nvidia-gpu, t4, ci]
+    runs-on: docker-gpu
     container:
       image: diffusers/diffusers-pytorch-cuda
       options: --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/ --gpus 0
@@ -139,35 +139,35 @@ jobs:
       run: python utils/print_env.py
 
     - name: Run nightly PyTorch CUDA tests for non-pipeline modules
-      if: ${{ matrix.module != 'examples'}}
+      if: ${{ matrix.module != 'examples'}} 
       env:
-        HF_TOKEN: ${{ secrets.HF_TOKEN }}
+        HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
         # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
         CUBLAS_WORKSPACE_CONFIG: :16:8
       run: |
         python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
           -s -v -k "not Flax and not Onnx" \
           --make-reports=tests_torch_${{ matrix.module }}_cuda \
-          --report-log=tests_torch_${{ matrix.module }}_cuda.log \
+          --report-log=tests_torch_${{ matrix.module }}_cuda.log \ 
           tests/${{ matrix.module }}
 
     - name: Run nightly example tests with Torch
       if: ${{ matrix.module == 'examples' }}
       env:
-        HF_TOKEN: ${{ secrets.HF_TOKEN }}
+        HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
         # 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 \
+          --report-log=examples_torch_cuda.log \ 
           examples/
 
     - name: Failure short reports
       if: ${{ failure() }}
       run: |
-        cat reports/tests_torch_${{ matrix.module }}_cuda_stats.txt
+        cat reports/tests_torch_${{ matrix.module }}_cuda_stats.txt 
         cat reports/tests_torch_${{ matrix.module }}_cuda_failures_short.txt
 
     - name: Test suite reports artifacts
@@ -185,7 +185,7 @@ jobs:
 
   run_lora_nightly_tests:
     name: Nightly LoRA Tests with PEFT and TORCH
-    runs-on: [single-gpu, nvidia-gpu, t4, ci]
+    runs-on: docker-gpu
     container:
       image: diffusers/diffusers-pytorch-cuda
       options: --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/ --gpus 0
@@ -211,20 +211,20 @@ jobs:
 
     - name: Run nightly LoRA tests with PEFT and Torch
       env:
-        HF_TOKEN: ${{ secrets.HF_TOKEN }}
+        HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_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 \
+          --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_stats.txt 
         cat reports/tests_torch_lora_cuda_failures_short.txt
 
     - name: Test suite reports artifacts
@@ -239,12 +239,12 @@ jobs:
       run: |
         pip install slack_sdk tabulate
         python scripts/log_reports.py >> $GITHUB_STEP_SUMMARY
-
+  
   run_flax_tpu_tests:
     name: Nightly Flax TPU Tests
     runs-on: docker-tpu
     if: github.event_name == 'schedule'
-
+    
     container:
       image: diffusers/diffusers-flax-tpu
       options: --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/ --privileged
@@ -269,12 +269,12 @@ jobs:
 
     - name: Run nightly Flax TPU tests
       env:
-        HF_TOKEN: ${{ secrets.HF_TOKEN }}
+        HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
       run: |
         python -m pytest -n 0 \
           -s -v -k "Flax" \
           --make-reports=tests_flax_tpu \
-          --report-log=tests_flax_tpu.log \
+          --report-log=tests_flax_tpu.log \ 
           tests/
 
     - name: Failure short reports
@@ -298,11 +298,11 @@ jobs:
 
   run_nightly_onnx_tests:
     name: Nightly ONNXRuntime CUDA tests on Ubuntu
-    runs-on: [single-gpu, nvidia-gpu, t4, ci]
+    runs-on: docker-gpu
     container:
       image: diffusers/diffusers-onnxruntime-cuda
       options: --gpus 0 --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/
-
+    
     steps:
     - name: Checkout diffusers
       uses: actions/checkout@v3
@@ -321,15 +321,15 @@ jobs:
 
     - name: Environment
       run: python utils/print_env.py
-
+    
     - name: Run nightly ONNXRuntime CUDA tests
       env:
-        HF_TOKEN: ${{ secrets.HF_TOKEN }}
+        HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
       run: |
         python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
           -s -v -k "Onnx" \
           --make-reports=tests_onnx_cuda \
-          --report-log=tests_onnx_cuda.log \
+          --report-log=tests_onnx_cuda.log \ 
           tests/
 
     - name: Failure short reports
@@ -344,7 +344,7 @@ jobs:
       with:
         name: ${{ matrix.config.report }}_test_reports
         path: reports
-
+    
     - name: Generate Report and Notify Channel
       if: always()
       run: |
@@ -390,7 +390,7 @@ jobs:
         shell: arch -arch arm64 bash {0}
         env:
           HF_HOME: /System/Volumes/Data/mnt/cache
-          HF_TOKEN: ${{ secrets.HF_TOKEN }}
+          HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
         run: |
           ${CONDA_RUN} python -m pytest -n 1 -s -v --make-reports=tests_torch_mps \
             --report-log=tests_torch_mps.log \

.github/workflows/notify_slack_about_release.yml

@@ -11,12 +11,12 @@ jobs:
 
     steps:
     - uses: actions/checkout@v3
-
+    
     - name: Setup Python
       uses: actions/setup-python@v4
       with:
         python-version: '3.8'
-
+    
     - name: Notify Slack about the release
       env:
         SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL }}

.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

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

.github/workflows/pr_test_peft_backend.yml

@@ -111,21 +111,3 @@ jobs:
           -s -v \
           --make-reports=tests_${{ matrix.config.report }} \
           tests/lora/
-        python -m pytest -n 4 --max-worker-restart=0 --dist=loadfile \
-          -s -v \
-          --make-reports=tests_models_lora_${{ matrix.config.report }} \
-          tests/models/ -k "lora"
-
-
-    - name: Failure short reports
-      if: ${{ failure() }}
-      run: |
-        cat reports/tests_${{ matrix.config.report }}_failures_short.txt
-        cat reports/tests_models_lora_${{ matrix.config.report }}_failures_short.txt
-
-    - name: Test suite reports artifacts
-      if: ${{ always() }}
-      uses: actions/upload-artifact@v2
-      with:
-        name: pr_${{ matrix.config.report }}_test_reports
-        path: reports

.github/workflows/pr_tests.yml

@@ -156,7 +156,7 @@ jobs:
       if: ${{ matrix.config.framework == 'pytorch_examples' }}
       run: |
         python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m uv pip install peft timm
+        python -m uv pip install peft
         python -m pytest -n 4 --max-worker-restart=0 --dist=loadfile \
           --make-reports=tests_${{ matrix.config.report }} \
           examples

.github/workflows/push_tests.yml

@@ -21,9 +21,7 @@ env:
 jobs:
   setup_torch_cuda_pipeline_matrix:
     name: Setup Torch Pipelines CUDA Slow Tests Matrix
-    runs-on: [ self-hosted, intel-cpu, 8-cpu, ci ]
-    container:
-      image: diffusers/diffusers-pytorch-cpu
+    runs-on: ubuntu-latest
     outputs:
       pipeline_test_matrix: ${{ steps.fetch_pipeline_matrix.outputs.pipeline_test_matrix }}
     steps:
@@ -31,13 +29,14 @@ jobs:
         uses: actions/checkout@v3
         with:
           fetch-depth: 2
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.8"
       - name: Install dependencies
         run: |
-          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-          python -m uv pip install -e [quality,test]
-      - name: Environment
-        run: |
-          python utils/print_env.py
+          pip install -e .
+          pip install huggingface_hub
       - name: Fetch Pipeline Matrix
         id: fetch_pipeline_matrix
         run: |
@@ -56,13 +55,12 @@ jobs:
     needs: setup_torch_cuda_pipeline_matrix
     strategy:
       fail-fast: false
-      max-parallel: 8
       matrix:
         module: ${{ fromJson(needs.setup_torch_cuda_pipeline_matrix.outputs.pipeline_test_matrix) }}
     runs-on: [single-gpu, nvidia-gpu, t4, ci]
     container:
       image: diffusers/diffusers-pytorch-cuda
-      options: --shm-size "16gb" --ipc host -v /mnt/cache/.cache/huggingface/diffusers:/mnt/cache/ --gpus 0
+      options: --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/ --gpus 0 --privileged
     steps:
       - name: Checkout diffusers
         uses: actions/checkout@v3
@@ -71,6 +69,12 @@ jobs:
       - name: NVIDIA-SMI
         run: |
           nvidia-smi
+      - name: Tailscale
+        uses: huggingface/tailscale-action@v1
+        with:
+          authkey: ${{ secrets.TAILSCALE_SSH_AUTHKEY }}
+          slackChannel: ${{ secrets.SLACK_CIFEEDBACK_CHANNEL }}
+          slackToken: ${{ secrets.SLACK_CIFEEDBACK_BOT_TOKEN }}
       - name: Install dependencies
         run: |
           python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
@@ -81,7 +85,7 @@ jobs:
           python utils/print_env.py
       - name: Slow PyTorch CUDA checkpoint tests on Ubuntu
         env:
-          HF_TOKEN: ${{ secrets.HF_TOKEN }}
+          HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
           # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
           CUBLAS_WORKSPACE_CONFIG: :16:8
         run: |
@@ -89,11 +93,18 @@ jobs:
             -s -v -k "not Flax and not Onnx" \
             --make-reports=tests_pipeline_${{ matrix.module }}_cuda \
             tests/pipelines/${{ matrix.module }}
+      - name: Tailscale Wait
+        if: ${{ failure() || runner.debug == '1' }}
+        uses: huggingface/tailscale-action@v1
+        with:
+           waitForSSH: true
+           authkey: ${{ secrets.TAILSCALE_SSH_AUTHKEY }}
       - 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
@@ -103,16 +114,16 @@ jobs:
 
   torch_cuda_tests:
     name: Torch CUDA Tests
-    runs-on: [single-gpu, nvidia-gpu, t4, ci]
+    runs-on: docker-gpu
     container:
       image: diffusers/diffusers-pytorch-cuda
-      options: --shm-size "16gb" --ipc host -v /mnt/cache/.cache/huggingface/diffusers:/mnt/cache/ --gpus 0
+      options: --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/ --gpus 0
     defaults:
       run:
         shell: bash
     strategy:
       matrix:
-        module: [models, schedulers, lora, others, single_file]
+        module: [models, schedulers, lora, others]
     steps:
     - name: Checkout diffusers
       uses: actions/checkout@v3
@@ -131,7 +142,7 @@ jobs:
 
     - name: Run slow PyTorch CUDA tests
       env:
-        HF_TOKEN: ${{ secrets.HF_TOKEN }}
+        HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
         # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
         CUBLAS_WORKSPACE_CONFIG: :16:8
       run: |
@@ -155,10 +166,10 @@ jobs:
 
   peft_cuda_tests:
     name: PEFT CUDA Tests
-    runs-on: [single-gpu, nvidia-gpu, t4, ci]
+    runs-on: docker-gpu
     container:
       image: diffusers/diffusers-pytorch-cuda
-      options: --shm-size "16gb" --ipc host -v /mnt/cache/.cache/huggingface/diffusers:/mnt/cache/ --gpus 0
+      options: --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/ --gpus 0
     defaults:
       run:
         shell: bash
@@ -181,7 +192,7 @@ jobs:
 
     - name: Run slow PEFT CUDA tests
       env:
-        HF_TOKEN: ${{ secrets.HF_TOKEN }}
+        HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
         # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
         CUBLAS_WORKSPACE_CONFIG: :16:8
       run: |
@@ -189,17 +200,12 @@ jobs:
           -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() }}
@@ -213,7 +219,7 @@ jobs:
     runs-on: docker-tpu
     container:
       image: diffusers/diffusers-flax-tpu
-      options: --shm-size "16gb" --ipc host -v /mnt/cache/.cache/huggingface:/mnt/cache/ --privileged
+      options: --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/ --privileged
     defaults:
       run:
         shell: bash
@@ -235,7 +241,7 @@ jobs:
 
     - name: Run slow Flax TPU tests
       env:
-        HF_TOKEN: ${{ secrets.HF_TOKEN }}
+        HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
       run: |
         python -m pytest -n 0 \
           -s -v -k "Flax" \
@@ -257,10 +263,10 @@ jobs:
 
   onnx_cuda_tests:
     name: ONNX CUDA Tests
-    runs-on: [single-gpu, nvidia-gpu, t4, ci]
+    runs-on: docker-gpu
     container:
       image: diffusers/diffusers-onnxruntime-cuda
-      options: --shm-size "16gb" --ipc host -v /mnt/cache/.cache/huggingface:/mnt/cache/ --gpus 0
+      options: --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/ --gpus 0
     defaults:
       run:
         shell: bash
@@ -282,7 +288,7 @@ jobs:
 
     - name: Run slow ONNXRuntime CUDA tests
       env:
-        HF_TOKEN: ${{ secrets.HF_TOKEN }}
+        HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
       run: |
         python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
           -s -v -k "Onnx" \
@@ -305,11 +311,11 @@ jobs:
   run_torch_compile_tests:
     name: PyTorch Compile CUDA tests
 
-    runs-on: [single-gpu, nvidia-gpu, t4, ci]
+    runs-on: docker-gpu
 
     container:
       image: diffusers/diffusers-pytorch-compile-cuda
-      options: --gpus 0 --shm-size "16gb" --ipc host -v /mnt/cache/.cache/huggingface:/mnt/cache/
+      options: --gpus 0 --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/
 
     steps:
     - name: Checkout diffusers
@@ -329,7 +335,7 @@ jobs:
         python utils/print_env.py
     - name: Run example tests on GPU
       env:
-        HF_TOKEN: ${{ secrets.HF_TOKEN }}
+        HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
       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
@@ -346,11 +352,11 @@ jobs:
   run_xformers_tests:
     name: PyTorch xformers CUDA tests
 
-    runs-on: [single-gpu, nvidia-gpu, t4, ci]
+    runs-on: docker-gpu
 
     container:
       image: diffusers/diffusers-pytorch-xformers-cuda
-      options: --gpus 0 --shm-size "16gb" --ipc host -v /mnt/cache/.cache/huggingface:/mnt/cache/
+      options: --gpus 0 --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/
 
     steps:
     - name: Checkout diffusers
@@ -370,7 +376,7 @@ jobs:
         python utils/print_env.py
     - name: Run example tests on GPU
       env:
-        HF_TOKEN: ${{ secrets.HF_TOKEN }}
+        HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
       run: |
         python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile -s -v -k "xformers" --make-reports=tests_torch_xformers_cuda tests/
     - name: Failure short reports
@@ -387,11 +393,11 @@ jobs:
   run_examples_tests:
     name: Examples PyTorch CUDA tests on Ubuntu
 
-    runs-on: [single-gpu, nvidia-gpu, t4, ci]
+    runs-on: docker-gpu
 
     container:
       image: diffusers/diffusers-pytorch-cuda
-      options: --gpus 0 --shm-size "16gb" --ipc host -v /mnt/cache/.cache/huggingface:/mnt/cache/
+      options: --gpus 0 --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/
 
     steps:
     - name: Checkout diffusers
@@ -415,10 +421,9 @@ jobs:
 
     - name: Run example tests on GPU
       env:
-        HF_TOKEN: ${{ secrets.HF_TOKEN }}
+        HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
       run: |
         python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m uv pip install timm
         python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile -s -v --make-reports=examples_torch_cuda examples/
 
     - name: Failure short reports

.github/workflows/push_tests_fast.yml

@@ -107,7 +107,7 @@ jobs:
       if: ${{ matrix.config.framework == 'pytorch_examples' }}
       run: |
         python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m uv pip install peft timm
+        python -m uv pip install peft
         python -m pytest -n 4 --max-worker-restart=0 --dist=loadfile \
           --make-reports=tests_${{ matrix.config.report }} \
           examples

.github/workflows/push_tests_mps.yml

@@ -23,7 +23,7 @@ concurrency:
 jobs:
   run_fast_tests_apple_m1:
     name: Fast PyTorch MPS tests on MacOS
-    runs-on: macos-13-xlarge
+    runs-on: [ self-hosted, apple-m1 ]
 
     steps:
     - name: Checkout diffusers
@@ -59,7 +59,7 @@ jobs:
       shell: arch -arch arm64 bash {0}
       env:
         HF_HOME: /System/Volumes/Data/mnt/cache
-        HF_TOKEN: ${{ secrets.HF_TOKEN }}
+        HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
       run: |
         ${CONDA_RUN} python -m pytest -n 0 -s -v --make-reports=tests_torch_mps tests/
 

.github/workflows/pypi_publish.yaml

@@ -29,7 +29,7 @@ jobs:
           LATEST_BRANCH=$(python utils/fetch_latest_release_branch.py)
           echo "Latest branch: $LATEST_BRANCH"
           echo "latest_branch=$LATEST_BRANCH" >> $GITHUB_ENV
-
+          
       - name: Set latest branch output
         id: set_latest_branch
         run: echo "::set-output name=latest_branch::${{ env.latest_branch }}"
@@ -43,27 +43,27 @@ jobs:
         uses: actions/checkout@v3
         with:
           ref: ${{ needs.find-and-checkout-latest-branch.outputs.latest_branch }}
-
+          
       - name: Setup Python
         uses: actions/setup-python@v4
         with:
           python-version: "3.8"
-
+      
       - name: Install dependencies
         run: |
           python -m pip install --upgrade pip
           pip install -U setuptools wheel twine
           pip install -U torch --index-url https://download.pytorch.org/whl/cpu
           pip install -U transformers
-
+      
       - name: Build the dist files
         run: python setup.py bdist_wheel && python setup.py sdist
-
+      
       - name: Publish to the test PyPI
         env:
           TWINE_USERNAME: ${{ secrets.TEST_PYPI_USERNAME }}
           TWINE_PASSWORD: ${{ secrets.TEST_PYPI_PASSWORD }}
-        run: twine upload dist/* -r pypitest --repository-url=https://test.pypi.org/legacy/
+        run: twine upload dist/* -r pypitest --repository-url=https://test.pypi.org/legacy/    
 
       - name: Test installing diffusers and importing
         run: |

.github/workflows/run_tests_from_a_pr.yml

@@ -1,73 +0,0 @@
-name: Check running SLOW tests from a PR (only GPU)
-
-on:
-  workflow_dispatch:
-    inputs:
-      docker_image:
-        default: 'diffusers/diffusers-pytorch-cuda'
-        description: 'Name of the Docker image'
-        required: true
-      branch:
-        description: 'PR Branch to test on'
-        required: true
-      test:
-        description: 'Tests to run (e.g.: `tests/models`).'
-        required: true
-
-env:
-  DIFFUSERS_IS_CI: yes
-  IS_GITHUB_CI: "1"
-  HF_HOME: /mnt/cache
-  OMP_NUM_THREADS: 8
-  MKL_NUM_THREADS: 8
-  PYTEST_TIMEOUT: 600
-  RUN_SLOW: yes
-
-jobs:
-  run_tests:
-    name: "Run a test on our runner from a PR"
-    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/
-
-    steps:
-      - name: Validate test files input
-        id: validate_test_files
-        env:
-          PY_TEST: ${{ github.event.inputs.test }}
-        run: |
-          if [[ ! "$PY_TEST" =~ ^tests/ ]]; then
-            echo "Error: The input string must start with 'tests/'."
-            exit 1
-          fi
-
-          if [[ ! "$PY_TEST" =~ ^tests/(models|pipelines) ]]; then
-            echo "Error: The input string must contain either 'models' or 'pipelines' after 'tests/'."
-            exit 1
-          fi
-
-          if [[ "$PY_TEST" == *";"* ]]; then
-            echo "Error: The input string must not contain ';'."
-            exit 1
-          fi
-          echo "$PY_TEST"
-
-      - name: Checkout PR branch
-        uses: actions/checkout@v4
-        with:
-          ref: ${{ github.event.inputs.branch }}
-          repository: ${{ github.event.pull_request.head.repo.full_name }}
-
-
-      - name: Install pytest
-        run: |
-          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-          python -m uv pip install -e [quality,test]
-          python -m uv pip install peft
-
-      - name: Run tests
-        env:
-            PY_TEST: ${{ github.event.inputs.test }}
-        run: |
-          pytest "$PY_TEST"

.github/workflows/ssh-runner.yml

@@ -25,7 +25,7 @@ jobs:
     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
+      options: --gpus all --privileged --ipc host -v /mnt/cache/.cache/huggingface:/mnt/cache/
 
     steps:
       - name: Checkout diffusers
@@ -38,7 +38,7 @@ jobs:
           nvidia-smi
 
       - name: Tailscale # In order to be able to SSH when a test fails
-        uses: huggingface/tailscale-action@main
+        uses: huggingface/tailscale-action@v1
         with:
           authkey: ${{ secrets.TAILSCALE_SSH_AUTHKEY }}
           slackChannel: ${{ secrets.SLACK_CIFEEDBACK_CHANNEL }}

.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

.github/workflows/update_metadata.yml

@@ -25,6 +25,6 @@ jobs:
 
       - name: Update metadata
         env:
-          HF_TOKEN: ${{ secrets.SAYAK_HF_TOKEN }}
+          HUGGING_FACE_HUB_TOKEN: ${{ secrets.SAYAK_HF_TOKEN }}
         run: |
           python utils/update_metadata.py --commit_sha ${{ github.sha }}

CONTRIBUTING.md

@@ -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).
@@ -356,7 +355,7 @@ 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/42f25d601a910dceadaee6c44345896b4cfa9928/setup.py#L270)):
+Follow these steps to start contributing ([supported Python versions](https://github.com/huggingface/diffusers/blob/main/setup.py#L265)):
 
 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
@@ -503,4 +502,4 @@ $ git push --set-upstream origin your-branch-for-syncing
 
 ### Style guide
 
-For documentation strings, 🧨 Diffusers follows the [Google style](https://google.github.io/styleguide/pyguide.html).
+For documentation strings, 🧨 Diffusers follows the [Google style](https://google.github.io/styleguide/pyguide.html).

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 25.000+ 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 22000+ 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
-- +11.000 other amazing GitHub repositories 💪
+- +9000 other amazing GitHub repositories 💪
 
 Thank you for using us ❤️.
 

docker/diffusers-doc-builder/Dockerfile

@@ -1,52 +0,0 @@
-FROM ubuntu:20.04
-LABEL maintainer="Hugging Face"
-LABEL repository="diffusers"
-
-ENV DEBIAN_FRONTEND=noninteractive
-
-RUN apt-get -y update \
-    && apt-get install -y software-properties-common \
-    && add-apt-repository ppa:deadsnakes/ppa
-
-RUN apt install -y bash \
-                   build-essential \
-                   git \
-                   git-lfs \
-                   curl \
-                   ca-certificates \
-                   libsndfile1-dev \
-                   python3.10 \
-                   python3-pip \
-                   libgl1 \
-                   zip \
-                   wget \
-                   python3.10-venv && \
-    rm -rf /var/lib/apt/lists
-
-# make sure to use venv
-RUN python3.10 -m venv /opt/venv
-ENV PATH="/opt/venv/bin:$PATH"
-
-# pre-install the heavy dependencies (these can later be overridden by the deps from setup.py)
-RUN python3.10 -m pip install --no-cache-dir --upgrade pip uv==0.1.11 && \
-    python3.10 -m uv pip install --no-cache-dir \
-        torch \
-        torchvision \
-        torchaudio \
-        invisible_watermark \
-        --extra-index-url https://download.pytorch.org/whl/cpu && \
-    python3.10 -m uv pip install --no-cache-dir \
-        accelerate \
-        datasets \
-        hf-doc-builder \
-        huggingface-hub \
-        Jinja2 \
-        librosa \
-        numpy==1.26.4 \
-        scipy \
-        tensorboard \
-        transformers \
-        matplotlib \
-        setuptools==69.5.1
-
-CMD ["/bin/bash"]

docker/diffusers-flax-cpu/Dockerfile

@@ -4,25 +4,22 @@ LABEL repository="diffusers"
 
 ENV DEBIAN_FRONTEND=noninteractive
 
-RUN apt-get -y update \
-    && apt-get install -y software-properties-common \
-    && add-apt-repository ppa:deadsnakes/ppa
-
-RUN apt install -y bash \
-        build-essential \
-        git \
-        git-lfs \
-        curl \
-        ca-certificates \
-        libsndfile1-dev \
-        libgl1 \
-        python3.10 \
-        python3-pip \
-        python3.10-venv && \
+RUN apt update && \
+    apt install -y bash \
+                   build-essential \
+                   git \
+                   git-lfs \
+                   curl \
+                   ca-certificates \
+                   libsndfile1-dev \
+                   libgl1 \
+                   python3.8 \
+                   python3-pip \
+                   python3.8-venv && \
     rm -rf /var/lib/apt/lists
 
 # make sure to use venv
-RUN python3.10 -m venv /opt/venv
+RUN python3 -m venv /opt/venv
 ENV PATH="/opt/venv/bin:$PATH"
 
 # pre-install the heavy dependencies (these can later be overridden by the deps from setup.py)
@@ -40,7 +37,7 @@ 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

@@ -4,11 +4,8 @@ LABEL repository="diffusers"
 
 ENV DEBIAN_FRONTEND=noninteractive
 
-RUN apt-get -y update \
-    && apt-get install -y software-properties-common \
-    && add-apt-repository ppa:deadsnakes/ppa
-
-RUN apt install -y bash \
+RUN apt update && \
+    apt install -y bash \
                    build-essential \
                    git \
                    git-lfs \
@@ -16,13 +13,13 @@ RUN apt install -y bash \
                    ca-certificates \
                    libsndfile1-dev \
                    libgl1 \
-                   python3.10 \
+                   python3.8 \
                    python3-pip \
-                   python3.10-venv && \
+                   python3.8-venv && \
     rm -rf /var/lib/apt/lists
 
 # make sure to use venv
-RUN python3.10 -m venv /opt/venv
+RUN python3 -m venv /opt/venv
 ENV PATH="/opt/venv/bin:$PATH"
 
 # pre-install the heavy dependencies (these can later be overridden by the deps from setup.py)
@@ -41,8 +38,8 @@ RUN python3 -m pip install --no-cache-dir --upgrade pip uv==0.1.11 && \
         hf-doc-builder \
         huggingface-hub \
         Jinja2 \
-        librosa \
-        numpy==1.26.4 \
+        librosa \        
+        numpy \
         scipy \
         tensorboard \
         transformers

docker/diffusers-onnxruntime-cpu/Dockerfile

@@ -4,11 +4,8 @@ LABEL repository="diffusers"
 
 ENV DEBIAN_FRONTEND=noninteractive
 
-RUN apt-get -y update \
-    && apt-get install -y software-properties-common \
-    && add-apt-repository ppa:deadsnakes/ppa
-
-RUN apt install -y bash \
+RUN apt update && \
+    apt install -y bash \
                    build-essential \
                    git \
                    git-lfs \
@@ -16,13 +13,13 @@ RUN apt install -y bash \
                    ca-certificates \
                    libsndfile1-dev \
                    libgl1 \
-                   python3.10 \
+                   python3.8 \
                    python3-pip \
-                   python3.10-venv && \
+                   python3.8-venv && \
     rm -rf /var/lib/apt/lists
 
 # make sure to use venv
-RUN python3.10 -m venv /opt/venv
+RUN python3 -m venv /opt/venv
 ENV PATH="/opt/venv/bin:$PATH"
 
 # pre-install the heavy dependencies (these can later be overridden by the deps from setup.py)
@@ -40,7 +37,7 @@ 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

@@ -4,11 +4,8 @@ LABEL repository="diffusers"
 
 ENV DEBIAN_FRONTEND=noninteractive
 
-RUN apt-get -y update \
-    && apt-get install -y software-properties-common \
-    && add-apt-repository ppa:deadsnakes/ppa
-
-RUN apt install -y bash \
+RUN apt update && \
+    apt install -y bash \
                    build-essential \
                    git \
                    git-lfs \
@@ -16,31 +13,31 @@ RUN apt install -y bash \
                    ca-certificates \
                    libsndfile1-dev \
                    libgl1 \
-                   python3.10 \
+                   python3.8 \
                    python3-pip \
-                   python3.10-venv && \
+                   python3.8-venv && \
     rm -rf /var/lib/apt/lists
 
 # make sure to use venv
-RUN python3.10 -m venv /opt/venv
+RUN python3 -m venv /opt/venv
 ENV PATH="/opt/venv/bin:$PATH"
 
 # pre-install the heavy dependencies (these can later be overridden by the deps from setup.py)
-RUN python3.10 -m pip install --no-cache-dir --upgrade pip uv==0.1.11 && \
-    python3.10 -m uv pip install --no-cache-dir \
+RUN python3 -m pip install --no-cache-dir --upgrade pip uv==0.1.11 && \
+    python3 -m uv pip install --no-cache-dir \
         torch \
         torchvision \
         torchaudio \
         "onnxruntime-gpu>=1.13.1" \
         --extra-index-url https://download.pytorch.org/whl/cu117 && \
-    python3.10 -m uv pip install --no-cache-dir \
+    python3 -m uv pip install --no-cache-dir \
         accelerate \
         datasets \
         hf-doc-builder \
         huggingface-hub \
         Jinja2 \
         librosa \
-        numpy==1.26.4 \
+        numpy \
         scipy \
         tensorboard \
         transformers

docker/diffusers-pytorch-compile-cuda/Dockerfile

@@ -4,11 +4,8 @@ LABEL repository="diffusers"
 
 ENV DEBIAN_FRONTEND=noninteractive
 
-RUN apt-get -y update \
-    && apt-get install -y software-properties-common \
-    && add-apt-repository ppa:deadsnakes/ppa
-
-RUN apt install -y bash \
+RUN apt update && \
+    apt install -y bash \
     build-essential \
     git \
     git-lfs \
@@ -16,30 +13,31 @@ RUN apt install -y bash \
     ca-certificates \
     libsndfile1-dev \
     libgl1 \
-    python3.10 \
+    python3.9 \
+    python3.9-dev \
     python3-pip \
-    python3.10-venv && \
+    python3.9-venv && \
     rm -rf /var/lib/apt/lists
 
 # make sure to use venv
-RUN python3.10 -m venv /opt/venv
+RUN python3.9 -m venv /opt/venv
 ENV PATH="/opt/venv/bin:$PATH"
 
 # pre-install the heavy dependencies (these can later be overridden by the deps from setup.py)
-RUN python3.10 -m pip install --no-cache-dir --upgrade pip uv==0.1.11 && \
-    python3.10 -m uv pip install --no-cache-dir \
+RUN python3.9 -m pip install --no-cache-dir --upgrade pip uv==0.1.11 && \
+    python3.9 -m uv pip install --no-cache-dir \
     torch \
     torchvision \
     torchaudio \
     invisible_watermark && \
-    python3.10 -m pip install --no-cache-dir \
+    python3.9 -m pip install --no-cache-dir \
     accelerate \
     datasets \
     hf-doc-builder \
     huggingface-hub \
     Jinja2 \
     librosa \
-    numpy==1.26.4 \
+    numpy \
     scipy \
     tensorboard \
     transformers

docker/diffusers-pytorch-cpu/Dockerfile

@@ -4,43 +4,40 @@ LABEL repository="diffusers"
 
 ENV DEBIAN_FRONTEND=noninteractive
 
-RUN apt-get -y update \
-    && apt-get install -y software-properties-common \
-    && add-apt-repository ppa:deadsnakes/ppa
-
-RUN apt install -y bash \
+RUN apt update && \
+    apt install -y bash \
                    build-essential \
                    git \
                    git-lfs \
                    curl \
                    ca-certificates \
                    libsndfile1-dev \
-                   python3.10 \
+                   python3.8 \
                    python3-pip \
                    libgl1 \
-                   python3.10-venv && \
+                   python3.8-venv && \
     rm -rf /var/lib/apt/lists
 
 # make sure to use venv
-RUN python3.10 -m venv /opt/venv
+RUN python3 -m venv /opt/venv
 ENV PATH="/opt/venv/bin:$PATH"
 
 # pre-install the heavy dependencies (these can later be overridden by the deps from setup.py)
-RUN python3.10 -m pip install --no-cache-dir --upgrade pip uv==0.1.11 && \
-    python3.10 -m uv pip install --no-cache-dir \
+RUN python3 -m pip install --no-cache-dir --upgrade pip uv==0.1.11 && \
+    python3 -m uv pip install --no-cache-dir \
         torch \
         torchvision \
         torchaudio \
         invisible_watermark \
         --extra-index-url https://download.pytorch.org/whl/cpu && \
-    python3.10 -m uv pip install --no-cache-dir \
+    python3 -m uv pip install --no-cache-dir \
         accelerate \
         datasets \
         hf-doc-builder \
         huggingface-hub \
         Jinja2 \
         librosa \
-        numpy==1.26.4 \
+        numpy \
         scipy \
         tensorboard \
         transformers matplotlib

docker/diffusers-pytorch-cuda/Dockerfile

@@ -4,11 +4,8 @@ LABEL repository="diffusers"
 
 ENV DEBIAN_FRONTEND=noninteractive
 
-RUN apt-get -y update \
-    && apt-get install -y software-properties-common \
-    && add-apt-repository ppa:deadsnakes/ppa
-
-RUN apt install -y bash \
+RUN apt update && \
+    apt install -y bash \
     build-essential \
     git \
     git-lfs \
@@ -16,30 +13,30 @@ RUN apt install -y bash \
     ca-certificates \
     libsndfile1-dev \
     libgl1 \
-    python3.10 \
+    python3.8 \
     python3-pip \
-    python3.10-venv && \
+    python3.8-venv && \
     rm -rf /var/lib/apt/lists
 
 # make sure to use venv
-RUN python3.10 -m venv /opt/venv
+RUN python3 -m venv /opt/venv
 ENV PATH="/opt/venv/bin:$PATH"
 
 # pre-install the heavy dependencies (these can later be overridden by the deps from setup.py)
-RUN python3.10 -m pip install --no-cache-dir --upgrade pip uv==0.1.11 && \
-    python3.10 -m uv pip install --no-cache-dir \
+RUN python3 -m pip install --no-cache-dir --upgrade pip uv==0.1.11 && \
+    python3 -m uv pip install --no-cache-dir \
     torch \
     torchvision \
     torchaudio \
     invisible_watermark && \
-    python3.10 -m pip install --no-cache-dir \
+    python3 -m pip install --no-cache-dir \
     accelerate \
     datasets \
     hf-doc-builder \
     huggingface-hub \
     Jinja2 \
     librosa \
-    numpy==1.26.4 \
+    numpy \
     scipy \
     tensorboard \
     transformers \

docker/diffusers-pytorch-xformers-cuda/Dockerfile

@@ -4,11 +4,8 @@ LABEL repository="diffusers"
 
 ENV DEBIAN_FRONTEND=noninteractive
 
-RUN apt-get -y update \
-    && apt-get install -y software-properties-common \
-    && add-apt-repository ppa:deadsnakes/ppa
-
-RUN apt install -y bash \
+RUN apt update && \
+    apt install -y bash \
                    build-essential \
                    git \
                    git-lfs \
@@ -16,30 +13,30 @@ RUN apt install -y bash \
                    ca-certificates \
                    libsndfile1-dev \
                    libgl1 \
-                   python3.10 \
+                   python3.8 \
                    python3-pip \
-                   python3.10-venv && \
+                   python3.8-venv && \
     rm -rf /var/lib/apt/lists
 
 # make sure to use venv
-RUN python3.10 -m venv /opt/venv
+RUN python3 -m venv /opt/venv
 ENV PATH="/opt/venv/bin:$PATH"
 
 # pre-install the heavy dependencies (these can later be overridden by the deps from setup.py)
-RUN python3.10 -m pip install --no-cache-dir --upgrade pip uv==0.1.11 && \
-    python3.10 -m pip install --no-cache-dir \
+RUN python3 -m pip install --no-cache-dir --upgrade pip uv==0.1.11 && \
+    python3 -m pip install --no-cache-dir \
         torch \
         torchvision \
         torchaudio \
         invisible_watermark && \
-    python3.10 -m uv pip install --no-cache-dir \
+    python3 -m uv pip install --no-cache-dir \
         accelerate \
         datasets \
         hf-doc-builder \
         huggingface-hub \
         Jinja2 \
         librosa \
-        numpy==1.26.4 \
+        numpy \
         scipy \
         tensorboard \
         transformers \

docs/README.md

@@ -242,10 +242,10 @@ Here's an example of a tuple return, comprising several objects:
 
 ```
     Returns:
-        `tuple(torch.Tensor)` comprising various elements depending on the configuration ([`BertConfig`]) and inputs:
-        - ** loss** (*optional*, returned when `masked_lm_labels` is provided) `torch.Tensor` of shape `(1,)` --
+        `tuple(torch.FloatTensor)` comprising various elements depending on the configuration ([`BertConfig`]) and inputs:
+        - ** loss** (*optional*, returned when `masked_lm_labels` is provided) `torch.FloatTensor` of shape `(1,)` --
           Total loss is the sum of the masked language modeling loss and the next sequence prediction (classification) loss.
-        - **prediction_scores** (`torch.Tensor` of shape `(batch_size, sequence_length, config.vocab_size)`) --
+        - **prediction_scores** (`torch.FloatTensor` of shape `(batch_size, sequence_length, config.vocab_size)`) --
           Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax).
 ```
 

docs/source/en/_toctree.yml

@@ -29,8 +29,10 @@
     title: Load community pipelines and components
   - local: using-diffusers/schedulers
     title: Load schedulers and models
+  - local: using-diffusers/using_safetensors
+    title: Load safetensors
   - local: using-diffusers/other-formats
-    title: Model files and layouts
+    title: Load different Stable Diffusion formats
   - local: using-diffusers/loading_adapters
     title: Load adapters
   - local: using-diffusers/push_to_hub
@@ -57,8 +59,6 @@
     title: Distributed inference with multiple GPUs
   - local: using-diffusers/merge_loras
     title: Merge LoRAs
-  - local: using-diffusers/scheduler_features
-    title: Scheduler features
   - local: using-diffusers/callback
     title: Pipeline callbacks
   - local: using-diffusers/reusing_seeds
@@ -68,10 +68,6 @@
   - local: using-diffusers/weighted_prompts
     title: Prompt techniques
   title: Inference techniques
-- sections:
-  - local: advanced_inference/outpaint
-    title: Outpainting
-  title: Advanced inference
 - sections:
   - local: using-diffusers/sdxl
     title: Stable Diffusion XL
@@ -85,20 +81,24 @@
     title: ControlNet
   - local: using-diffusers/t2i_adapter
     title: T2I-Adapter
-  - local: using-diffusers/inference_with_lcm
-    title: Latent Consistency Model
   - local: using-diffusers/textual_inversion_inference
     title: Textual inversion
   - local: using-diffusers/shap-e
     title: Shap-E
   - local: using-diffusers/diffedit
     title: DiffEdit
+  - local: using-diffusers/custom_pipeline_examples
+    title: Community pipelines
+  - local: using-diffusers/contribute_pipeline
+    title: Contribute a community pipeline
+  - local: using-diffusers/inference_with_lcm_lora
+    title: Latent Consistency Model-LoRA
+  - local: using-diffusers/inference_with_lcm
+    title: Latent Consistency Model
   - local: using-diffusers/inference_with_tcd_lora
     title: Trajectory Consistency Distillation-LoRA
   - local: using-diffusers/svd
     title: Stable Video Diffusion
-  - local: using-diffusers/marigold_usage
-    title: Marigold Computer Vision
   title: Specific pipeline examples
 - sections:
   - local: training/overview
@@ -107,8 +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
@@ -126,8 +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
@@ -141,10 +140,13 @@
     - local: training/ddpo
       title: Reinforcement learning training with DDPO
     title: Methods
+    isExpanded: false
   title: Training
 - sections:
   - local: optimization/fp16
     title: Speed up inference
+  - local: using-diffusers/distilled_sd
+    title: Distilled Stable Diffusion inference
   - local: optimization/memory
     title: Reduce memory usage
   - local: optimization/torch2.0
@@ -187,8 +189,7 @@
     title: Evaluating Diffusion Models
   title: Conceptual Guides
 - sections:
-  - isExpanded: false
-    sections:
+  - sections:
     - local: api/configuration
       title: Configuration
     - local: api/logging
@@ -196,8 +197,8 @@
     - 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
@@ -211,8 +212,8 @@
     - local: api/loaders/peft
       title: PEFT
     title: Loaders
-  - isExpanded: false
-    sections:
+    isExpanded: false
+  - sections:
     - local: api/models/overview
       title: Overview
     - local: api/models/unet
@@ -238,26 +239,16 @@
     - local: api/models/consistency_decoder_vae
       title: ConsistencyDecoderVAE
     - local: api/models/transformer2d
-      title: Transformer2DModel
-    - local: api/models/pixart_transformer2d
-      title: PixArtTransformer2DModel
-    - local: api/models/dit_transformer2d
-      title: DiTTransformer2DModel
-    - local: api/models/hunyuan_transformer2d
-      title: HunyuanDiT2DModel
+      title: Transformer2D
     - local: api/models/transformer_temporal
-      title: TransformerTemporalModel
-    - local: api/models/sd3_transformer2d
-      title: SD3Transformer2DModel
+      title: Transformer Temporal
     - local: api/models/prior_transformer
-      title: PriorTransformer
+      title: Prior Transformer
     - local: api/models/controlnet
-      title: ControlNetModel
-    - local: api/models/controlnet_sd3
-      title: SD3ControlNetModel
+      title: ControlNet
     title: Models
-  - isExpanded: false
-    sections:
+    isExpanded: false
+  - sections:
     - local: api/pipelines/overview
       title: Overview
     - local: api/pipelines/amused
@@ -278,8 +269,6 @@
       title: Consistency Models
     - local: api/pipelines/controlnet
       title: ControlNet
-    - 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
@@ -298,8 +287,6 @@
       title: DiffEdit
     - local: api/pipelines/dit
       title: DiT
-    - local: api/pipelines/hunyuandit
-      title: Hunyuan-DiT
     - local: api/pipelines/i2vgenxl
       title: I2VGen-XL
     - local: api/pipelines/pix2pix
@@ -316,8 +303,6 @@
       title: Latent Diffusion
     - local: api/pipelines/ledits_pp
       title: LEDITS++
-    - local: api/pipelines/marigold
-      title: Marigold
     - local: api/pipelines/panorama
       title: MultiDiffusion
     - local: api/pipelines/musicldm
@@ -328,8 +313,6 @@
       title: Personalized Image Animator (PIA)
     - local: api/pipelines/pixart
       title: PixArt-α
-    - local: api/pipelines/pixart_sigma
-      title: PixArt-Σ
     - local: api/pipelines/self_attention_guidance
       title: Self-Attention Guidance
     - local: api/pipelines/semantic_stable_diffusion
@@ -357,8 +340,6 @@
         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
@@ -391,8 +372,8 @@
     - 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
@@ -423,8 +404,6 @@
       title: EulerAncestralDiscreteScheduler
     - local: api/schedulers/euler
       title: EulerDiscreteScheduler
-    - local: api/schedulers/flow_match_euler_discrete
-      title: FlowMatchEulerDiscreteScheduler
     - local: api/schedulers/heun
       title: HeunDiscreteScheduler
     - local: api/schedulers/ipndm
@@ -454,8 +433,8 @@
     - 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
@@ -468,7 +447,6 @@
       title: Utilities
     - local: api/image_processor
       title: VAE Image Processor
-    - local: api/video_processor
-      title: Video Processor
     title: Internal classes
+    isExpanded: false
   title: API

docs/source/en/advanced_inference/outpaint.md

@@ -1,231 +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.
--->
-
-# Outpainting
-
-Outpainting extends an image beyond its original boundaries, allowing you to add, replace, or modify visual elements in an image while preserving the original image. Like [inpainting](../using-diffusers/inpaint), you want to fill the white area (in this case, the area outside of the original image) with new visual elements while keeping the original image (represented by a mask of black pixels). There are a couple of ways to outpaint, such as with a [ControlNet](https://hf.co/blog/OzzyGT/outpainting-controlnet) or with [Differential Diffusion](https://hf.co/blog/OzzyGT/outpainting-differential-diffusion).
-
-This guide will show you how to outpaint with an inpainting model, ControlNet, and a ZoeDepth estimator.
-
-Before you begin, make sure you have the [controlnet_aux](https://github.com/huggingface/controlnet_aux) library installed so you can use the ZoeDepth estimator.
-
-```py
-!pip install -q controlnet_aux
-```
-
-## Image preparation
-
-Start by picking an image to outpaint with and remove the background with a Space like [BRIA-RMBG-1.4](https://hf.co/spaces/briaai/BRIA-RMBG-1.4).
-
-<iframe
-	src="https://briaai-bria-rmbg-1-4.hf.space"
-	frameborder="0"
-	width="850"
-	height="450"
-></iframe>
-
-For example, remove the background from this image of a pair of shoes.
-
-<div class="flex flex-row gap-4">
-  <div class="flex-1">
-    <img class="rounded-xl" src="https://huggingface.co/datasets/stevhliu/testing-images/resolve/main/original-jordan.png"/>
-    <figcaption class="mt-2 text-center text-sm text-gray-500">original image</figcaption>
-  </div>
-  <div class="flex-1">
-    <img class="rounded-xl" src="https://huggingface.co/datasets/stevhliu/testing-images/resolve/main/no-background-jordan.png"/>
-    <figcaption class="mt-2 text-center text-sm text-gray-500">background removed</figcaption>
-  </div>
-</div>
-
-[Stable Diffusion XL (SDXL)](../using-diffusers/sdxl) models work best with 1024x1024 images, but you can resize the image to any size as long as your hardware has enough memory to support it. The transparent background in the image should also be replaced with a white background. Create a function (like the one below) that scales and pastes the image onto a white background.
-
-```py
-import random
-
-import requests
-import torch
-from controlnet_aux import ZoeDetector
-from PIL import Image, ImageOps
-
-from diffusers import (
-    AutoencoderKL,
-    ControlNetModel,
-    StableDiffusionXLControlNetPipeline,
-    StableDiffusionXLInpaintPipeline,
-)
-
-def scale_and_paste(original_image):
-    aspect_ratio = original_image.width / original_image.height
-
-    if original_image.width > original_image.height:
-        new_width = 1024
-        new_height = round(new_width / aspect_ratio)
-    else:
-        new_height = 1024
-        new_width = round(new_height * aspect_ratio)
-
-    resized_original = original_image.resize((new_width, new_height), Image.LANCZOS)
-    white_background = Image.new("RGBA", (1024, 1024), "white")
-    x = (1024 - new_width) // 2
-    y = (1024 - new_height) // 2
-    white_background.paste(resized_original, (x, y), resized_original)
-
-    return resized_original, white_background
-
-original_image = Image.open(
-    requests.get(
-        "https://huggingface.co/datasets/stevhliu/testing-images/resolve/main/no-background-jordan.png",
-        stream=True,
-    ).raw
-).convert("RGBA")
-resized_img, white_bg_image = scale_and_paste(original_image)
-```
-
-To avoid adding unwanted extra details, use the ZoeDepth estimator to provide additional guidance during generation and to ensure the shoes remain consistent with the original image.
-
-```py
-zoe = ZoeDetector.from_pretrained("lllyasviel/Annotators")
-image_zoe = zoe(white_bg_image, detect_resolution=512, image_resolution=1024)
-image_zoe
-```
-
-<div class="flex justify-center">
-    <img src="https://huggingface.co/datasets/stevhliu/testing-images/resolve/main/zoedepth-jordan.png"/>
-</div>
-
-## Outpaint
-
-Once your image is ready, you can generate content in the white area around the shoes with [controlnet-inpaint-dreamer-sdxl](https://hf.co/destitech/controlnet-inpaint-dreamer-sdxl), a SDXL ControlNet trained for inpainting.
-
-Load the inpainting ControlNet, ZoeDepth model, VAE and pass them to the [`StableDiffusionXLControlNetPipeline`]. Then you can create an optional `generate_image` function (for convenience) to outpaint an initial image.
-
-```py
-controlnets = [
-    ControlNetModel.from_pretrained(
-        "destitech/controlnet-inpaint-dreamer-sdxl", torch_dtype=torch.float16, variant="fp16"
-    ),
-    ControlNetModel.from_pretrained(
-        "diffusers/controlnet-zoe-depth-sdxl-1.0", torch_dtype=torch.float16
-    ),
-]
-vae = AutoencoderKL.from_pretrained("madebyollin/sdxl-vae-fp16-fix", torch_dtype=torch.float16).to("cuda")
-pipeline = StableDiffusionXLControlNetPipeline.from_pretrained(
-    "SG161222/RealVisXL_V4.0", torch_dtype=torch.float16, variant="fp16", controlnet=controlnets, vae=vae
-).to("cuda")
-
-def generate_image(prompt, negative_prompt, inpaint_image, zoe_image, seed: int = None):
-    if seed is None:
-        seed = random.randint(0, 2**32 - 1)
-
-    generator = torch.Generator(device="cpu").manual_seed(seed)
-
-    image = pipeline(
-        prompt,
-        negative_prompt=negative_prompt,
-        image=[inpaint_image, zoe_image],
-        guidance_scale=6.5,
-        num_inference_steps=25,
-        generator=generator,
-        controlnet_conditioning_scale=[0.5, 0.8],
-        control_guidance_end=[0.9, 0.6],
-    ).images[0]
-
-    return image
-
-prompt = "nike air jordans on a basketball court"
-negative_prompt = ""
-
-temp_image = generate_image(prompt, negative_prompt, white_bg_image, image_zoe, 908097)
-```
-
-Paste the original image over the initial outpainted image. You'll improve the outpainted background in a later step.
-
-```py
-x = (1024 - resized_img.width) // 2
-y = (1024 - resized_img.height) // 2
-temp_image.paste(resized_img, (x, y), resized_img)
-temp_image
-```
-
-<div class="flex justify-center">
-    <img src="https://huggingface.co/datasets/stevhliu/testing-images/resolve/main/initial-outpaint.png"/>
-</div>
-
-> [!TIP]
-> Now is a good time to free up some memory if you're running low!
->
-> ```py
-> pipeline=None
-> torch.cuda.empty_cache()
-> ```
-
-Now that you have an initial outpainted image, load the [`StableDiffusionXLInpaintPipeline`] with the [RealVisXL](https://hf.co/SG161222/RealVisXL_V4.0) model to generate the final outpainted image with better quality.
-
-```py
-pipeline = StableDiffusionXLInpaintPipeline.from_pretrained(
-    "OzzyGT/RealVisXL_V4.0_inpainting",
-    torch_dtype=torch.float16,
-    variant="fp16",
-    vae=vae,
-).to("cuda")
-```
-
-Prepare a mask for the final outpainted image. To create a more natural transition between the original image and the outpainted background, blur the mask to help it blend better.
-
-```py
-mask = Image.new("L", temp_image.size)
-mask.paste(resized_img.split()[3], (x, y))
-mask = ImageOps.invert(mask)
-final_mask = mask.point(lambda p: p > 128 and 255)
-mask_blurred = pipeline.mask_processor.blur(final_mask, blur_factor=20)
-mask_blurred
-```
-
-<div class="flex justify-center">
-    <img src="https://huggingface.co/datasets/stevhliu/testing-images/resolve/main/blurred-mask.png"/>
-</div>
-
-Create a better prompt and pass it to the `generate_outpaint` function to generate the final outpainted image. Again, paste the original image over the final outpainted background.
-
-```py
-def generate_outpaint(prompt, negative_prompt, image, mask, seed: int = None):
-    if seed is None:
-        seed = random.randint(0, 2**32 - 1)
-
-    generator = torch.Generator(device="cpu").manual_seed(seed)
-
-    image = pipeline(
-        prompt,
-        negative_prompt=negative_prompt,
-        image=image,
-        mask_image=mask,
-        guidance_scale=10.0,
-        strength=0.8,
-        num_inference_steps=30,
-        generator=generator,
-    ).images[0]
-
-    return image
-
-prompt = "high quality photo of nike air jordans on a basketball court, highly detailed"
-negative_prompt = ""
-
-final_image = generate_outpaint(prompt, negative_prompt, temp_image, mask_blurred, 7688778)
-x = (1024 - resized_img.width) // 2
-y = (1024 - resized_img.height) // 2
-final_image.paste(resized_img, (x, y), resized_img)
-final_image
-```
-
-<div class="flex justify-center">
-    <img src="https://huggingface.co/datasets/stevhliu/testing-images/resolve/main/final-outpaint.png"/>
-</div>

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
 
@@ -49,6 +55,3 @@ An attention processor is a class for applying different types of attention mech
 
 ## XFormersAttnProcessor
 [[autodoc]] models.attention_processor.XFormersAttnProcessor
-
-## AttnProcessorNPU
-[[autodoc]] models.attention_processor.AttnProcessorNPU

docs/source/en/api/image_processor.md

@@ -25,11 +25,3 @@ All pipelines with [`VaeImageProcessor`] accept PIL Image, PyTorch tensor, or Nu
 The [`VaeImageProcessorLDM3D`] accepts RGB and depth inputs and returns RGB and depth outputs.
 
 [[autodoc]] image_processor.VaeImageProcessorLDM3D
-
-## PixArtImageProcessor
-
-[[autodoc]] image_processor.PixArtImageProcessor
-
-## IPAdapterMaskProcessor
-
-[[autodoc]] image_processor.IPAdapterMaskProcessor

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

@@ -12,50 +12,26 @@ specific language governing permissions and limitations under the License.
 
 # Single files
 
-The [`~loaders.FromSingleFileMixin.from_single_file`] method allows you to load:
+Diffusers supports loading pretrained pipeline (or model) weights stored in a single file, such as a `ckpt` or `safetensors` file. These single file types are typically produced from community trained models. There are three classes for loading single file weights:
 
-* a model stored in a single file, which is useful if you're working with models from the diffusion ecosystem, like Automatic1111, and commonly rely on a single-file layout to store and share models
-* a model stored in their originally distributed layout, which is useful if you're working with models finetuned with other services, and want to load it directly into Diffusers model objects and pipelines
+- [`FromSingleFileMixin`] supports loading pretrained pipeline weights stored in a single file, which can either be a `ckpt` or `safetensors` file.
+- [`FromOriginalVAEMixin`] supports loading a pretrained [`AutoencoderKL`] from pretrained ControlNet weights stored in a single file, which can either be a `ckpt` or `safetensors` file.
+- [`FromOriginalControlnetMixin`] supports loading pretrained ControlNet weights stored in a single file, which can either be a `ckpt` or `safetensors` file.
 
-> [!TIP]
-> Read the [Model files and layouts](../../using-diffusers/other-formats) guide to learn more about the Diffusers-multifolder layout versus the single-file layout, and how to load models stored in these different layouts.
+<Tip>
 
-## Supported pipelines
+To learn more about how to load single file weights, see the [Load different Stable Diffusion formats](../../using-diffusers/other-formats) loading guide.
 
-- [`StableDiffusionPipeline`]
-- [`StableDiffusionImg2ImgPipeline`]
-- [`StableDiffusionInpaintPipeline`]
-- [`StableDiffusionControlNetPipeline`]
-- [`StableDiffusionControlNetImg2ImgPipeline`]
-- [`StableDiffusionControlNetInpaintPipeline`]
-- [`StableDiffusionUpscalePipeline`]
-- [`StableDiffusionXLPipeline`]
-- [`StableDiffusionXLImg2ImgPipeline`]
-- [`StableDiffusionXLInpaintPipeline`]
-- [`StableDiffusionXLInstructPix2PixPipeline`]
-- [`StableDiffusionXLControlNetPipeline`]
-- [`StableDiffusionXLKDiffusionPipeline`]
-- [`StableDiffusion3Pipeline`]
-- [`LatentConsistencyModelPipeline`]
-- [`LatentConsistencyModelImg2ImgPipeline`]
-- [`StableDiffusionControlNetXSPipeline`]
-- [`StableDiffusionXLControlNetXSPipeline`]
-- [`LEditsPPPipelineStableDiffusion`]
-- [`LEditsPPPipelineStableDiffusionXL`]
-- [`PIAPipeline`]
-
-## Supported models
-
-- [`UNet2DConditionModel`]
-- [`StableCascadeUNet`]
-- [`AutoencoderKL`]
-- [`ControlNetModel`]
-- [`SD3Transformer2DModel`]
+</Tip>
 
 ## FromSingleFileMixin
 
 [[autodoc]] loaders.single_file.FromSingleFileMixin
 
-## FromOriginalModelMixin
+## FromOriginalVAEMixin
 
-[[autodoc]] loaders.single_file_model.FromOriginalModelMixin
+[[autodoc]] loaders.autoencoder.FromOriginalVAEMixin
+
+## FromOriginalControlnetMixin
+
+[[autodoc]] loaders.controlnet.FromOriginalControlNetMixin

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

@@ -10,7 +10,7 @@ an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express o
 specific language governing permissions and limitations under the License.
 -->
 
-# ControlNetModel
+# ControlNet
 
 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.
 

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/dit_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.
--->
-
-# DiTTransformer2DModel
-
-A Transformer model for image-like data from [DiT](https://huggingface.co/papers/2212.09748).
-
-## DiTTransformer2DModel
-
-[[autodoc]] DiTTransformer2DModel

docs/source/en/api/models/hunyuan_transformer2d.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.
--->
-
-# HunyuanDiT2DModel
-
-A Diffusion Transformer model for 2D data from [Hunyuan-DiT](https://github.com/Tencent/HunyuanDiT).
-
-## HunyuanDiT2DModel
-
-[[autodoc]] HunyuanDiT2DModel
-

docs/source/en/api/models/pixart_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.
--->
-
-# PixArtTransformer2DModel
-
-A Transformer model for image-like data from [PixArt-Alpha](https://huggingface.co/papers/2310.00426) and [PixArt-Sigma](https://huggingface.co/papers/2403.04692).
-
-## PixArtTransformer2DModel
-
-[[autodoc]] PixArtTransformer2DModel

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

@@ -10,7 +10,7 @@ an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express o
 specific language governing permissions and limitations under the License.
 -->
 
-# PriorTransformer
+# Prior Transformer
 
 The Prior Transformer was originally introduced in [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://huggingface.co/papers/2204.06125) by Ramesh et al. It is used to predict CLIP image embeddings from CLIP text embeddings; image embeddings are predicted through a denoising diffusion process.
 

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/transformer2d.md

@@ -10,7 +10,7 @@ an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express o
 specific language governing permissions and limitations under the License.
 -->
 
-# Transformer2DModel
+# Transformer2D
 
 A Transformer model for image-like data from [CompVis](https://huggingface.co/CompVis) that is based on the [Vision Transformer](https://huggingface.co/papers/2010.11929) introduced by Dosovitskiy et al. The [`Transformer2DModel`] accepts discrete (classes of vector embeddings) or continuous (actual embeddings) inputs.
 

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

@@ -10,7 +10,7 @@ an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express o
 specific language governing permissions and limitations under the License.
 -->
 
-# TransformerTemporalModel
+# Transformer Temporal
 
 A Transformer model for video-like data.
 

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

@@ -24,4 +24,4 @@ The abstract from the paper is:
 
 ## VQEncoderOutput
 
-[[autodoc]] models.autoencoders.vq_model.VQEncoderOutput
+[[autodoc]] models.vq_model.VQEncoderOutput

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

@@ -16,7 +16,7 @@ aMUSEd was introduced in [aMUSEd: An Open MUSE Reproduction](https://huggingface
 
 Amused is a lightweight text to image model based off of the [MUSE](https://arxiv.org/abs/2301.00704) architecture. Amused is particularly useful in applications that require a lightweight and fast model such as generating many images quickly at once.
 
-Amused is a vqvae token based transformer that can generate an image in fewer forward passes than many diffusion models. In contrast with muse, it uses the smaller text encoder CLIP-L/14 instead of t5-xxl. Due to its small parameter count and few forward pass generation process, amused can generate many images quickly. This benefit is seen particularly at larger batch sizes.
+Amused is a vqvae token based transformer that can generate an image in fewer forward passes than many diffusion models. In contrast with muse, it uses the smaller text encoder CLIP-L/14 instead of t5-xxl. Due to its small parameter count and few forward pass generation process, amused can generate many images quickly. This benefit is seen particularly at larger batch sizes. 
 
 The abstract from the paper is:
 

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

@@ -78,6 +78,7 @@ output = pipe(
 )
 frames = output.frames[0]
 export_to_gif(frames, "animation.gif")
+
 ```
 
 Here are some sample outputs:
@@ -100,53 +101,6 @@ AnimateDiff tends to work better with finetuned Stable Diffusion models. If you
 
 </Tip>
 
-### 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.
-
-```python
-import torch
-from diffusers.models import MotionAdapter
-from diffusers import AnimateDiffSDXLPipeline, DDIMScheduler
-from diffusers.utils import export_to_gif
-
-adapter = MotionAdapter.from_pretrained("guoyww/animatediff-motion-adapter-sdxl-beta", torch_dtype=torch.float16)
-
-model_id = "stabilityai/stable-diffusion-xl-base-1.0"
-scheduler = DDIMScheduler.from_pretrained(
-    model_id,
-    subfolder="scheduler",
-    clip_sample=False,
-    timestep_spacing="linspace",
-    beta_schedule="linear",
-    steps_offset=1,
-)
-pipe = AnimateDiffSDXLPipeline.from_pretrained(
-    model_id,
-    motion_adapter=adapter,
-    scheduler=scheduler,
-    torch_dtype=torch.float16,
-    variant="fp16",
-).to("cuda")
-
-# enable memory savings
-pipe.enable_vae_slicing()
-pipe.enable_vae_tiling()
-
-output = pipe(
-    prompt="a panda surfing in the ocean, realistic, high quality",
-    negative_prompt="low quality, worst quality",
-    num_inference_steps=20,
-    guidance_scale=8,
-    width=1024,
-    height=1024,
-    num_frames=16,
-)
-
-frames = output.frames[0]
-export_to_gif(frames, "animation.gif")
-```
-
 ### AnimateDiffVideoToVideoPipeline
 
 AnimateDiff can also be used to generate visually similar videos or enable style/character/background or other edits starting from an initial video, allowing you to seamlessly explore creative possibilities.
@@ -164,7 +118,7 @@ from PIL import Image
 adapter = MotionAdapter.from_pretrained("guoyww/animatediff-motion-adapter-v1-5-2", torch_dtype=torch.float16)
 # load SD 1.5 based finetuned model
 model_id = "SG161222/Realistic_Vision_V5.1_noVAE"
-pipe = AnimateDiffVideoToVideoPipeline.from_pretrained(model_id, motion_adapter=adapter, torch_dtype=torch.float16)
+pipe = AnimateDiffVideoToVideoPipeline.from_pretrained(model_id, motion_adapter=adapter, torch_dtype=torch.float16).to("cuda")
 scheduler = DDIMScheduler.from_pretrained(
     model_id,
     subfolder="scheduler",
@@ -302,6 +256,7 @@ output = pipe(
 )
 frames = output.frames[0]
 export_to_gif(frames, "animation.gif")
+
 ```
 
 <table>
@@ -376,6 +331,7 @@ output = pipe(
 )
 frames = output.frames[0]
 export_to_gif(frames, "animation.gif")
+
 ```
 
 <table>
@@ -566,12 +522,6 @@ export_to_gif(frames, "animatelcm-motion-lora.gif")
   - all
   - __call__
 
-## AnimateDiffSDXLPipeline
-
-[[autodoc]] AnimateDiffSDXLPipeline
-  - all
-  - __call__
-
 ## AnimateDiffVideoToVideoPipeline
 
 [[autodoc]] AnimateDiffVideoToVideoPipeline

docs/source/en/api/pipelines/audioldm2.md

@@ -20,8 +20,8 @@ The abstract of the paper is the following:
 
 *Although audio generation shares commonalities across different types of audio, such as speech, music, and sound effects, designing models for each type requires careful consideration of specific objectives and biases that can significantly differ from those of other types. To bring us closer to a unified perspective of audio generation, this paper proposes a framework that utilizes the same learning method for speech, music, and sound effect generation. Our framework introduces a general representation of audio, called "language of audio" (LOA). Any audio can be translated into LOA based on AudioMAE, a self-supervised pre-trained representation learning model. In the generation process, we translate any modalities into LOA by using a GPT-2 model, and we perform self-supervised audio generation learning with a latent diffusion model conditioned on LOA. The proposed framework naturally brings advantages such as in-context learning abilities and reusable self-supervised pretrained AudioMAE and latent diffusion models. Experiments on the major benchmarks of text-to-audio, text-to-music, and text-to-speech demonstrate state-of-the-art or competitive performance against previous approaches. Our code, pretrained model, and demo are available at [this https URL](https://audioldm.github.io/audioldm2).*
 
-This pipeline was contributed by [sanchit-gandhi](https://huggingface.co/sanchit-gandhi) and [Nguyễn Công Tú Anh](https://github.com/tuanh123789). The original codebase can be
-found at [haoheliu/audioldm2](https://github.com/haoheliu/audioldm2).
+This pipeline was contributed by [sanchit-gandhi](https://huggingface.co/sanchit-gandhi) and [Nguyễn Công Tú Anh](https://github.com/tuanh123789). The original codebase can be 
+found at [haoheliu/audioldm2](https://github.com/haoheliu/audioldm2). 
 
 ## Tips
 

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

@@ -12,7 +12,7 @@ specific language governing permissions and limitations under the License.
 
 # BLIP-Diffusion
 
-BLIP-Diffusion was proposed in [BLIP-Diffusion: Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editing](https://arxiv.org/abs/2305.14720). It enables zero-shot subject-driven generation and control-guided zero-shot generation.
+BLIP-Diffusion was proposed in [BLIP-Diffusion: Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editing](https://arxiv.org/abs/2305.14720). It enables zero-shot subject-driven generation and control-guided zero-shot generation. 
 
 
 The abstract from the paper is:

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/hunyuandit.md

@@ -1,95 +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.
--->
-
-# Hunyuan-DiT
-![chinese elements understanding](https://github.com/gnobitab/diffusers-hunyuan/assets/1157982/39b99036-c3cb-4f16-bb1a-40ec25eda573)
-
-[Hunyuan-DiT : A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding](https://arxiv.org/abs/2405.08748) from Tencent Hunyuan.
-
-The abstract from the paper is:
-
-*We present Hunyuan-DiT, a text-to-image diffusion transformer with fine-grained understanding of both English and Chinese. To construct Hunyuan-DiT, we carefully design the transformer structure, text encoder, and positional encoding. We also build from scratch a whole data pipeline to update and evaluate data for iterative model optimization. For fine-grained language understanding, we train a Multimodal Large Language Model to refine the captions of the images. Finally, Hunyuan-DiT can perform multi-turn multimodal dialogue with users, generating and refining images according to the context. Through our holistic human evaluation protocol with more than 50 professional human evaluators, Hunyuan-DiT sets a new state-of-the-art in Chinese-to-image generation compared with other open-source models.*
-
-
-You can find the original codebase at [Tencent/HunyuanDiT](https://github.com/Tencent/HunyuanDiT) and all the available checkpoints at [Tencent-Hunyuan](https://huggingface.co/Tencent-Hunyuan/HunyuanDiT).
-
-**Highlights**: HunyuanDiT supports Chinese/English-to-image, multi-resolution generation.
-
-HunyuanDiT has the following components:
-* It uses a diffusion transformer as the backbone
-* It combines two text encoders, a bilingual CLIP and a multilingual T5 encoder
-
-<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>
-
-## 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.
-
-### 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
-from diffusers import HunyuanDiTPipeline
-import torch
-
-pipeline = HunyuanDiTPipeline.from_pretrained(
-	"Tencent-Hunyuan/HunyuanDiT-Diffusers", 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, mode="max-autotune", fullgraph=True)
-pipeline.vae.decode = torch.compile(pipeline.vae.decode, mode="max-autotune", fullgraph=True)
-
-image = pipeline(prompt="一个宇航员在骑马").images[0]
-```
-
-The [benchmark](https://gist.github.com/sayakpaul/29d3a14905cfcbf611fe71ebd22e9b23) results on a 80GB A100 machine are:
-
-```bash
-With torch.compile(): Average inference time: 12.470 seconds.
-Without torch.compile(): Average inference time: 20.570 seconds.
-```
-
-### Memory optimization
-
-By loading the T5 text encoder in 8 bits, you can run the pipeline in just under 6 GBs of GPU VRAM. Refer to [this script](https://gist.github.com/sayakpaul/3154605f6af05b98a41081aaba5ca43e) for details.
-
-Furthermore, you can use the [`~HunyuanDiT2DModel.enable_forward_chunking`] method to reduce memory usage. Feed-forward chunking runs the feed-forward layers in a transformer block in a loop instead of all at once. This gives you a trade-off between memory consumption and inference runtime.
-
-```diff
-+ pipeline.transformer.enable_forward_chunking(chunk_size=1, dim=1)
-```
-
-
-## HunyuanDiTPipeline
-
-[[autodoc]] HunyuanDiTPipeline
-	- all
-	- __call__
-

docs/source/en/api/pipelines/i2vgenxl.md

@@ -47,7 +47,6 @@ Sample output with I2VGenXL:
 * Unlike SVD, it additionally accepts text prompts as inputs.
 * It can generate higher resolution videos.
 * When using the [`DDIMScheduler`] (which is default for this pipeline), less than 50 steps for inference leads to bad results.
-* This implementation is 1-stage variant of I2VGenXL. The main figure in the [I2VGen-XL](https://arxiv.org/abs/2311.04145) paper shows a 2-stage variant, however, 1-stage variant works well. See [this discussion](https://github.com/huggingface/diffusers/discussions/7952) for more details.
 
 ## I2VGenXLPipeline
 [[autodoc]] I2VGenXLPipeline

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

@@ -11,12 +11,12 @@ 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.*
 
 Its architecture includes 3 main components:
-1. [FLAN-UL2](https://huggingface.co/google/flan-ul2), which is an encoder decoder model based on the T5 architecture.
+1. [FLAN-UL2](https://huggingface.co/google/flan-ul2), which is an encoder decoder model based on the T5 architecture. 
 2. New U-Net architecture featuring BigGAN-deep blocks doubles depth while maintaining the same number of parameters.
 3. Sber-MoVQGAN is a decoder proven to have superior results in image restoration.
 

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

@@ -25,11 +25,11 @@ You can find additional information about LEDITS++ on the [project page](https:/
 </Tip>
 
 <Tip warning={true}>
-Due to some backward compatability issues with the current diffusers implementation of [`~schedulers.DPMSolverMultistepScheduler`] this implementation of LEdits++ can no longer guarantee perfect inversion.
-This issue is unlikely to have any noticeable effects on applied use-cases. However, we provide an alternative implementation that guarantees perfect inversion in a dedicated [GitHub repo](https://github.com/ml-research/ledits_pp).
+Due to some backward compatability issues with the current diffusers implementation of [`~schedulers.DPMSolverMultistepScheduler`] this implementation of LEdits++ can no longer guarantee perfect inversion. 
+This issue is unlikely to have any noticeable effects on applied use-cases. However, we provide an alternative implementation that guarantees perfect inversion in a dedicated [GitHub repo](https://github.com/ml-research/ledits_pp). 
 </Tip>
 
-We provide two distinct pipelines based on different pre-trained models.
+We provide two distinct pipelines based on different pre-trained models. 
 
 ## LEditsPPPipelineStableDiffusion
 [[autodoc]] pipelines.ledits_pp.LEditsPPPipelineStableDiffusion

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

@@ -1,76 +0,0 @@
-<!--Copyright 2024 Marigold authors and 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.
--->
-
-# Marigold Pipelines for Computer Vision Tasks
-
-![marigold](https://marigoldmonodepth.github.io/images/teaser_collage_compressed.jpg)
-
-Marigold was proposed in [Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation](https://huggingface.co/papers/2312.02145), a CVPR 2024 Oral paper by [Bingxin Ke](http://www.kebingxin.com/), [Anton Obukhov](https://www.obukhov.ai/), [Shengyu Huang](https://shengyuh.github.io/), [Nando Metzger](https://nandometzger.github.io/), [Rodrigo Caye Daudt](https://rcdaudt.github.io/), and [Konrad Schindler](https://scholar.google.com/citations?user=FZuNgqIAAAAJ&hl=en).
-The idea is to repurpose the rich generative prior of Text-to-Image Latent Diffusion Models (LDMs) for traditional computer vision tasks.
-Initially, this idea was explored to fine-tune Stable Diffusion for Monocular Depth Estimation, as shown in the teaser above.
-Later,
-- [Tianfu Wang](https://tianfwang.github.io/) trained the first Latent Consistency Model (LCM) of Marigold, which unlocked fast single-step inference;
-- [Kevin Qu](https://www.linkedin.com/in/kevin-qu-b3417621b/?locale=en_US) extended the approach to Surface Normals Estimation;
-- [Anton Obukhov](https://www.obukhov.ai/) contributed the pipelines and documentation into diffusers (enabled and supported by [YiYi Xu](https://yiyixuxu.github.io/) and [Sayak Paul](https://sayak.dev/)).
-
-The abstract from the paper is:
-
-*Monocular depth estimation is a fundamental computer vision task. Recovering 3D depth from a single image is geometrically ill-posed and requires scene understanding, so it is not surprising that the rise of deep learning has led to a breakthrough. The impressive progress of monocular depth estimators has mirrored the growth in model capacity, from relatively modest CNNs to large Transformer architectures. Still, monocular depth estimators tend to struggle when presented with images with unfamiliar content and layout, since their knowledge of the visual world is restricted by the data seen during training, and challenged by zero-shot generalization to new domains. This motivates us to explore whether the extensive priors captured in recent generative diffusion models can enable better, more generalizable depth estimation. We introduce Marigold, a method for affine-invariant monocular depth estimation that is derived from Stable Diffusion and retains its rich prior knowledge. The estimator can be fine-tuned in a couple of days on a single GPU using only synthetic training data. It delivers state-of-the-art performance across a wide range of datasets, including over 20% performance gains in specific cases. Project page: https://marigoldmonodepth.github.io.*
-
-## Available Pipelines
-
-Each pipeline supports one Computer Vision task, which takes an input RGB image as input and produces a *prediction* of the modality of interest, such as a depth map of the input image.
-Currently, the following tasks are implemented:
-
-| Pipeline                                                                                                                                    | Predicted Modalities                                                                                             |                                                                       Demos                                                                        |
-|---------------------------------------------------------------------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------:|
-| [MarigoldDepthPipeline](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/marigold/pipeline_marigold_depth.py)     | [Depth](https://en.wikipedia.org/wiki/Depth_map), [Disparity](https://en.wikipedia.org/wiki/Binocular_disparity) | [Fast Demo (LCM)](https://huggingface.co/spaces/prs-eth/marigold-lcm), [Slow Original Demo (DDIM)](https://huggingface.co/spaces/prs-eth/marigold) |
-| [MarigoldNormalsPipeline](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/marigold/pipeline_marigold_normals.py) | [Surface normals](https://en.wikipedia.org/wiki/Normal_mapping)                                                  |                                   [Fast Demo (LCM)](https://huggingface.co/spaces/prs-eth/marigold-normals-lcm)                                    |
-
-
-## Available Checkpoints
-
-The original checkpoints can be found under the [PRS-ETH](https://huggingface.co/prs-eth/) Hugging Face organization.
-
-<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. Also, to know more about reducing the memory usage of this pipeline, refer to the ["Reduce memory usage"] section [here](../../using-diffusers/svd#reduce-memory-usage).
-
-</Tip>
-
-<Tip warning={true}>
-
-Marigold pipelines were designed and tested only with `DDIMScheduler` and `LCMScheduler`.
-Depending on the scheduler, the number of inference steps required to get reliable predictions varies, and there is no universal value that works best across schedulers.
-Because of that, the default value of `num_inference_steps` in the `__call__` method of the pipeline is set to `None` (see the API reference).
-Unless set explicitly, its value will be taken from the checkpoint configuration `model_index.json`.
-This is done to ensure high-quality predictions when calling the pipeline with just the `image` argument.
-
-</Tip>
-
-See also Marigold [usage examples](marigold_usage).
-
-## MarigoldDepthPipeline
-[[autodoc]] MarigoldDepthPipeline
-	- all
-	- __call__
-
-## MarigoldNormalsPipeline
-[[autodoc]] MarigoldNormalsPipeline
-	- all
-	- __call__
-
-## MarigoldDepthOutput
-[[autodoc]] pipelines.marigold.pipeline_marigold_depth.MarigoldDepthOutput
-
-## MarigoldNormalsOutput
-[[autodoc]] pipelines.marigold.pipeline_marigold_normals.MarigoldNormalsOutput

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

@@ -31,13 +31,13 @@ Some notes about this pipeline:
 
 <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.
+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>
 
 ## Inference with under 8GB GPU VRAM
 
-Run the [`PixArtAlphaPipeline`] with under 8GB GPU VRAM by loading the text encoder in 8-bit precision. Let's walk through a full-fledged example.
+Run the [`PixArtAlphaPipeline`] with under 8GB GPU VRAM by loading the text encoder in 8-bit precision. Let's walk through a full-fledged example. 
 
 First, install the [bitsandbytes](https://github.com/TimDettmers/bitsandbytes) library:
 
@@ -75,10 +75,10 @@ with torch.no_grad():
     prompt_embeds, prompt_attention_mask, negative_embeds, negative_prompt_attention_mask = pipe.encode_prompt(prompt)
 ```
 
-Since text embeddings have been computed, remove the `text_encoder` and `pipe` from the memory, and free up some GPU VRAM:
+Since text embeddings have been computed, remove the `text_encoder` and `pipe` from the memory, and free up som GPU VRAM:
 
 ```python
-import gc
+import gc 
 
 def flush():
     gc.collect()
@@ -99,7 +99,7 @@ pipe = PixArtAlphaPipeline.from_pretrained(
 ).to("cuda")
 
 latents = pipe(
-    negative_prompt=None,
+    negative_prompt=None, 
     prompt_embeds=prompt_embeds,
     negative_prompt_embeds=negative_embeds,
     prompt_attention_mask=prompt_attention_mask,
@@ -146,3 +146,4 @@ While loading the `text_encoder`, you set `load_in_8bit` to `True`. You could al
 [[autodoc]] PixArtAlphaPipeline
 	- all
 	- __call__
+	

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

@@ -1,149 +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.
--->
-
-# PixArt-Σ
-
-![](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/pixart/header_collage_sigma.jpg)
-
-[PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation](https://huggingface.co/papers/2403.04692) is Junsong Chen, Jincheng Yu, Chongjian Ge, Lewei Yao, Enze Xie, Yue Wu, Zhongdao Wang, James Kwok, Ping Luo, Huchuan Lu, and Zhenguo Li.
-
-The abstract from the paper is:
-
-*In this paper, we introduce PixArt-Σ, a Diffusion Transformer model (DiT) capable of directly generating images at 4K resolution. PixArt-Σ represents a significant advancement over its predecessor, PixArt-α, offering images of markedly higher fidelity and improved alignment with text prompts. A key feature of PixArt-Σ is its training efficiency. Leveraging the foundational pre-training of PixArt-α, it evolves from the ‘weaker’ baseline to a ‘stronger’ model via incorporating higher quality data, a process we term “weak-to-strong training”. The advancements in PixArt-Σ are twofold: (1) High-Quality Training Data: PixArt-Σ incorporates superior-quality image data, paired with more precise and detailed image captions. (2) Efficient Token Compression: we propose a novel attention module within the DiT framework that compresses both keys and values, significantly improving efficiency and facilitating ultra-high-resolution image generation. Thanks to these improvements, PixArt-Σ achieves superior image quality and user prompt adherence capabilities with significantly smaller model size (0.6B parameters) than existing text-to-image diffusion models, such as SDXL (2.6B parameters) and SD Cascade (5.1B parameters). Moreover, PixArt-Σ’s capability to generate 4K images supports the creation of high-resolution posters and wallpapers, efficiently bolstering the production of highquality visual content in industries such as film and gaming.*
-
-You can find the original codebase at [PixArt-alpha/PixArt-sigma](https://github.com/PixArt-alpha/PixArt-sigma) and all the available checkpoints at [PixArt-alpha](https://huggingface.co/PixArt-alpha).
-
-Some notes about this pipeline:
-
-* It uses a Transformer backbone (instead of a UNet) for denoising. As such it has a similar architecture as [DiT](https://hf.co/docs/transformers/model_doc/dit).
-* It was trained using text conditions computed from T5. This aspect makes the pipeline better at following complex text prompts with intricate details.
-* It is good at producing high-resolution images at different aspect ratios. To get the best results, the authors recommend some size brackets which can be found [here](https://github.com/PixArt-alpha/PixArt-sigma/blob/master/diffusion/data/datasets/utils.py).
-* It rivals the quality of state-of-the-art text-to-image generation systems (as of this writing) such as PixArt-α, Stable Diffusion XL, Playground V2.0 and DALL-E 3, while being more efficient than them.
-* It shows the ability of generating super high resolution images, such as 2048px or even 4K.
-* It shows that text-to-image models can grow from a weak model to a stronger one through several improvements (VAEs, datasets, and so on.)
-
-<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-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
-
-</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.
-
-First, install the [bitsandbytes](https://github.com/TimDettmers/bitsandbytes) library:
-
-```bash
-pip install -U bitsandbytes
-```
-
-Then load the text encoder in 8-bit:
-
-```python
-from transformers import T5EncoderModel
-from diffusers import PixArtSigmaPipeline
-import torch
-
-text_encoder = T5EncoderModel.from_pretrained(
-    "PixArt-alpha/PixArt-Sigma-XL-2-1024-MS",
-    subfolder="text_encoder",
-    load_in_8bit=True,
-    device_map="auto",
-)
-pipe = PixArtSigmaPipeline.from_pretrained(
-    "PixArt-alpha/PixArt-Sigma-XL-2-1024-MS",
-    text_encoder=text_encoder,
-    transformer=None,
-    device_map="balanced"
-)
-```
-
-Now, use the `pipe` to encode a prompt:
-
-```python
-with torch.no_grad():
-    prompt = "cute cat"
-    prompt_embeds, prompt_attention_mask, negative_embeds, negative_prompt_attention_mask = pipe.encode_prompt(prompt)
-```
-
-Since text embeddings have been computed, remove the `text_encoder` and `pipe` from the memory, and free up some GPU VRAM:
-
-```python
-import gc
-
-def flush():
-    gc.collect()
-    torch.cuda.empty_cache()
-
-del text_encoder
-del pipe
-flush()
-```
-
-Then compute the latents with the prompt embeddings as inputs:
-
-```python
-pipe = PixArtSigmaPipeline.from_pretrained(
-    "PixArt-alpha/PixArt-Sigma-XL-2-1024-MS",
-    text_encoder=None,
-    torch_dtype=torch.float16,
-).to("cuda")
-
-latents = pipe(
-    negative_prompt=None,
-    prompt_embeds=prompt_embeds,
-    negative_prompt_embeds=negative_embeds,
-    prompt_attention_mask=prompt_attention_mask,
-    negative_prompt_attention_mask=negative_prompt_attention_mask,
-    num_images_per_prompt=1,
-    output_type="latent",
-).images
-
-del pipe.transformer
-flush()
-```
-
-<Tip>
-
-Notice that while initializing `pipe`, you're setting `text_encoder` to `None` so that it's not loaded.
-
-</Tip>
-
-Once the latents are computed, pass it off to the VAE to decode into a real image:
-
-```python
-with torch.no_grad():
-    image = pipe.vae.decode(latents / pipe.vae.config.scaling_factor, return_dict=False)[0]
-image = pipe.image_processor.postprocess(image, output_type="pil")[0]
-image.save("cat.png")
-```
-
-By deleting components you aren't using and flushing the GPU VRAM, you should be able to run [`PixArtSigmaPipeline`] with under 8GB GPU VRAM.
-
-![](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/pixart/8bits_cat.png)
-
-If you want a report of your memory-usage, run this [script](https://gist.github.com/sayakpaul/3ae0f847001d342af27018a96f467e4e).
-
-<Tip warning={true}>
-
-Text embeddings computed in 8-bit can impact the quality of the generated images because of the information loss in the representation space caused by the reduced precision. It's recommended to compare the outputs with and without 8-bit.
-
-</Tip>
-
-While loading the `text_encoder`, you set `load_in_8bit` to `True`. You could also specify `load_in_4bit` to bring your memory requirements down even further to under 7GB.
-
-## PixArtSigmaPipeline
-
-[[autodoc]] PixArtSigmaPipeline
-	- all
-	- __call__

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

@@ -12,7 +12,7 @@ specific language governing permissions and limitations under the License.
 
 # K-Diffusion
 
-[k-diffusion](https://github.com/crowsonkb/k-diffusion) is a popular library created by [Katherine Crowson](https://github.com/crowsonkb/). We provide `StableDiffusionKDiffusionPipeline` and `StableDiffusionXLKDiffusionPipeline` that allow you to run Stable DIffusion with samplers from k-diffusion.
+[k-diffusion](https://github.com/crowsonkb/k-diffusion) is a popular library created by [Katherine Crowson](https://github.com/crowsonkb/). We provide `StableDiffusionKDiffusionPipeline` and `StableDiffusionXLKDiffusionPipeline` that allow you to run Stable DIffusion with samplers from k-diffusion. 
 
 Note that most the samplers from k-diffusion are implemented in Diffusers and we recommend using existing schedulers. You can find a mapping between k-diffusion samplers and schedulers in Diffusers [here](https://huggingface.co/docs/diffusers/api/schedulers/overview)
 

docs/source/en/api/pipelines/stable_diffusion/ldm3d_diffusion.md

@@ -12,11 +12,11 @@ specific language governing permissions and limitations under the License.
 
 # Text-to-(RGB, depth)
 
-LDM3D was proposed in [LDM3D: Latent Diffusion Model for 3D](https://huggingface.co/papers/2305.10853) by Gabriela Ben Melech Stan, Diana Wofk, Scottie Fox, Alex Redden, Will Saxton, Jean Yu, Estelle Aflalo, Shao-Yen Tseng, Fabio Nonato, Matthias Muller, and Vasudev Lal. LDM3D generates an image and a depth map from a given text prompt unlike the existing text-to-image diffusion models such as [Stable Diffusion](./overview) which only generates an image. With almost the same number of parameters, LDM3D achieves to create a latent space that can compress both the RGB images and the depth maps.
+LDM3D was proposed in [LDM3D: Latent Diffusion Model for 3D](https://huggingface.co/papers/2305.10853) by Gabriela Ben Melech Stan, Diana Wofk, Scottie Fox, Alex Redden, Will Saxton, Jean Yu, Estelle Aflalo, Shao-Yen Tseng, Fabio Nonato, Matthias Muller, and Vasudev Lal. LDM3D generates an image and a depth map from a given text prompt unlike the existing text-to-image diffusion models such as [Stable Diffusion](./overview) which only generates an image. With almost the same number of parameters, LDM3D achieves to create a latent space that can compress both the RGB images and the depth maps. 
 
 Two checkpoints are available for use:
 - [ldm3d-original](https://huggingface.co/Intel/ldm3d). The original checkpoint used in the [paper](https://arxiv.org/pdf/2305.10853.pdf)
-- [ldm3d-4c](https://huggingface.co/Intel/ldm3d-4c). The new version of LDM3D using 4 channels inputs instead of 6-channels inputs and finetuned on higher resolution images.
+- [ldm3d-4c](https://huggingface.co/Intel/ldm3d-4c). The new version of LDM3D using 4 channels inputs instead of 6-channels inputs and finetuned on higher resolution images. 
 
 
 The abstract from the paper is:
@@ -44,7 +44,7 @@ Make sure to check out the Stable Diffusion [Tips](overview#tips) section to lea
 
 # Upscaler
 
-[LDM3D-VR](https://arxiv.org/pdf/2311.03226.pdf) is an extended version of LDM3D.
+[LDM3D-VR](https://arxiv.org/pdf/2311.03226.pdf) is an extended version of LDM3D. 
 
 The abstract from the paper is:
 *Latent diffusion models have proven to be state-of-the-art in the creation and manipulation of visual outputs. However, as far as we know, the generation of depth maps jointly with RGB is still limited. We introduce LDM3D-VR, a suite of diffusion models targeting virtual reality development that includes LDM3D-pano and LDM3D-SR. These models enable the generation of panoramic RGBD based on textual prompts and the upscaling of low-resolution inputs to high-resolution RGBD, respectively. Our models are fine-tuned from existing pretrained models on datasets containing panoramic/high-resolution RGB images, depth maps and captions. Both models are evaluated in comparison to existing related methods*

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

@@ -177,7 +177,7 @@ inpaint = StableDiffusionInpaintPipeline(**text2img.components)
 
 The Stable Diffusion pipelines are automatically supported in [Gradio](https://github.com/gradio-app/gradio/), a library that makes creating beautiful and user-friendly machine learning apps on the web a breeze. First, make sure you have Gradio installed:
 
-```sh
+```
 pip install -U gradio
 ```
 
@@ -209,4 +209,4 @@ gr.Interface.from_pipeline(pipe).launch()
 ```
 
 By default, the web demo runs on a local server. If you'd like to share it with others, you can generate a temporary public
-link by setting `share=True` in `launch()`. Or, you can host your demo on [Hugging Face Spaces](https://huggingface.co/spaces)https://huggingface.co/spaces for a permanent link.
+link by setting `share=True` in `launch()`. Or, you can host your demo on [Hugging Face Spaces](https://huggingface.co/spaces)https://huggingface.co/spaces for a permanent link. 

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

@@ -1,272 +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).
-
-## 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
-
-```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/pipelines/text_to_video_zero.md

@@ -155,28 +155,28 @@ To generate a video from prompt with additional pose control
     imageio.mimsave("video.mp4", result, fps=4)
     ```
 - #### SDXL Support
-
+	
 	Since our attention processor also works with SDXL, it can be utilized to generate a video from prompt using ControlNet models powered by SDXL:
 	```python
 	import torch
 	from diffusers import StableDiffusionXLControlNetPipeline, ControlNetModel
 	from diffusers.pipelines.text_to_video_synthesis.pipeline_text_to_video_zero import CrossFrameAttnProcessor
-
+	
 	controlnet_model_id = 'thibaud/controlnet-openpose-sdxl-1.0'
 	model_id = 'stabilityai/stable-diffusion-xl-base-1.0'
-
+	
 	controlnet = ControlNetModel.from_pretrained(controlnet_model_id, torch_dtype=torch.float16)
 	pipe = StableDiffusionControlNetPipeline.from_pretrained(
 		model_id, controlnet=controlnet, torch_dtype=torch.float16
 	).to('cuda')
-
+	
 	# Set the attention processor
 	pipe.unet.set_attn_processor(CrossFrameAttnProcessor(batch_size=2))
 	pipe.controlnet.set_attn_processor(CrossFrameAttnProcessor(batch_size=2))
-
+	
 	# fix latents for all frames
 	latents = torch.randn((1, 4, 128, 128), device="cuda", dtype=torch.float16).repeat(len(pose_images), 1, 1, 1)
-
+	
 	prompt = "Darth Vader dancing in a desert"
 	result = pipe(prompt=[prompt] * len(pose_images), image=pose_images, latents=latents).images
 	imageio.mimsave("video.mp4", result, fps=4)

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

@@ -12,7 +12,7 @@ specific language governing permissions and limitations under the License.
 
 # EDMDPMSolverMultistepScheduler
 
-`EDMDPMSolverMultistepScheduler` is a [Karras formulation](https://huggingface.co/papers/2206.00364) of `DPMSolverMultistepScheduler`, a multistep scheduler from [DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps](https://huggingface.co/papers/2206.00927) and [DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models](https://huggingface.co/papers/2211.01095) by Cheng Lu, Yuhao Zhou, Fan Bao, Jianfei Chen, Chongxuan Li, and Jun Zhu.
+`EDMDPMSolverMultistepScheduler` is a [Karras formulation](https://huggingface.co/papers/2206.00364) of `DPMSolverMultistep`, a multistep scheduler from [DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps](https://huggingface.co/papers/2206.00927) and [DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models](https://huggingface.co/papers/2211.01095) by Cheng Lu, Yuhao Zhou, Fan Bao, Jianfei Chen, Chongxuan Li, and Jun Zhu.
 
 DPMSolver (and the improved version DPMSolver++) is a fast dedicated high-order solver for diffusion ODEs with convergence order guarantee. Empirically, DPMSolver sampling with only 20 steps can generate high-quality
 samples, and it can generate quite good samples even in 10 steps.

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/multistep_dpm_solver.md

@@ -12,7 +12,7 @@ specific language governing permissions and limitations under the License.
 
 # DPMSolverMultistepScheduler
 
-`DPMSolverMultistepScheduler` is a multistep scheduler from [DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps](https://huggingface.co/papers/2206.00927) and [DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models](https://huggingface.co/papers/2211.01095) by Cheng Lu, Yuhao Zhou, Fan Bao, Jianfei Chen, Chongxuan Li, and Jun Zhu.
+`DPMSolverMultistep` is a multistep scheduler from [DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps](https://huggingface.co/papers/2206.00927) and [DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models](https://huggingface.co/papers/2211.01095) by Cheng Lu, Yuhao Zhou, Fan Bao, Jianfei Chen, Chongxuan Li, and Jun Zhu.
 
 DPMSolver (and the improved version DPMSolver++) is a fast dedicated high-order solver for diffusion ODEs with convergence order guarantee. Empirically, DPMSolver sampling with only 20 steps can generate high-quality
 samples, and it can generate quite good samples even in 10 steps.

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

@@ -10,7 +10,7 @@ an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express o
 specific language governing permissions and limitations under the License.
 -->
 
-# TCDScheduler
+# TCDScheduler 
 
 [Trajectory Consistency Distillation](https://huggingface.co/papers/2402.19159) by Jianbin Zheng, Minghui Hu, Zhongyi Fan, Chaoyue Wang, Changxing Ding, Dacheng Tao and Tat-Jen Cham introduced a Strategic Stochastic Sampling (Algorithm 4) that is capable of generating good samples in a small number of steps. Distinguishing it as an advanced iteration of the multistep scheduler (Algorithm 1) in the [Consistency Models](https://huggingface.co/papers/2303.01469), Strategic Stochastic Sampling specifically tailored for the trajectory consistency function.
 

docs/source/en/api/video_processor.md

@@ -1,21 +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.
--->
-
-# Video Processor
-
-The [`VideoProcessor`] provides a unified API for video pipelines to prepare inputs for VAE encoding and post-processing outputs once they're decoded. The class inherits [`VaeImageProcessor`] so it includes transformations such as resizing, normalization, and conversion between PIL Image, PyTorch, and NumPy arrays.
-
-## VideoProcessor
-
-[[autodoc]] video_processor.VideoProcessor.preprocess_video
-
-[[autodoc]] video_processor.VideoProcessor.postprocess_video

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.
 
@@ -197,81 +198,38 @@ Anything displayed on [the official Diffusers doc page](https://huggingface.co/d
 
 Please have a look at [this page](https://github.com/huggingface/diffusers/tree/main/docs) on how to verify changes made to the documentation locally.
 
+
 ### 6. Contribute a community pipeline
 
-> [!TIP]
-> Read the [Community pipelines](../using-diffusers/custom_pipeline_overview#community-pipelines) guide to learn more about the difference between a GitHub and Hugging Face Hub community pipeline. If you're interested in why we have community pipelines, take a look at GitHub Issue [#841](https://github.com/huggingface/diffusers/issues/841) (basically, we can't maintain all the possible ways diffusion models can be used for inference but we also don't want to prevent the community from building them).
+[Pipelines](https://huggingface.co/docs/diffusers/api/pipelines/overview) are usually the first point of contact between the Diffusers library and the user.
+Pipelines are examples of how to use Diffusers [models](https://huggingface.co/docs/diffusers/api/models/overview) and [schedulers](https://huggingface.co/docs/diffusers/api/schedulers/overview).
+We support two types of pipelines:
 
-Contributing a community pipeline is a great way to share your creativity and work with the community. It lets you build on top of the [`DiffusionPipeline`] so that anyone can load and use it by setting the `custom_pipeline` parameter. This section will walk you through how to create a simple pipeline where the UNet only does a single forward pass and calls the scheduler once (a "one-step" pipeline).
+- Official Pipelines
+- Community Pipelines
 
-1. Create a one_step_unet.py file for your community pipeline. This file can contain whatever package you want to use as long as it's installed by the user. Make sure you only have one pipeline class that inherits from [`DiffusionPipeline`] to load model weights and the scheduler configuration from the Hub. Add a UNet and scheduler to the `__init__` function.
+Both official and community pipelines follow the same design and consist of the same type of components.
 
-    You should also add the `register_modules` function to ensure your pipeline and its components can be saved with [`~DiffusionPipeline.save_pretrained`].
+Official pipelines are tested and maintained by the core maintainers of Diffusers. Their code
+resides in [src/diffusers/pipelines](https://github.com/huggingface/diffusers/tree/main/src/diffusers/pipelines).
+In contrast, community pipelines are contributed and maintained purely by the **community** and are **not** tested.
+They reside in [examples/community](https://github.com/huggingface/diffusers/tree/main/examples/community) and while they can be accessed via the [PyPI diffusers package](https://pypi.org/project/diffusers/), their code is not part of the PyPI distribution.
 
-```py
-from diffusers import DiffusionPipeline
-import torch
+The reason for the distinction is that the core maintainers of the Diffusers library cannot maintain and test all
+possible ways diffusion models can be used for inference, but some of them may be of interest to the community.
+Officially released diffusion pipelines,
+such as Stable Diffusion are added to the core src/diffusers/pipelines package which ensures
+high quality of maintenance, no backward-breaking code changes, and testing.
+More bleeding edge pipelines should be added as community pipelines. If usage for a community pipeline is high, the pipeline can be moved to the official pipelines upon request from the community. This is one of the ways we strive to be a community-driven library.
 
-class UnetSchedulerOneForwardPipeline(DiffusionPipeline):
-    def __init__(self, unet, scheduler):
-        super().__init__()
+To add a community pipeline, one should add a <name-of-the-community>.py file to [examples/community](https://github.com/huggingface/diffusers/tree/main/examples/community) and adapt the [examples/community/README.md](https://github.com/huggingface/diffusers/tree/main/examples/community/README.md) to include an example of the new pipeline.
 
-        self.register_modules(unet=unet, scheduler=scheduler)
-```
+An example can be seen [here](https://github.com/huggingface/diffusers/pull/2400).
 
-1. In the forward pass (which we recommend defining as `__call__`), you can add any feature you'd like. For the "one-step" pipeline, create a random image and call the UNet and scheduler once by setting `timestep=1`.
+Community pipeline PRs are only checked at a superficial level and ideally they should be maintained by their original authors.
 
-```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
-```
-
-Now you can run the pipeline by passing a UNet and scheduler to it or load pretrained weights if the pipeline structure is identical.
-
-```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()
-```
-
-You can either share your pipeline as a GitHub community pipeline or Hub community pipeline.
-
-<hfoptions id="pipeline type">
-<hfoption id="GitHub pipeline">
-
-Share your GitHub pipeline by opening a pull request on the Diffusers [repository](https://github.com/huggingface/diffusers) and add the one_step_unet.py file to the [examples/community](https://github.com/huggingface/diffusers/tree/main/examples/community) subfolder.
-
-</hfoption>
-<hfoption id="Hub pipeline">
-
-Share your Hub pipeline by creating a model repository on the Hub and uploading the one_step_unet.py file to it.
-
-</hfoption>
-</hfoptions>
+Contributing a community pipeline is a great way to understand how Diffusers models and schedulers work. Having contributed a community pipeline is usually the first stepping stone to contributing an official pipeline to the
+core package.
 
 ### 7. Contribute to training examples
 
@@ -287,7 +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
@@ -297,8 +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).
@@ -316,7 +273,7 @@ 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 +375,7 @@ 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
@@ -565,4 +522,4 @@ $ git push --set-upstream origin your-branch-for-syncing
 
 ### Style guide
 
-For documentation strings, 🧨 Diffusers follows the [Google style](https://google.github.io/styleguide/pyguide.html).
+For documentation strings, 🧨 Diffusers follows the [Google style](https://google.github.io/styleguide/pyguide.html).

docs/source/en/conceptual/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.

docs/source/en/installation.md

@@ -112,7 +112,7 @@ pip install -e ".[flax]"
 
 These commands will link the folder you cloned the repository to and your Python library paths.
 Python will now look inside the folder you cloned to in addition to the normal library paths.
-For example, if your Python packages are typically installed in `~/anaconda3/envs/main/lib/python3.10/site-packages/`, Python will also search the `~/diffusers/` folder you cloned to.
+For example, if your Python packages are typically installed in `~/anaconda3/envs/main/lib/python3.8/site-packages/`, Python will also search the `~/diffusers/` folder you cloned to.
 
 <Tip warning={true}>
 

docs/source/en/optimization/deepcache.md

@@ -36,7 +36,7 @@ Then load and enable the [`DeepCacheSDHelper`](https://github.com/horseee/DeepCa
   image = pipe("a photo of an astronaut on a moon").images[0]
 ```
 
-The `set_params` method accepts two arguments: `cache_interval` and `cache_branch_id`. `cache_interval` means the frequency of feature caching, specified as the number of steps between each cache operation. `cache_branch_id` identifies which branch of the network (ordered from the shallowest to the deepest layer) is responsible for executing the caching processes.
+The `set_params` method accepts two arguments: `cache_interval` and `cache_branch_id`. `cache_interval` means the frequency of feature caching, specified as the number of steps between each cache operation. `cache_branch_id` identifies which branch of the network (ordered from the shallowest to the deepest layer) is responsible for executing the caching processes. 
 Opting for a lower `cache_branch_id` or a larger `cache_interval` can lead to faster inference speed at the expense of reduced image quality (ablation experiments of these two hyperparameters can be found in the [paper](https://arxiv.org/abs/2312.00858)). Once those arguments are set, use the `enable` or `disable` methods to activate or deactivate the `DeepCacheSDHelper`.
 
 <div class="flex justify-center">

docs/source/en/optimization/fp16.md

@@ -12,23 +12,27 @@ specific language governing permissions and limitations under the License.
 
 # Speed up inference
 
-There are several ways to optimize Diffusers for inference speed, such as reducing the computational burden by lowering the data precision or using a lightweight distilled model. There are also memory-efficient attention implementations, [xFormers](xformers) and [scaled dot product attention](https://pytorch.org/docs/stable/generated/torch.nn.functional.scaled_dot_product_attention.html) in PyTorch 2.0, that reduce memory usage which also indirectly speeds up inference. Different speed optimizations can be stacked together to get the fastest inference times.
+There are several ways to optimize 🤗 Diffusers for inference speed. As a general rule of thumb, we recommend using either [xFormers](xformers) or `torch.nn.functional.scaled_dot_product_attention` in PyTorch 2.0 for their memory-efficient attention.
 
-> [!TIP]
-> Optimizing for inference speed or reduced memory usage can lead to improved performance in the other category, so you should try to optimize for both whenever you can. This guide focuses on inference speed, but you can learn more about lowering memory usage in the [Reduce memory usage](memory) guide.
+<Tip>
 
-The inference times below are obtained from generating a single 512x512 image from the prompt "a photo of an astronaut riding a horse on mars" with 50 DDIM steps on a NVIDIA A100.
+In many cases, optimizing for speed or memory leads to improved performance in the other, so you should try to optimize for both whenever you can. This guide focuses on inference speed, but you can learn more about preserving memory in the [Reduce memory usage](memory) guide.
 
-| setup    | latency | speed-up |
-|----------|---------|----------|
-| baseline | 5.27s   | x1       |
-| tf32     | 4.14s   | x1.27    |
-| fp16     | 3.51s   | x1.50    |
-| combined | 3.41s   | x1.54    |
+</Tip>
 
-## TensorFloat-32
+The results below are obtained from generating a single 512x512 image from the prompt `a photo of an astronaut riding a horse on mars` with 50 DDIM steps on a Nvidia Titan RTX, demonstrating the speed-up you can expect.
 
-On Ampere and later CUDA devices, matrix multiplications and convolutions can use the [TensorFloat-32 (tf32)](https://blogs.nvidia.com/blog/2020/05/14/tensorfloat-32-precision-format/) mode for faster, but slightly less accurate computations. By default, PyTorch enables tf32 mode for convolutions but not matrix multiplications. Unless your network requires full float32 precision, we recommend enabling tf32 for matrix multiplications. It can significantly speed up computations with typically negligible loss in numerical accuracy.
+|                  | latency | speed-up |
+| ---------------- | ------- | ------- |
+| original         | 9.50s   | x1      |
+| fp16             | 3.61s   | x2.63   |
+| channels last    | 3.30s   | x2.88   |
+| traced UNet      | 3.21s   | x2.96   |
+| memory efficient attention  | 2.63s  | x3.61   |
+
+## Use TensorFloat-32
+
+On Ampere and later CUDA devices, matrix multiplications and convolutions can use the [TensorFloat-32 (TF32)](https://blogs.nvidia.com/blog/2020/05/14/tensorfloat-32-precision-format/) mode for faster, but slightly less accurate computations. By default, PyTorch enables TF32 mode for convolutions but not matrix multiplications. Unless your network requires full float32 precision, we recommend enabling TF32 for matrix multiplications. It can significantly speeds up computations with typically negligible loss in numerical accuracy.
 
 ```python
 import torch
@@ -36,11 +40,11 @@ import torch
 torch.backends.cuda.matmul.allow_tf32 = True
 ```
 
-Learn more about tf32 in the [Mixed precision training](https://huggingface.co/docs/transformers/en/perf_train_gpu_one#tf32) guide.
+You can learn more about TF32 in the [Mixed precision training](https://huggingface.co/docs/transformers/en/perf_train_gpu_one#tf32) guide.
 
 ## Half-precision weights
 
-To save GPU memory and get more speed, set `torch_dtype=torch.float16` to load and run the model weights directly with half-precision weights.
+To save GPU memory and get more speed, try loading and running the model weights directly in half-precision or float16:
 
 ```Python
 import torch
@@ -52,76 +56,19 @@ pipe = DiffusionPipeline.from_pretrained(
     use_safetensors=True,
 )
 pipe = pipe.to("cuda")
+
+prompt = "a photo of an astronaut riding a horse on mars"
+image = pipe(prompt).images[0]
 ```
 
-> [!WARNING]
-> Don't use [torch.autocast](https://pytorch.org/docs/stable/amp.html#torch.autocast) in any of the pipelines as it can lead to black images and is always slower than pure float16 precision.
+<Tip warning={true}>
+
+Don't use [`torch.autocast`](https://pytorch.org/docs/stable/amp.html#torch.autocast) in any of the pipelines as it can lead to black images and is always slower than pure float16 precision.
+
+</Tip>
 
 ## Distilled model
 
-You could also use a distilled Stable Diffusion model and autoencoder to speed up inference. During distillation, many of the UNet's residual and attention blocks are shed to reduce the model size by 51% and improve latency on CPU/GPU by 43%. The distilled model is faster and uses less memory while generating images of comparable quality to the full Stable Diffusion model.
+You could also use a distilled Stable Diffusion model and autoencoder to speed up inference. During distillation, many of the UNet's residual and attention blocks are shed to reduce the model size. The distilled model is faster and uses less memory while generating images of comparable quality to the full Stable Diffusion model.
 
-> [!TIP]
-> Read the [Open-sourcing Knowledge Distillation Code and Weights of SD-Small and SD-Tiny](https://huggingface.co/blog/sd_distillation) blog post to learn more about how knowledge distillation training works to produce a faster, smaller, and cheaper generative model.
-
-The inference times below are obtained from generating 4 images from the prompt "a photo of an astronaut riding a horse on mars" with 25 PNDM steps on a NVIDIA A100. Each generation is repeated 3 times with the distilled Stable Diffusion v1.4 model by [Nota AI](https://hf.co/nota-ai).
-
-| setup                        | latency | speed-up |
-|------------------------------|---------|----------|
-| baseline                     | 6.37s   | x1       |
-| distilled                    | 4.18s   | x1.52    |
-| distilled + tiny autoencoder | 3.83s   | x1.66    |
-
-Let's load the distilled Stable Diffusion model and compare it against the original Stable Diffusion model.
-
-```py
-from diffusers import StableDiffusionPipeline
-import torch
-
-distilled = StableDiffusionPipeline.from_pretrained(
-    "nota-ai/bk-sdm-small", torch_dtype=torch.float16, use_safetensors=True,
-).to("cuda")
-prompt = "a golden vase with different flowers"
-generator = torch.manual_seed(2023)
-image = distilled("a golden vase with different flowers", num_inference_steps=25, generator=generator).images[0]
-image
-```
-
-<div class="flex gap-4">
-  <div>
-    <img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/original_sd.png"/>
-    <figcaption class="mt-2 text-center text-sm text-gray-500">original Stable Diffusion</figcaption>
-  </div>
-  <div>
-    <img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/distilled_sd.png"/>
-    <figcaption class="mt-2 text-center text-sm text-gray-500">distilled Stable Diffusion</figcaption>
-  </div>
-</div>
-
-### Tiny AutoEncoder
-
-To speed inference up even more, replace the autoencoder with a [distilled version](https://huggingface.co/sayakpaul/taesdxl-diffusers) of it.
-
-```py
-import torch
-from diffusers import AutoencoderTiny, StableDiffusionPipeline
-
-distilled = StableDiffusionPipeline.from_pretrained(
-    "nota-ai/bk-sdm-small", torch_dtype=torch.float16, use_safetensors=True,
-).to("cuda")
-distilled.vae = AutoencoderTiny.from_pretrained(
-    "sayakpaul/taesd-diffusers", torch_dtype=torch.float16, use_safetensors=True,
-).to("cuda")
-
-prompt = "a golden vase with different flowers"
-generator = torch.manual_seed(2023)
-image = distilled("a golden vase with different flowers", num_inference_steps=25, generator=generator).images[0]
-image
-```
-
-<div class="flex justify-center">
-  <div>
-    <img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/distilled_sd_vae.png" />
-    <figcaption class="mt-2 text-center text-sm text-gray-500">distilled Stable Diffusion + Tiny AutoEncoder</figcaption>
-  </div>
-</div>
+Learn more about in the [Distilled Stable Diffusion inference](../using-diffusers/distilled_sd) guide!

docs/source/en/optimization/memory.md

@@ -261,7 +261,7 @@ from dataclasses import dataclass
 
 @dataclass
 class UNet2DConditionOutput:
-    sample: torch.Tensor
+    sample: torch.FloatTensor
 
 
 pipe = StableDiffusionPipeline.from_pretrained(

docs/source/en/optimization/tgate.md

@@ -6,7 +6,7 @@ Before you begin, make sure you install T-GATE.
 
 ```bash
 pip install tgate
-pip install -U torch diffusers transformers accelerate DeepCache
+pip install -U pytorch diffusers transformers accelerate DeepCache
 ```
 
 
@@ -46,12 +46,12 @@ pipe = TgatePixArtLoader(
 
 image = pipe.tgate(
        "An alpaca made of colorful building blocks, cyberpunk.",
-       gate_step=gate_step,
+        gate_step=gate_step,
        num_inference_steps=inference_step,
 ).images[0]
 ```
 </hfoption>
-<hfoption id="Stable Diffusion XL">
+<hfoption id="Stable Diffusion XL"> 
 
 Accelerate `StableDiffusionXLPipeline` with T-GATE:
 
@@ -78,9 +78,9 @@ pipe = TgateSDXLLoader(
 ).to("cuda")
 
 image = pipe.tgate(
-       "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k.",
-       gate_step=gate_step,
-       num_inference_steps=inference_step
+        "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k.",
+        gate_step=gate_step,
+        num_inference_steps=inference_step
 ).images[0]
 ```
 </hfoption>
@@ -111,9 +111,9 @@ pipe = TgateSDXLDeepCacheLoader(
 ).to("cuda")
 
 image = pipe.tgate(
-       "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k.",
-       gate_step=gate_step,
-       num_inference_steps=inference_step
+        "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k.",
+        gate_step=gate_step,
+        num_inference_steps=inference_step
 ).images[0]
 ```
 </hfoption>
@@ -151,9 +151,9 @@ pipe = TgateSDXLLoader(
 ).to("cuda")
 
 image = pipe.tgate(
-       "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k.",
-       gate_step=gate_step,
-       num_inference_steps=inference_step
+        "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k.",
+        gate_step=gate_step,
+        num_inference_steps=inference_step
 ).images[0]
 ```
 </hfoption>

docs/source/en/training/adapt_a_model.md

@@ -26,7 +26,7 @@ pipeline.unet.config["in_channels"]
 9
 ```
 
-To adapt your text-to-image model for inpainting, you'll need to change the number of `in_channels` from 4 to 9.
+To adapt your text-to-image model for inpainting, you'll need to change the number of `in_channels` from 4 to 9. 
 
 Initialize a [`UNet2DConditionModel`] with the pretrained text-to-image model weights, and change `in_channels` to 9. Changing the number of `in_channels` means you need to set `ignore_mismatched_sizes=True` and `low_cpu_mem_usage=False` to avoid a size mismatch error because the shape is different now.
 

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")
 ```
 
@@ -363,4 +363,4 @@ The SDXL training script is discussed in more detail in the [SDXL training](sdxl
 
 Congratulations on training your own ControlNet! To learn more about how to use your new model, the following guides may be helpful:
 
-- Learn how to [use a ControlNet](../using-diffusers/controlnet) for inference on a variety of tasks.
+- Learn how to [use a ControlNet](../using-diffusers/controlnet) for inference on a variety of tasks.

docs/source/en/training/create_dataset.md

@@ -9,7 +9,7 @@ This guide will show you two ways to create a dataset to finetune on:
 
 <Tip>
 
-💡 Learn more about how to create an image dataset for training in the [Create an image dataset](https://huggingface.co/docs/datasets/image_dataset) guide.
+💡 Learn more about how to create an image dataset for training in the [Create an image dataset](https://huggingface.co/docs/datasets/image_dataset) guide. 
 
 </Tip>
 
@@ -39,7 +39,7 @@ accelerate launch train_unconditional.py \
 
 </Tip>
 
-Start by creating a dataset with the [`ImageFolder`](https://huggingface.co/docs/datasets/image_load#imagefolder) feature, which creates an `image` column containing the PIL-encoded images.
+Start by creating a dataset with the [`ImageFolder`](https://huggingface.co/docs/datasets/image_load#imagefolder) feature, which creates an `image` column containing the PIL-encoded images. 
 
 You can use the `data_dir` or `data_files` parameters to specify the location of the dataset. The `data_files` parameter supports mapping specific files to dataset splits like `train` or `test`:
 

docs/source/en/training/distributed_inference.md

@@ -55,7 +55,7 @@ To learn more, take a look at the [Distributed Inference with 🤗 Accelerate](h
 ### Device placement
 
 > [!WARNING]
-> This feature is experimental and its APIs might change in the future.
+> 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.
 
@@ -90,8 +90,8 @@ import torch
 max_memory = {0:"1GB", 1:"1GB"}
 pipeline = DiffusionPipeline.from_pretrained(
     "runwayml/stable-diffusion-v1-5",
-    torch_dtype=torch.float16,
-    use_safetensors=True,
+    torch_dtype=torch.float16, 
+    use_safetensors=True, 
     device_map="balanced",
 +   max_memory=max_memory
 )
@@ -99,7 +99,7 @@ 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.
+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`].
 

docs/source/en/training/dreambooth.md

@@ -440,198 +440,6 @@ Stable Diffusion XL (SDXL) is a powerful text-to-image model that generates high
 
 The SDXL training script is discussed in more detail in the [SDXL training](sdxl) guide.
 
-## DeepFloyd IF
-
-DeepFloyd IF is a cascading pixel diffusion model with three stages. The first stage generates a base image and the second and third stages progressively upscales the base image into a high-resolution 1024x1024 image. Use the [train_dreambooth_lora.py](https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/train_dreambooth_lora.py) or [train_dreambooth.py](https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/train_dreambooth.py) scripts to train a DeepFloyd IF model with LoRA or the full model.
-
-DeepFloyd IF uses predicted variance, but the Diffusers training scripts uses predicted error so the trained DeepFloyd IF models are switched to a fixed variance schedule. The training scripts will update the scheduler config of the fully trained model for you. However, when you load the saved LoRA weights you must also update the pipeline's scheduler config.
-
-```py
-from diffusers import DiffusionPipeline
-
-pipe = DiffusionPipeline.from_pretrained("DeepFloyd/IF-I-XL-v1.0", use_safetensors=True)
-
-pipe.load_lora_weights("<lora weights path>")
-
-# Update scheduler config to fixed variance schedule
-pipe.scheduler = pipe.scheduler.__class__.from_config(pipe.scheduler.config, variance_type="fixed_small")
-```
-
-The stage 2 model requires additional validation images to upscale. You can download and use a downsized version of the training images for this.
-
-```py
-from huggingface_hub import snapshot_download
-
-local_dir = "./dog_downsized"
-snapshot_download(
-    "diffusers/dog-example-downsized",
-    local_dir=local_dir,
-    repo_type="dataset",
-    ignore_patterns=".gitattributes",
-)
-```
-
-The code samples below provide a brief overview of how to train a DeepFloyd IF model with a combination of DreamBooth and LoRA. Some important parameters to note are:
-
-* `--resolution=64`, a much smaller resolution is required because DeepFloyd IF is a pixel diffusion model and to work on uncompressed pixels, the input images must be smaller
-* `--pre_compute_text_embeddings`, compute the text embeddings ahead of time to save memory because the [`~transformers.T5Model`] can take up a lot of memory
-* `--tokenizer_max_length=77`, you can use a longer default text length with T5 as the text encoder but the default model encoding procedure uses a shorter text length
-* `--text_encoder_use_attention_mask`, to pass the attention mask to the text encoder
-
-<hfoptions id="IF-DreamBooth">
-<hfoption id="Stage 1 LoRA DreamBooth">
-
-Training stage 1 of DeepFloyd IF with LoRA and DreamBooth requires ~28GB of memory.
-
-```bash
-export MODEL_NAME="DeepFloyd/IF-I-XL-v1.0"
-export INSTANCE_DIR="dog"
-export OUTPUT_DIR="dreambooth_dog_lora"
-
-accelerate launch train_dreambooth_lora.py \
-  --report_to wandb \
-  --pretrained_model_name_or_path=$MODEL_NAME  \
-  --instance_data_dir=$INSTANCE_DIR \
-  --output_dir=$OUTPUT_DIR \
-  --instance_prompt="a sks dog" \
-  --resolution=64 \
-  --train_batch_size=4 \
-  --gradient_accumulation_steps=1 \
-  --learning_rate=5e-6 \
-  --scale_lr \
-  --max_train_steps=1200 \
-  --validation_prompt="a sks dog" \
-  --validation_epochs=25 \
-  --checkpointing_steps=100 \
-  --pre_compute_text_embeddings \
-  --tokenizer_max_length=77 \
-  --text_encoder_use_attention_mask
-```
-
-</hfoption>
-<hfoption id="Stage 2 LoRA DreamBooth">
-
-For stage 2 of DeepFloyd IF with LoRA and DreamBooth, pay attention to these parameters:
-
-* `--validation_images`, the images to upscale during validation
-* `--class_labels_conditioning=timesteps`, to additionally conditional the UNet as needed in stage 2
-* `--learning_rate=1e-6`, a lower learning rate is used compared to stage 1
-* `--resolution=256`, the expected resolution for the upscaler
-
-```bash
-export MODEL_NAME="DeepFloyd/IF-II-L-v1.0"
-export INSTANCE_DIR="dog"
-export OUTPUT_DIR="dreambooth_dog_upscale"
-export VALIDATION_IMAGES="dog_downsized/image_1.png dog_downsized/image_2.png dog_downsized/image_3.png dog_downsized/image_4.png"
-
-python train_dreambooth_lora.py \
-    --report_to wandb \
-    --pretrained_model_name_or_path=$MODEL_NAME \
-    --instance_data_dir=$INSTANCE_DIR \
-    --output_dir=$OUTPUT_DIR \
-    --instance_prompt="a sks dog" \
-    --resolution=256 \
-    --train_batch_size=4 \
-    --gradient_accumulation_steps=1 \
-    --learning_rate=1e-6 \
-    --max_train_steps=2000 \
-    --validation_prompt="a sks dog" \
-    --validation_epochs=100 \
-    --checkpointing_steps=500 \
-    --pre_compute_text_embeddings \
-    --tokenizer_max_length=77 \
-    --text_encoder_use_attention_mask \
-    --validation_images $VALIDATION_IMAGES \
-    --class_labels_conditioning=timesteps
-```
-
-</hfoption>
-<hfoption id="Stage 1 DreamBooth">
-
-For stage 1 of DeepFloyd IF with DreamBooth, pay attention to these parameters:
-
-* `--skip_save_text_encoder`, to skip saving the full T5 text encoder with the finetuned model
-* `--use_8bit_adam`, to use 8-bit Adam optimizer to save memory due to the size of the optimizer state when training the full model
-* `--learning_rate=1e-7`, a really low learning rate should be used for full model training otherwise the model quality is degraded (you can use a higher learning rate with a larger batch size)
-
-Training with 8-bit Adam and a batch size of 4, the full model can be trained with ~48GB of memory.
-
-```bash
-export MODEL_NAME="DeepFloyd/IF-I-XL-v1.0"
-export INSTANCE_DIR="dog"
-export OUTPUT_DIR="dreambooth_if"
-
-accelerate launch train_dreambooth.py \
-  --pretrained_model_name_or_path=$MODEL_NAME  \
-  --instance_data_dir=$INSTANCE_DIR \
-  --output_dir=$OUTPUT_DIR \
-  --instance_prompt="a photo of sks dog" \
-  --resolution=64 \
-  --train_batch_size=4 \
-  --gradient_accumulation_steps=1 \
-  --learning_rate=1e-7 \
-  --max_train_steps=150 \
-  --validation_prompt "a photo of sks dog" \
-  --validation_steps 25 \
-  --text_encoder_use_attention_mask \
-  --tokenizer_max_length 77 \
-  --pre_compute_text_embeddings \
-  --use_8bit_adam \
-  --set_grads_to_none \
-  --skip_save_text_encoder \
-  --push_to_hub
-```
-
-</hfoption>
-<hfoption id="Stage 2 DreamBooth">
-
-For stage 2 of DeepFloyd IF with DreamBooth, pay attention to these parameters:
-
-* `--learning_rate=5e-6`, use a lower learning rate with a smaller effective batch size
-* `--resolution=256`, the expected resolution for the upscaler
-* `--train_batch_size=2` and `--gradient_accumulation_steps=6`, to effectively train on images wiht faces requires larger batch sizes
-
-```bash
-export MODEL_NAME="DeepFloyd/IF-II-L-v1.0"
-export INSTANCE_DIR="dog"
-export OUTPUT_DIR="dreambooth_dog_upscale"
-export VALIDATION_IMAGES="dog_downsized/image_1.png dog_downsized/image_2.png dog_downsized/image_3.png dog_downsized/image_4.png"
-
-accelerate launch train_dreambooth.py \
-  --report_to wandb \
-  --pretrained_model_name_or_path=$MODEL_NAME \
-  --instance_data_dir=$INSTANCE_DIR \
-  --output_dir=$OUTPUT_DIR \
-  --instance_prompt="a sks dog" \
-  --resolution=256 \
-  --train_batch_size=2 \
-  --gradient_accumulation_steps=6 \
-  --learning_rate=5e-6 \
-  --max_train_steps=2000 \
-  --validation_prompt="a sks dog" \
-  --validation_steps=150 \
-  --checkpointing_steps=500 \
-  --pre_compute_text_embeddings \
-  --tokenizer_max_length=77 \
-  --text_encoder_use_attention_mask \
-  --validation_images $VALIDATION_IMAGES \
-  --class_labels_conditioning timesteps \
-  --push_to_hub
-```
-
-</hfoption>
-</hfoptions>
-
-### Training tips
-
-Training the DeepFloyd IF model can be challenging, but here are some tips that we've found helpful:
-
-- LoRA is sufficient for training the stage 1 model because the model's low resolution makes representing finer details difficult regardless.
-- For common or simple objects, you don't necessarily need to finetune the upscaler. Make sure the prompt passed to the upscaler is adjusted to remove the new token from the instance prompt. For example, if your stage 1 prompt is "a sks dog" then your stage 2 prompt should be "a dog".
-- For finer details like faces, fully training the stage 2 upscaler is better than training the stage 2 model with LoRA. It also helps to use lower learning rates with larger batch sizes.
-- Lower learning rates should be used to train the stage 2 model.
-- The [`DDPMScheduler`] works better than the DPMSolver used in the training scripts.
-
 ## Next steps
 
 Congratulations on training your DreamBooth model! To learn more about how to use your new model, the following guide may be helpful:

docs/source/en/training/kandinsky.md

@@ -205,7 +205,7 @@ model_pred = unet(noisy_latents, timesteps, None, added_cond_kwargs=added_cond_k
 
 Once you’ve made all your changes or you’re okay with the default configuration, you’re ready to launch the training script! 🚀
 
-You'll train on the [Naruto BLIP captions](https://huggingface.co/datasets/lambdalabs/naruto-blip-captions) dataset to generate your own Naruto characters, but you can also create and train on your own dataset by following the [Create a dataset for training](create_dataset) guide. Set the environment variable `DATASET_NAME` to the name of the dataset on the Hub or if you're training on your own files, set the environment variable `TRAIN_DIR` to a path to your dataset.
+You'll train on the [Pokémon BLIP captions](https://huggingface.co/datasets/lambdalabs/pokemon-blip-captions) dataset to generate your own Pokémon, but you can also create and train on your own dataset by following the [Create a dataset for training](create_dataset) guide. Set the environment variable `DATASET_NAME` to the name of the dataset on the Hub or if you're training on your own files, set the environment variable `TRAIN_DIR` to a path to your dataset.
 
 If you’re training on more than one GPU, add the `--multi_gpu` parameter to the `accelerate launch` command.
 
@@ -219,7 +219,7 @@ To monitor training progress with Weights & Biases, add the `--report_to=wandb`
 <hfoption id="prior model">
 
 ```bash
-export DATASET_NAME="lambdalabs/naruto-blip-captions"
+export DATASET_NAME="lambdalabs/pokemon-blip-captions"
 
 accelerate launch --mixed_precision="fp16"  train_text_to_image_prior.py \
   --dataset_name=$DATASET_NAME \
@@ -232,17 +232,17 @@ accelerate launch --mixed_precision="fp16"  train_text_to_image_prior.py \
   --checkpoints_total_limit=3 \
   --lr_scheduler="constant" \
   --lr_warmup_steps=0 \
-  --validation_prompts="A robot naruto, 4k photo" \
+  --validation_prompts="A robot pokemon, 4k photo" \
   --report_to="wandb" \
   --push_to_hub \
-  --output_dir="kandi2-prior-naruto-model"
+  --output_dir="kandi2-prior-pokemon-model"
 ```
 
 </hfoption>
 <hfoption id="decoder model">
 
 ```bash
-export DATASET_NAME="lambdalabs/naruto-blip-captions"
+export DATASET_NAME="lambdalabs/pokemon-blip-captions"
 
 accelerate launch --mixed_precision="fp16"  train_text_to_image_decoder.py \
   --dataset_name=$DATASET_NAME \
@@ -256,10 +256,10 @@ accelerate launch --mixed_precision="fp16"  train_text_to_image_decoder.py \
   --checkpoints_total_limit=3 \
   --lr_scheduler="constant" \
   --lr_warmup_steps=0 \
-  --validation_prompts="A robot naruto, 4k photo" \
+  --validation_prompts="A robot pokemon, 4k photo" \
   --report_to="wandb" \
   --push_to_hub \
-  --output_dir="kandi2-decoder-naruto-model"
+  --output_dir="kandi2-decoder-pokemon-model"
 ```
 
 </hfoption>
@@ -279,7 +279,7 @@ prior_components = {"prior_" + k: v for k,v in prior_pipeline.components.items()
 pipeline = AutoPipelineForText2Image.from_pretrained("kandinsky-community/kandinsky-2-2-decoder", **prior_components, torch_dtype=torch.float16)
 
 pipe.enable_model_cpu_offload()
-prompt="A robot naruto, 4k photo"
+prompt="A robot pokemon, 4k photo"
 image = pipeline(prompt=prompt, negative_prompt=negative_prompt).images[0]
 ```
 
@@ -299,7 +299,7 @@ import torch
 pipeline = AutoPipelineForText2Image.from_pretrained("path/to/saved/model", torch_dtype=torch.float16)
 pipeline.enable_model_cpu_offload()
 
-prompt="A robot naruto, 4k photo"
+prompt="A robot pokemon, 4k photo"
 image = pipeline(prompt=prompt).images[0]
 ```
 
@@ -313,7 +313,7 @@ unet = UNet2DConditionModel.from_pretrained("path/to/saved/model" + "/checkpoint
 pipeline = AutoPipelineForText2Image.from_pretrained("kandinsky-community/kandinsky-2-2-decoder", unet=unet, torch_dtype=torch.float16)
 pipeline.enable_model_cpu_offload()
 
-image = pipeline(prompt="A robot naruto, 4k photo").images[0]
+image = pipeline(prompt="A robot pokemon, 4k photo").images[0]
 ```
 
 </hfoption>

docs/source/en/training/lora.md

@@ -170,7 +170,7 @@ Aside from setting up the LoRA layers, the training script is more or less the s
 
 Once you've made all your changes or you're okay with the default configuration, you're ready to launch the training script! 🚀
 
-Let's train on the [Naruto BLIP captions](https://huggingface.co/datasets/lambdalabs/naruto-blip-captions) dataset to generate your own Naruto characters. Set the environment variables `MODEL_NAME` and `DATASET_NAME` to the model and dataset respectively. You should also specify where to save the model in `OUTPUT_DIR`, and the name of the model to save to on the Hub with `HUB_MODEL_ID`. The script creates and saves the following files to your repository:
+Let's train on the [Pokémon BLIP captions](https://huggingface.co/datasets/lambdalabs/pokemon-blip-captions) dataset to generate our own Pokémon. Set the environment variables `MODEL_NAME` and `DATASET_NAME` to the model and dataset respectively. You should also specify where to save the model in `OUTPUT_DIR`, and the name of the model to save to on the Hub with `HUB_MODEL_ID`. The script creates and saves the following files to your repository:
 
 - saved model checkpoints
 - `pytorch_lora_weights.safetensors` (the trained LoRA weights)
@@ -185,9 +185,9 @@ A full training run takes ~5 hours on a 2080 Ti GPU with 11GB of VRAM.
 
 ```bash
 export MODEL_NAME="runwayml/stable-diffusion-v1-5"
-export OUTPUT_DIR="/sddata/finetune/lora/naruto"
-export HUB_MODEL_ID="naruto-lora"
-export DATASET_NAME="lambdalabs/naruto-blip-captions"
+export OUTPUT_DIR="/sddata/finetune/lora/pokemon"
+export HUB_MODEL_ID="pokemon-lora"
+export DATASET_NAME="lambdalabs/pokemon-blip-captions"
 
 accelerate launch --mixed_precision="fp16"  train_text_to_image_lora.py \
   --pretrained_model_name_or_path=$MODEL_NAME \
@@ -208,7 +208,7 @@ accelerate launch --mixed_precision="fp16"  train_text_to_image_lora.py \
   --hub_model_id=${HUB_MODEL_ID} \
   --report_to=wandb \
   --checkpointing_steps=500 \
-  --validation_prompt="A naruto with blue eyes." \
+  --validation_prompt="A pokemon with blue eyes." \
   --seed=1337
 ```
 
@@ -220,7 +220,7 @@ import torch
 
 pipeline = AutoPipelineForText2Image.from_pretrained("runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16).to("cuda")
 pipeline.load_lora_weights("path/to/lora/model", weight_name="pytorch_lora_weights.safetensors")
-image = pipeline("A naruto with blue eyes").images[0]
+image = pipeline("A pokemon with blue eyes").images[0]
 ```
 
 ## Next steps

docs/source/en/training/sdxl.md

@@ -176,7 +176,7 @@ If you want to learn more about how the training loop works, check out the [Unde
 
 Once you’ve made all your changes or you’re okay with the default configuration, you’re ready to launch the training script! 🚀
 
-Let’s train on the [Naruto BLIP captions](https://huggingface.co/datasets/lambdalabs/naruto-blip-captions) dataset to generate your own Naruto characters. Set the environment variables `MODEL_NAME` and `DATASET_NAME` to the model and the dataset (either from the Hub or a local path). You should also specify a VAE other than the SDXL VAE (either from the Hub or a local path) with `VAE_NAME` to avoid numerical instabilities.
+Let’s train on the [Pokémon BLIP captions](https://huggingface.co/datasets/lambdalabs/pokemon-blip-captions) dataset to generate your own Pokémon. Set the environment variables `MODEL_NAME` and `DATASET_NAME` to the model and the dataset (either from the Hub or a local path). You should also specify a VAE other than the SDXL VAE (either from the Hub or a local path) with `VAE_NAME` to avoid numerical instabilities.
 
 <Tip>
 
@@ -187,7 +187,7 @@ To monitor training progress with Weights & Biases, add the `--report_to=wandb`
 ```bash
 export MODEL_NAME="stabilityai/stable-diffusion-xl-base-1.0"
 export VAE_NAME="madebyollin/sdxl-vae-fp16-fix"
-export DATASET_NAME="lambdalabs/naruto-blip-captions"
+export DATASET_NAME="lambdalabs/pokemon-blip-captions"
 
 accelerate launch train_text_to_image_sdxl.py \
   --pretrained_model_name_or_path=$MODEL_NAME \
@@ -211,7 +211,7 @@ accelerate launch train_text_to_image_sdxl.py \
   --validation_prompt="a cute Sundar Pichai creature" \
   --validation_epochs 5 \
   --checkpointing_steps=5000 \
-  --output_dir="sdxl-naruto-model" \
+  --output_dir="sdxl-pokemon-model" \
   --push_to_hub
 ```
 
@@ -226,9 +226,9 @@ import torch
 
 pipeline = DiffusionPipeline.from_pretrained("path/to/your/model", torch_dtype=torch.float16).to("cuda")
 
-prompt = "A naruto with green eyes and red legs."
+prompt = "A pokemon with green eyes and red legs."
 image = pipeline(prompt, num_inference_steps=30, guidance_scale=7.5).images[0]
-image.save("naruto.png")
+image.save("pokemon.png")
 ```
 
 </hfoption>
@@ -244,11 +244,11 @@ import torch_xla.core.xla_model as xm
 device = xm.xla_device()
 pipeline = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0").to(device)
 
-prompt = "A naruto with green eyes and red legs."
+prompt = "A pokemon with green eyes and red legs."
 start = time()
 image = pipeline(prompt, num_inference_steps=inference_steps).images[0]
 print(f'Compilation time is {time()-start} sec')
-image.save("naruto.png")
+image.save("pokemon.png")
 
 start = time()
 image = pipeline(prompt, num_inference_steps=inference_steps).images[0]

docs/source/en/training/text2image.md

@@ -158,7 +158,7 @@ Once you've made all your changes or you're okay with the default configuration,
 <hfoptions id="training-inference">
 <hfoption id="PyTorch">
 
-Let's train on the [Naruto BLIP captions](https://huggingface.co/datasets/lambdalabs/naruto-blip-captions) dataset to generate your own Naruto characters. Set the environment variables `MODEL_NAME` and `dataset_name` to the model and the dataset (either from the Hub or a local path). If you're training on more than one GPU, add the `--multi_gpu` parameter to the `accelerate launch` command.
+Let's train on the [Pokémon BLIP captions](https://huggingface.co/datasets/lambdalabs/pokemon-blip-captions) dataset to generate your own Pokémon. Set the environment variables `MODEL_NAME` and `dataset_name` to the model and the dataset (either from the Hub or a local path). If you're training on more than one GPU, add the `--multi_gpu` parameter to the `accelerate launch` command.
 
 <Tip>
 
@@ -168,7 +168,7 @@ To train on a local dataset, set the `TRAIN_DIR` and `OUTPUT_DIR` environment va
 
 ```bash
 export MODEL_NAME="runwayml/stable-diffusion-v1-5"
-export dataset_name="lambdalabs/naruto-blip-captions"
+export dataset_name="lambdalabs/pokemon-blip-captions"
 
 accelerate launch --mixed_precision="fp16"  train_text_to_image.py \
   --pretrained_model_name_or_path=$MODEL_NAME \
@@ -181,9 +181,9 @@ 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" \
+  --output_dir="sd-pokemon-model" \
   --push_to_hub
 ```
 
@@ -202,7 +202,7 @@ To train on a local dataset, set the `TRAIN_DIR` and `OUTPUT_DIR` environment va
 
 ```bash
 export MODEL_NAME="runwayml/stable-diffusion-v1-5"
-export dataset_name="lambdalabs/naruto-blip-captions"
+export dataset_name="lambdalabs/pokemon-blip-captions"
 
 python train_text_to_image_flax.py \
   --pretrained_model_name_or_path=$MODEL_NAME \
@@ -212,7 +212,7 @@ python train_text_to_image_flax.py \
   --max_train_steps=15000 \
   --learning_rate=1e-05 \
   --max_grad_norm=1 \
-  --output_dir="sd-naruto-model" \
+  --output_dir="sd-pokemon-model" \
   --push_to_hub
 ```
 
@@ -231,7 +231,7 @@ import torch
 pipeline = StableDiffusionPipeline.from_pretrained("path/to/saved_model", torch_dtype=torch.float16, use_safetensors=True).to("cuda")
 
 image = pipeline(prompt="yoda").images[0]
-image.save("yoda-naruto.png")
+image.save("yoda-pokemon.png")
 ```
 
 </hfoption>
@@ -246,7 +246,7 @@ from diffusers import FlaxStableDiffusionPipeline
 
 pipeline, params = FlaxStableDiffusionPipeline.from_pretrained("path/to/saved_model", dtype=jax.numpy.bfloat16)
 
-prompt = "yoda naruto"
+prompt = "yoda pokemon"
 prng_seed = jax.random.PRNGKey(0)
 num_inference_steps = 50
 
@@ -261,7 +261,7 @@ prompt_ids = shard(prompt_ids)
 
 images = pipeline(prompt_ids, params, prng_seed, num_inference_steps, jit=True).images
 images = pipeline.numpy_to_pil(np.asarray(images.reshape((num_samples,) + images.shape[-3:])))
-image.save("yoda-naruto.png")
+image.save("yoda-pokemon.png")
 ```
 
 </hfoption>

docs/source/en/training/wuerstchen.md

@@ -131,7 +131,7 @@ If you want to learn more about how the training loop works, check out the [Unde
 
 Once you’ve made all your changes or you’re okay with the default configuration, you’re ready to launch the training script! 🚀
 
-Set the `DATASET_NAME` environment variable to the dataset name from the Hub. This guide uses the [Naruto BLIP captions](https://huggingface.co/datasets/lambdalabs/naruto-blip-captions) dataset, but you can create and train on your own datasets as well (see the [Create a dataset for training](create_dataset) guide).
+Set the `DATASET_NAME` environment variable to the dataset name from the Hub. This guide uses the [Pokémon BLIP captions](https://huggingface.co/datasets/lambdalabs/pokemon-blip-captions) dataset, but you can create and train on your own datasets as well (see the [Create a dataset for training](create_dataset) guide).
 
 <Tip>
 
@@ -140,7 +140,7 @@ To monitor training progress with Weights & Biases, add the `--report_to=wandb`
 </Tip>
 
 ```bash
-export DATASET_NAME="lambdalabs/naruto-blip-captions"
+export DATASET_NAME="lambdalabs/pokemon-blip-captions"
 
 accelerate launch  train_text_to_image_prior.py \
   --mixed_precision="fp16" \
@@ -156,10 +156,10 @@ accelerate launch  train_text_to_image_prior.py \
   --checkpoints_total_limit=3 \
   --lr_scheduler="constant" \
   --lr_warmup_steps=0 \
-  --validation_prompts="A robot naruto, 4k photo" \
+  --validation_prompts="A robot pokemon, 4k photo" \
   --report_to="wandb" \
   --push_to_hub \
-  --output_dir="wuerstchen-prior-naruto-model"
+  --output_dir="wuerstchen-prior-pokemon-model"
 ```
 
 Once training is complete, you can use your newly trained model for inference!
@@ -171,7 +171,7 @@ from diffusers.pipelines.wuerstchen import DEFAULT_STAGE_C_TIMESTEPS
 
 pipeline = AutoPipelineForText2Image.from_pretrained("path/to/saved/model", torch_dtype=torch.float16).to("cuda")
 
-caption = "A cute bird naruto holding a shield"
+caption = "A cute bird pokemon holding a shield"
 images = pipeline(
     caption,
     width=1024,

docs/source/en/tutorials/basic_training.md

@@ -260,7 +260,7 @@ Then, you'll need a way to evaluate the model. For evaluation, you can use the [
 ...     # The default pipeline output type is `List[PIL.Image]`
 ...     images = pipeline(
 ...         batch_size=config.eval_batch_size,
-...         generator=torch.Generator(device='cpu').manual_seed(config.seed), # Use a separate torch generator to avoid rewinding the random state of the main training loop
+...         generator=torch.manual_seed(config.seed),
 ...     ).images
 
 ...     # Make a grid out of the images

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.
@@ -222,7 +222,7 @@ First, configure all the compiler tags:
 
 ```python
 from diffusers import StableDiffusionXLPipeline
-import torch
+import torch 
 
 # Notice the two new flags at the end.
 torch._inductor.config.conv_1x1_as_mm = True

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

@@ -19,74 +19,13 @@ The denoising loop of a pipeline can be modified with custom defined functions u
 
 This guide will demonstrate how callbacks work by a few features you can implement with them.
 
-## Official callbacks
-
-We provide a list of callbacks you can plug into an existing pipeline and modify the denoising loop. This is the current list of official callbacks:
-
-- `SDCFGCutoffCallback`: Disables the CFG after a certain number of steps for all SD 1.5 pipelines, including text-to-image, image-to-image, inpaint, and controlnet.
-- `SDXLCFGCutoffCallback`: Disables the CFG after a certain number of steps for all SDXL pipelines, including text-to-image, image-to-image, inpaint, and controlnet.
-- `IPAdapterScaleCutoffCallback`: Disables the IP Adapter after a certain number of steps for all pipelines supporting IP-Adapter.
-
-> [!TIP]
-> If you want to add a new official callback, feel free to open a [feature request](https://github.com/huggingface/diffusers/issues/new/choose) or [submit a PR](https://huggingface.co/docs/diffusers/main/en/conceptual/contribution#how-to-open-a-pr).
-
-To set up a callback, you need to specify the number of denoising steps after which the callback comes into effect. You can do so by using either one of these two arguments
-
-- `cutoff_step_ratio`: Float number with the ratio of the steps.
-- `cutoff_step_index`: Integer number with the exact number of the step.
-
-```python
-import torch
-
-from diffusers import DPMSolverMultistepScheduler, StableDiffusionXLPipeline
-from diffusers.callbacks import SDXLCFGCutoffCallback
-
-
-callback = SDXLCFGCutoffCallback(cutoff_step_ratio=0.4)
-# can also be used with cutoff_step_index
-# callback = SDXLCFGCutoffCallback(cutoff_step_ratio=None, cutoff_step_index=10)
-
-pipeline = StableDiffusionXLPipeline.from_pretrained(
-    "stabilityai/stable-diffusion-xl-base-1.0",
-    torch_dtype=torch.float16,
-    variant="fp16",
-).to("cuda")
-pipeline.scheduler = DPMSolverMultistepScheduler.from_config(pipeline.scheduler.config, use_karras_sigmas=True)
-
-prompt = "a sports car at the road, best quality, high quality, high detail, 8k resolution"
-
-generator = torch.Generator(device="cpu").manual_seed(2628670641)
-
-out = pipeline(
-    prompt=prompt,
-    negative_prompt="",
-    guidance_scale=6.5,
-    num_inference_steps=25,
-    generator=generator,
-    callback_on_step_end=callback,
-)
-
-out.images[0].save("official_callback.png")
-```
-
-<div class="flex gap-4">
-  <div>
-    <img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/without_cfg_callback.png" alt="generated image of a sports car at the road" />
-    <figcaption class="mt-2 text-center text-sm text-gray-500">without SDXLCFGCutoffCallback</figcaption>
-  </div>
-  <div>
-    <img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/with_cfg_callback.png" alt="generated image of a a sports car at the road with cfg callback" />
-    <figcaption class="mt-2 text-center text-sm text-gray-500">with SDXLCFGCutoffCallback</figcaption>
-  </div>
-</div>
-
 ## Dynamic classifier-free guidance
 
 Dynamic classifier-free guidance (CFG) is a feature that allows you to disable CFG after a certain number of inference steps which can help you save compute with minimal cost to performance. The callback function for this should have the following arguments:
 
-- `pipeline` (or the pipeline instance) provides access to important properties such as `num_timesteps` and `guidance_scale`. You can modify these properties by updating the underlying attributes. For this example, you'll disable CFG by setting `pipeline._guidance_scale=0.0`.
-- `step_index` and `timestep` tell you where you are in the denoising loop. Use `step_index` to turn off CFG after reaching 40% of `num_timesteps`.
-- `callback_kwargs` is a dict that contains tensor variables you can modify during the denoising loop. It only includes variables specified in the `callback_on_step_end_tensor_inputs` argument, which is passed to the pipeline's `__call__` method. Different pipelines may use different sets of variables, so please check a pipeline's `_callback_tensor_inputs` attribute for the list of variables you can modify. Some common variables include `latents` and `prompt_embeds`. For this function, change the batch size of `prompt_embeds` after setting `guidance_scale=0.0` in order for it to work properly.
+* `pipeline` (or the pipeline instance) provides access to important properties such as `num_timesteps` and `guidance_scale`. You can modify these properties by updating the underlying attributes. For this example, you'll disable CFG by setting `pipeline._guidance_scale=0.0`.
+* `step_index` and `timestep` tell you where you are in the denoising loop. Use `step_index` to turn off CFG after reaching 40% of `num_timesteps`.
+* `callback_kwargs` is a dict that contains tensor variables you can modify during the denoising loop. It only includes variables specified in the `callback_on_step_end_tensor_inputs` argument, which is passed to the pipeline's `__call__` method. Different pipelines may use different sets of variables, so please check a pipeline's `_callback_tensor_inputs` attribute for the list of variables you can modify. Some common variables include `latents` and `prompt_embeds`. For this function, change the batch size of `prompt_embeds` after setting `guidance_scale=0.0` in order for it to work properly.
 
 Your callback function should look something like this:
 
@@ -188,7 +127,7 @@ def latents_to_rgb(latents):
 ```py
 def decode_tensors(pipe, step, timestep, callback_kwargs):
     latents = callback_kwargs["latents"]
-
+    
     image = latents_to_rgb(latents)
     image.save(f"{step}.png")
 

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

@@ -0,0 +1,184 @@
+<!--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.
+-->
+
+# Contribute a community pipeline
+
+<Tip>
+
+💡 Take a look at GitHub Issue [#841](https://github.com/huggingface/diffusers/issues/841) for more context about why we're adding community pipelines to help everyone easily share their work without being slowed down.
+
+</Tip>
+
+Community pipelines allow you to add any additional features you'd like on top of the [`DiffusionPipeline`]. The main benefit of building on top of the `DiffusionPipeline` is anyone can load and use your pipeline by only adding one more argument, making it super easy for the community to access.
+
+This guide will show you how to create a community pipeline and explain how they work. To keep things simple, you'll create a "one-step" pipeline where the `UNet` does a single forward pass and calls the scheduler once.
+
+## Initialize the pipeline
+
+You should start by creating a `one_step_unet.py` file for your community pipeline. In this file, create a pipeline class that inherits from the [`DiffusionPipeline`] to be able to load model weights and the scheduler configuration from the Hub. The one-step pipeline needs a `UNet` and a scheduler, so you'll need to add these as arguments to the `__init__` function:
+
+```python
+from diffusers import DiffusionPipeline
+import torch
+
+class UnetSchedulerOneForwardPipeline(DiffusionPipeline):
+    def __init__(self, unet, scheduler):
+        super().__init__()
+```
+
+To ensure your pipeline and its components (`unet` and `scheduler`) can be saved with [`~DiffusionPipeline.save_pretrained`], add them to the `register_modules` function:
+
+```diff
+  from diffusers import DiffusionPipeline
+  import torch
+
+  class UnetSchedulerOneForwardPipeline(DiffusionPipeline):
+      def __init__(self, unet, scheduler):
+          super().__init__()
+
++         self.register_modules(unet=unet, scheduler=scheduler)
+```
+
+Cool, the `__init__` step is done and you can move to the forward pass now! 🔥
+
+## Define the forward pass
+
+In the forward pass, which we recommend defining as `__call__`, you have complete creative freedom to add whatever feature you'd like. For our amazing one-step pipeline, create a random image and only call the `unet` and `scheduler` once by setting `timestep=1`:
+
+```diff
+  from diffusers import DiffusionPipeline
+  import torch
+
+  class UnetSchedulerOneForwardPipeline(DiffusionPipeline):
+      def __init__(self, unet, scheduler):
+          super().__init__()
+
+          self.register_modules(unet=unet, scheduler=scheduler)
+
++     def __call__(self):
++         image = torch.randn(
++             (1, self.unet.config.in_channels, self.unet.config.sample_size, self.unet.config.sample_size),
++         )
++         timestep = 1
+
++         model_output = self.unet(image, timestep).sample
++         scheduler_output = self.scheduler.step(model_output, timestep, image).prev_sample
+
++         return scheduler_output
+```
+
+That's it! 🚀 You can now run this pipeline by passing a `unet` and `scheduler` to it:
+
+```python
+from diffusers import DDPMScheduler, UNet2DModel
+
+scheduler = DDPMScheduler()
+unet = UNet2DModel()
+
+pipeline = UnetSchedulerOneForwardPipeline(unet=unet, scheduler=scheduler)
+
+output = pipeline()
+```
+
+But what's even better is you can load pre-existing weights into the pipeline if the pipeline structure is identical. For example, you can load the [`google/ddpm-cifar10-32`](https://huggingface.co/google/ddpm-cifar10-32) weights into the one-step pipeline:
+
+```python
+pipeline = UnetSchedulerOneForwardPipeline.from_pretrained("google/ddpm-cifar10-32", use_safetensors=True)
+
+output = pipeline()
+```
+
+## Share your pipeline
+
+Open a Pull Request on the 🧨 Diffusers [repository](https://github.com/huggingface/diffusers) to add your awesome pipeline in `one_step_unet.py` to the [examples/community](https://github.com/huggingface/diffusers/tree/main/examples/community) subfolder.
+
+Once it is merged, anyone with `diffusers >= 0.4.0` installed can use this pipeline magically 🪄 by specifying it in the `custom_pipeline` argument:
+
+```python
+from diffusers import DiffusionPipeline
+
+pipe = DiffusionPipeline.from_pretrained(
+    "google/ddpm-cifar10-32", custom_pipeline="one_step_unet", use_safetensors=True
+)
+pipe()
+```
+
+Another way to share your community pipeline is to upload the `one_step_unet.py` file directly to your preferred [model repository](https://huggingface.co/docs/hub/models-uploading) on the Hub. Instead of specifying the `one_step_unet.py` file, pass the model repository id to the `custom_pipeline` argument:
+
+```python
+from diffusers import DiffusionPipeline
+
+pipeline = DiffusionPipeline.from_pretrained(
+    "google/ddpm-cifar10-32", custom_pipeline="stevhliu/one_step_unet", use_safetensors=True
+)
+```
+
+Take a look at the following table to compare the two sharing workflows to help you decide the best option for you:
+
+|                | GitHub community pipeline                                                                                        | HF Hub community pipeline                                                                 |
+|----------------|------------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------|
+| usage          | same                                                                                                             | same                                                                                      |
+| review process | open a Pull Request on GitHub and undergo a review process from the Diffusers team before merging; may be slower | upload directly to a Hub repository without any review; this is the fastest workflow      |
+| visibility     | included in the official Diffusers repository and documentation                                                  | included on your HF Hub profile and relies on your own usage/promotion to gain visibility |
+
+<Tip>
+
+💡 You can use whatever package you want in your community pipeline file - as long as the user has it installed, everything will work fine. Make sure you have one and only one pipeline class that inherits from `DiffusionPipeline` because this is automatically detected.
+
+</Tip>
+
+## How do community pipelines work?
+
+A community pipeline is a class that inherits from [`DiffusionPipeline`] which means:
+
+- It can be loaded with the [`custom_pipeline`] argument.
+- The model weights and scheduler configuration are loaded from [`pretrained_model_name_or_path`].
+- The code that implements a feature in the community pipeline is defined in a `pipeline.py` file.
+
+Sometimes you can't load all the pipeline components weights from an official repository. In this case, the other components should be passed directly to the pipeline:
+
+```python
+from diffusers import DiffusionPipeline
+from transformers import CLIPImageProcessor, CLIPModel
+
+model_id = "CompVis/stable-diffusion-v1-4"
+clip_model_id = "laion/CLIP-ViT-B-32-laion2B-s34B-b79K"
+
+feature_extractor = CLIPImageProcessor.from_pretrained(clip_model_id)
+clip_model = CLIPModel.from_pretrained(clip_model_id, torch_dtype=torch.float16)
+
+pipeline = DiffusionPipeline.from_pretrained(
+    model_id,
+    custom_pipeline="clip_guided_stable_diffusion",
+    clip_model=clip_model,
+    feature_extractor=feature_extractor,
+    scheduler=scheduler,
+    torch_dtype=torch.float16,
+    use_safetensors=True,
+)
+```
+
+The magic behind community pipelines is contained in the following code. It allows the community pipeline to be loaded from GitHub or the Hub, and it'll be available to all 🧨 Diffusers packages.
+
+```python
+# 2. Load the pipeline class, if using custom module then load it from the Hub
+# if we load from explicit class, let's use it
+if custom_pipeline is not None:
+    pipeline_class = get_class_from_dynamic_module(
+        custom_pipeline, module_file=CUSTOM_PIPELINE_FILE_NAME, cache_dir=custom_pipeline
+    )
+elif cls != DiffusionPipeline:
+    pipeline_class = cls
+else:
+    diffusers_module = importlib.import_module(cls.__module__.split(".")[0])
+    pipeline_class = getattr(diffusers_module, config_dict["_class_name"])
+```

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

@@ -506,7 +506,7 @@ make_image_grid([original_image, canny_image], rows=1, cols=2)
 </div>
 
 For human pose estimation, install [controlnet_aux](https://github.com/patrickvonplaten/controlnet_aux):
-
+  
 ```py
 # uncomment to install the necessary library in Colab
 #!pip install -q controlnet-aux

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

@@ -0,0 +1,119 @@
+<!--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 pipelines
+
+[[open-in-colab]]
+
+<Tip>
+
+For more context about the design choices behind community pipelines, please have a look at [this issue](https://github.com/huggingface/diffusers/issues/841).
+
+</Tip>
+
+Community pipelines allow you to get creative and build your own unique pipelines to share with the community. You can find all community pipelines in the [diffusers/examples/community](https://github.com/huggingface/diffusers/tree/main/examples/community) folder along with inference and training examples for how to use them. This guide showcases some of the community pipelines and hopefully it'll inspire you to create your own (feel free to open a PR with your own pipeline and we will merge it!).
+
+To load a community pipeline, use the `custom_pipeline` argument in [`DiffusionPipeline`] to specify one of the files in [diffusers/examples/community](https://github.com/huggingface/diffusers/tree/main/examples/community):
+
+```py
+from diffusers import DiffusionPipeline
+
+pipe = DiffusionPipeline.from_pretrained(
+    "CompVis/stable-diffusion-v1-4", custom_pipeline="filename_in_the_community_folder", use_safetensors=True
+)
+```
+
+If a community pipeline doesn't work as expected, please open a GitHub issue and mention the author.
+
+You can learn more about community pipelines in the how to [load community pipelines](custom_pipeline_overview) and how to [contribute a community pipeline](contribute_pipeline) guides.
+
+## Multilingual Stable Diffusion
+
+The multilingual Stable Diffusion pipeline uses a pretrained [XLM-RoBERTa](https://huggingface.co/papluca/xlm-roberta-base-language-detection) to identify a language and the [mBART-large-50](https://huggingface.co/facebook/mbart-large-50-many-to-one-mmt) model to handle the translation. This allows you to generate images from text in 20 languages.
+
+```py
+import torch
+from diffusers import DiffusionPipeline
+from diffusers.utils import make_image_grid
+from transformers import (
+    pipeline,
+    MBart50TokenizerFast,
+    MBartForConditionalGeneration,
+)
+
+device = "cuda" if torch.cuda.is_available() else "cpu"
+device_dict = {"cuda": 0, "cpu": -1}
+
+# add language detection pipeline
+language_detection_model_ckpt = "papluca/xlm-roberta-base-language-detection"
+language_detection_pipeline = pipeline("text-classification",
+                                       model=language_detection_model_ckpt,
+                                       device=device_dict[device])
+
+# add model for language translation
+translation_tokenizer = MBart50TokenizerFast.from_pretrained("facebook/mbart-large-50-many-to-one-mmt")
+translation_model = MBartForConditionalGeneration.from_pretrained("facebook/mbart-large-50-many-to-one-mmt").to(device)
+
+diffuser_pipeline = DiffusionPipeline.from_pretrained(
+    "CompVis/stable-diffusion-v1-4",
+    custom_pipeline="multilingual_stable_diffusion",
+    detection_pipeline=language_detection_pipeline,
+    translation_model=translation_model,
+    translation_tokenizer=translation_tokenizer,
+    torch_dtype=torch.float16,
+)
+
+diffuser_pipeline.enable_attention_slicing()
+diffuser_pipeline = diffuser_pipeline.to(device)
+
+prompt = ["a photograph of an astronaut riding a horse",
+          "Una casa en la playa",
+          "Ein Hund, der Orange isst",
+          "Un restaurant parisien"]
+
+images = diffuser_pipeline(prompt).images
+make_image_grid(images, rows=2, cols=2)
+```
+
+<div class="flex justify-center">
+    <img src="https://user-images.githubusercontent.com/4313860/198328706-295824a4-9856-4ce5-8e66-278ceb42fd29.png"/>
+</div>
+
+## MagicMix
+
+[MagicMix](https://huggingface.co/papers/2210.16056) is a pipeline that can mix an image and text prompt to generate a new image that preserves the image structure. The `mix_factor` determines how much influence the prompt has on the layout generation, `kmin` controls the number of steps during the content generation process, and `kmax` determines how much information is kept in the layout of the original image.
+
+```py
+from diffusers import DiffusionPipeline, DDIMScheduler
+from diffusers.utils import load_image, make_image_grid
+
+pipeline = DiffusionPipeline.from_pretrained(
+    "CompVis/stable-diffusion-v1-4",
+    custom_pipeline="magic_mix",
+    scheduler=DDIMScheduler.from_pretrained("CompVis/stable-diffusion-v1-4", subfolder="scheduler"),
+).to('cuda')
+
+img = load_image("https://user-images.githubusercontent.com/59410571/209578593-141467c7-d831-4792-8b9a-b17dc5e47816.jpg")
+mix_img = pipeline(img, prompt="bed", kmin=0.3, kmax=0.5, mix_factor=0.5)
+make_image_grid([img, mix_img], rows=1, cols=2)
+```
+
+<div class="flex gap-4">
+  <div>
+    <img class="rounded-xl" src="https://user-images.githubusercontent.com/59410571/209578593-141467c7-d831-4792-8b9a-b17dc5e47816.jpg" />
+    <figcaption class="mt-2 text-center text-sm text-gray-500">original image</figcaption>
+  </div>
+  <div>
+    <img class="rounded-xl" src="https://user-images.githubusercontent.com/59410571/209578602-70f323fa-05b7-4dd6-b055-e40683e37914.jpg" />
+    <figcaption class="mt-2 text-center text-sm text-gray-500">image and text prompt mix</figcaption>
+  </div>
+</div>

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

@@ -16,19 +16,11 @@ specific language governing permissions and limitations under the License.
 
 ## Community pipelines
 
-> [!TIP] Take a look at GitHub Issue [#841](https://github.com/huggingface/diffusers/issues/841) for more context about why we're adding community pipelines to help everyone easily share their work without being slowed down.
-
 Community pipelines are any [`DiffusionPipeline`] class that are different from the original paper implementation (for example, the [`StableDiffusionControlNetPipeline`] corresponds to the [Text-to-Image Generation with ControlNet Conditioning](https://arxiv.org/abs/2302.05543) paper). They provide additional functionality or extend the original implementation of a pipeline.
 
 There are many cool community pipelines like [Marigold Depth Estimation](https://github.com/huggingface/diffusers/tree/main/examples/community#marigold-depth-estimation) or [InstantID](https://github.com/huggingface/diffusers/tree/main/examples/community#instantid-pipeline), and you can find all the official community pipelines [here](https://github.com/huggingface/diffusers/tree/main/examples/community).
 
-There are two types of community pipelines, those stored on the Hugging Face Hub and those stored on Diffusers GitHub repository. Hub pipelines are completely customizable (scheduler, models, pipeline code, etc.) while Diffusers GitHub pipelines are only limited to custom pipeline code.
-
-|                | GitHub community pipeline                                                                                        | HF Hub community pipeline                                                                 |
-|----------------|------------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------|
-| usage          | same                                                                                                             | same                                                                                      |
-| review process | open a Pull Request on GitHub and undergo a review process from the Diffusers team before merging; may be slower | upload directly to a Hub repository without any review; this is the fastest workflow      |
-| visibility     | included in the official Diffusers repository and documentation                                                  | included on your HF Hub profile and relies on your own usage/promotion to gain visibility |
+There are two types of community pipelines, those stored on the Hugging Face Hub and those stored on Diffusers GitHub repository. Hub pipelines are completely customizable (scheduler, models, pipeline code, etc.) while Diffusers GitHub pipelines are only limited to custom pipeline code. Refer to this [table](./contribute_pipeline#share-your-pipeline) for a more detailed comparison of Hub vs GitHub community pipelines.
 
 <hfoptions id="community">
 <hfoption id="Hub pipelines">
@@ -147,11 +139,11 @@ prompt = "cat, hiding in the leaves, ((rain)), zazie rainyday, beautiful eyes, m
 neg_prompt = "(deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime, mutated hands and fingers:1.4), (deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, amputation"
 generator = torch.Generator(device="cpu").manual_seed(20)
 out_lpw = pipe_lpw(
-    prompt,
-    negative_prompt=neg_prompt,
+    prompt, 
+    negative_prompt=neg_prompt, 
     width=512,
     height=512,
-    max_embeddings_multiples=3,
+    max_embeddings_multiples=3, 
     num_inference_steps=50,
     generator=generator,
     ).images[0]
@@ -169,97 +161,6 @@ out_lpw
   </div>
 </div>
 
-## Example community pipelines
-
-Community pipelines are a really fun and creative way to extend the capabilities of the original pipeline with new and unique features. You can find all community pipelines in the [diffusers/examples/community](https://github.com/huggingface/diffusers/tree/main/examples/community) folder with inference and training examples for how to use them.
-
-This section showcases a couple of the community pipelines and hopefully it'll inspire you to create your own (feel free to open a PR for your community pipeline and ping us for a review)!
-
-> [!TIP]
-> The [`~DiffusionPipeline.from_pipe`] method is particularly useful for loading community pipelines because many of them don't have pretrained weights and add a feature on top of an existing pipeline like Stable Diffusion or Stable Diffusion XL. You can learn more about the [`~DiffusionPipeline.from_pipe`] method in the [Load with from_pipe](custom_pipeline_overview#load-with-from_pipe) section.
-
-<hfoptions id="community">
-<hfoption id="Marigold">
-
-[Marigold](https://marigoldmonodepth.github.io/) is a depth estimation diffusion pipeline that uses the rich existing and inherent visual knowledge in diffusion models. It takes an input image and denoises and decodes it into a depth map. Marigold performs well even on images it hasn't seen before.
-
-```py
-import torch
-from PIL import Image
-from diffusers import DiffusionPipeline
-from diffusers.utils import load_image
-
-pipeline = DiffusionPipeline.from_pretrained(
-    "prs-eth/marigold-lcm-v1-0",
-    custom_pipeline="marigold_depth_estimation",
-    torch_dtype=torch.float16,
-    variant="fp16",
-)
-
-pipeline.to("cuda")
-image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/community-marigold.png")
-output = pipeline(
-    image,
-    denoising_steps=4,
-    ensemble_size=5,
-    processing_res=768,
-    match_input_res=True,
-    batch_size=0,
-    seed=33,
-    color_map="Spectral",
-    show_progress_bar=True,
-)
-depth_colored: Image.Image = output.depth_colored
-depth_colored.save("./depth_colored.png")
-```
-
-<div class="flex flex-row gap-4">
-  <div class="flex-1">
-    <img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/community-marigold.png"/>
-    <figcaption class="mt-2 text-center text-sm text-gray-500">original image</figcaption>
-  </div>
-  <div class="flex-1">
-    <img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/marigold-depth.png"/>
-    <figcaption class="mt-2 text-center text-sm text-gray-500">colorized depth image</figcaption>
-  </div>
-</div>
-
-</hfoption>
-<hfoption id="HD-Painter">
-
-[HD-Painter](https://hf.co/papers/2312.14091) is a high-resolution inpainting pipeline. It introduces a *Prompt-Aware Introverted Attention (PAIntA)* layer to better align a prompt with the area to be inpainted, and *Reweighting Attention Score Guidance (RASG)* to keep the latents more prompt-aligned and within their trained domain to generate realistc images.
-
-```py
-import torch
-from diffusers import DiffusionPipeline, DDIMScheduler
-from diffusers.utils import load_image
-
-pipeline = DiffusionPipeline.from_pretrained(
-    "Lykon/dreamshaper-8-inpainting",
-    custom_pipeline="hd_painter"
-)
-pipeline.scheduler = DDIMScheduler.from_config(pipeline.scheduler.config)
-init_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/hd-painter.jpg")
-mask_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/hd-painter-mask.png")
-prompt = "football"
-image = pipeline(prompt, init_image, mask_image, use_rasg=True, use_painta=True, generator=torch.manual_seed(0)).images[0]
-image
-```
-
-<div class="flex flex-row gap-4">
-  <div class="flex-1">
-    <img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/hd-painter.jpg"/>
-    <figcaption class="mt-2 text-center text-sm text-gray-500">original image</figcaption>
-  </div>
-  <div class="flex-1">
-    <img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/hd-painter-output.png"/>
-    <figcaption class="mt-2 text-center text-sm text-gray-500">generated image</figcaption>
-  </div>
-</div>
-
-</hfoption>
-</hfoptions>
-
 ## Community components
 
 Community components allow users to build pipelines that may have customized components that are not a part of Diffusers. If your pipeline has custom components that Diffusers doesn't already support, you need to provide their implementations as Python modules. These customized components could be a VAE, UNet, and scheduler. In most cases, the text encoder is imported from the Transformers library. The pipeline code itself can also be customized.

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

@@ -0,0 +1,133 @@
+<!--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.
+-->
+
+# Distilled Stable Diffusion inference
+
+[[open-in-colab]]
+
+Stable Diffusion inference can be a computationally intensive process because it must iteratively denoise the latents to generate an image. To reduce the computational burden, you can use a *distilled* version of the Stable Diffusion model from [Nota AI](https://huggingface.co/nota-ai). The distilled version of their Stable Diffusion model eliminates some of the residual and attention blocks from the UNet, reducing the model size by 51% and improving latency on CPU/GPU by 43%.
+
+<Tip>
+
+Read this [blog post](https://huggingface.co/blog/sd_distillation) to learn more about how knowledge distillation training works to produce a faster, smaller, and cheaper generative model.
+
+</Tip>
+
+Let's load the distilled Stable Diffusion model and compare it against the original Stable Diffusion model:
+
+```py
+from diffusers import StableDiffusionPipeline
+import torch
+
+distilled = StableDiffusionPipeline.from_pretrained(
+    "nota-ai/bk-sdm-small", torch_dtype=torch.float16, use_safetensors=True,
+).to("cuda")
+
+original = StableDiffusionPipeline.from_pretrained(
+    "CompVis/stable-diffusion-v1-4", torch_dtype=torch.float16, use_safetensors=True,
+).to("cuda")
+```
+
+Given a prompt, get the inference time for the original model:
+
+```py
+import time
+
+seed = 2023
+generator = torch.manual_seed(seed)
+
+NUM_ITERS_TO_RUN = 3
+NUM_INFERENCE_STEPS = 25
+NUM_IMAGES_PER_PROMPT = 4
+
+prompt = "a golden vase with different flowers"
+
+start = time.time_ns()
+for _ in range(NUM_ITERS_TO_RUN):
+    images = original(
+        prompt,
+        num_inference_steps=NUM_INFERENCE_STEPS,
+        generator=generator,
+        num_images_per_prompt=NUM_IMAGES_PER_PROMPT
+    ).images
+end = time.time_ns()
+original_sd = f"{(end - start) / 1e6:.1f}"
+
+print(f"Execution time -- {original_sd} ms\n")
+"Execution time -- 45781.5 ms"
+```
+
+Time the distilled model inference:
+
+```py
+start = time.time_ns()
+for _ in range(NUM_ITERS_TO_RUN):
+    images = distilled(
+        prompt,
+        num_inference_steps=NUM_INFERENCE_STEPS,
+        generator=generator,
+        num_images_per_prompt=NUM_IMAGES_PER_PROMPT
+    ).images
+end = time.time_ns()
+
+distilled_sd = f"{(end - start) / 1e6:.1f}"
+print(f"Execution time -- {distilled_sd} ms\n")
+"Execution time -- 29884.2 ms"
+```
+
+<div class="flex gap-4">
+  <div>
+    <img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/original_sd.png"/>
+    <figcaption class="mt-2 text-center text-sm text-gray-500">original Stable Diffusion (45781.5 ms)</figcaption>
+  </div>
+  <div>
+    <img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/distilled_sd.png"/>
+    <figcaption class="mt-2 text-center text-sm text-gray-500">distilled Stable Diffusion (29884.2 ms)</figcaption>
+  </div>
+</div>
+
+## Tiny AutoEncoder
+
+To speed inference up even more, use a tiny distilled version of the [Stable Diffusion VAE](https://huggingface.co/sayakpaul/taesdxl-diffusers) to denoise the latents into images. Replace the VAE in the distilled Stable Diffusion model with the tiny VAE:
+
+```py
+from diffusers import AutoencoderTiny
+
+distilled.vae = AutoencoderTiny.from_pretrained(
+    "sayakpaul/taesd-diffusers", torch_dtype=torch.float16, use_safetensors=True,
+).to("cuda")
+```
+
+Time the distilled model and distilled VAE inference:
+
+```py
+start = time.time_ns()
+for _ in range(NUM_ITERS_TO_RUN):
+    images = distilled(
+        prompt,
+        num_inference_steps=NUM_INFERENCE_STEPS,
+        generator=generator,
+        num_images_per_prompt=NUM_IMAGES_PER_PROMPT
+    ).images
+end = time.time_ns()
+
+distilled_tiny_sd = f"{(end - start) / 1e6:.1f}"
+print(f"Execution time -- {distilled_tiny_sd} ms\n")
+"Execution time -- 27165.7 ms"
+```
+
+<div class="flex justify-center">
+  <div>
+    <img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/distilled_sd_vae.png" />
+    <figcaption class="mt-2 text-center text-sm text-gray-500">distilled Stable Diffusion + Tiny AutoEncoder (27165.7 ms)</figcaption>
+  </div>
+</div>

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

@@ -12,10 +12,54 @@ specific language governing permissions and limitations under the License.
 
 # Controlling image quality
 
-The components of a diffusion model, like the UNet and scheduler, can be optimized to improve the quality of generated images leading to better details. These techniques are especially useful if you don't have the resources to simply use a larger model for inference. You can enable these techniques during inference without any additional training.
+The components of a diffusion model, like the UNet and scheduler, can be optimized to improve the quality of generated images leading to better image lighting and details. These techniques are especially useful if you don't have the resources to simply use a larger model for inference. You can enable these techniques during inference without any additional training.
 
 This guide will show you how to turn these techniques on in your pipeline and how to configure them to improve the quality of your generated images.
 
+## Lighting
+
+The Stable Diffusion models aren't very good at generating images that are very bright or dark because the scheduler doesn't start sampling from the last timestep and it doesn't enforce a zero signal-to-noise ratio (SNR). The [Common Diffusion Noise Schedules and Sample Steps are Flawed](https://hf.co/papers/2305.08891) paper fixes these issues which are now available in some Diffusers schedulers.
+
+> [!TIP]
+> For inference, you need a model that has been trained with *v_prediction*. To train your own model with *v_prediction*, add the following flag to the [train_text_to_image.py](https://github.com/huggingface/diffusers/blob/main/examples/text_to_image/train_text_to_image.py) or [train_text_to_image_lora.py](https://github.com/huggingface/diffusers/blob/main/examples/text_to_image/train_text_to_image_lora.py) scripts.
+>
+> ```bash
+> --prediction_type="v_prediction"
+> ```
+
+For example, load the [ptx0/pseudo-journey-v2](https://hf.co/ptx0/pseudo-journey-v2) checkpoint which was trained with `v_prediction` and the [`DDIMScheduler`]. Now you should configure the following parameters in the [`DDIMScheduler`].
+
+* `rescale_betas_zero_snr=True` to rescale the noise schedule to zero SNR
+* `timestep_spacing="trailing"` to start sampling from the last timestep
+
+Set `guidance_rescale` in the pipeline to prevent over-exposure. A lower value increases brightness but some of the details may appear washed out.
+
+```py
+from diffusers import DiffusionPipeline, DDIMScheduler
+
+pipeline = DiffusionPipeline.from_pretrained("ptx0/pseudo-journey-v2", use_safetensors=True)
+
+pipeline.scheduler = DDIMScheduler.from_config(
+    pipeline.scheduler.config, rescale_betas_zero_snr=True, timestep_spacing="trailing"
+)
+pipeline.to("cuda")
+prompt = "cinematic photo of a snowy mountain at night with the northern lights aurora borealis overhead, 35mm photograph, film, professional, 4k, highly detailed"
+generator = torch.Generator(device="cpu").manual_seed(23)
+image = pipeline(prompt, guidance_rescale=0.7, generator=generator).images[0]
+image
+```
+
+<div class="flex gap-4">
+  <div>
+    <img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/no-zero-snr.png"/>
+    <figcaption class="mt-2 text-center text-sm text-gray-500">default Stable Diffusion v2-1 image</figcaption>
+  </div>
+  <div>
+    <img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/zero-snr.png"/>
+    <figcaption class="mt-2 text-center text-sm text-gray-500">image with zero SNR and trailing timestep spacing enabled</figcaption>
+  </div>
+</div>
+
 ## Details
 
 [FreeU](https://hf.co/papers/2309.11497) improves image details by rebalancing the UNet's backbone and skip connection weights. The skip connections can cause the model to overlook some of the backbone semantics which may lead to unnatural image details in the generated image. This technique does not require any additional training and can be applied on the fly during inference for tasks like image-to-image and text-to-video.

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

@@ -10,30 +10,29 @@ an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express o
 specific language governing permissions and limitations under the License.
 -->
 
-# Latent Consistency Model
-
 [[open-in-colab]]
 
-[Latent Consistency Models (LCMs)](https://hf.co/papers/2310.04378) enable fast high-quality image generation by directly predicting the reverse diffusion process in the latent rather than pixel space. In other words, LCMs try to predict the noiseless image from the noisy image in contrast to typical diffusion models that iteratively remove noise from the noisy image. By avoiding the iterative sampling process, LCMs are able to generate high-quality images in 2-4 steps instead of 20-30 steps.
+# Latent Consistency Model
 
-LCMs are distilled from pretrained models which requires ~32 hours of A100 compute. To speed this up, [LCM-LoRAs](https://hf.co/papers/2311.05556) train a [LoRA adapter](https://huggingface.co/docs/peft/conceptual_guides/adapter#low-rank-adaptation-lora) which have much fewer parameters to train compared to the full model. The LCM-LoRA can be plugged into a diffusion model once it has been trained.
+Latent Consistency Models (LCM) enable quality image generation in typically 2-4 steps making it possible to use diffusion models in almost real-time settings. 
 
-This guide will show you how to use LCMs and LCM-LoRAs for fast inference on tasks and how to use them with other adapters like ControlNet or T2I-Adapter.
+From the [official website](https://latent-consistency-models.github.io/):
 
-> [!TIP]
-> LCMs and LCM-LoRAs are available for Stable Diffusion v1.5, Stable Diffusion XL, and the SSD-1B model. You can find their checkpoints on the [Latent Consistency](https://hf.co/collections/latent-consistency/latent-consistency-models-weights-654ce61a95edd6dffccef6a8) Collections.
+> LCMs can be distilled from any pre-trained Stable Diffusion (SD) in only 4,000 training steps (~32 A100 GPU Hours) for generating high quality 768 x 768 resolution images in 2~4 steps or even one step, significantly accelerating text-to-image generation. We employ LCM to distill the Dreamshaper-V7 version of SD in just 4,000 training iterations.
+
+For a more technical overview of LCMs, refer to [the paper](https://huggingface.co/papers/2310.04378).
+
+LCM distilled models are available for [stable-diffusion-v1-5](https://huggingface.co/runwayml/stable-diffusion-v1-5), [stable-diffusion-xl-base-1.0](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0), and the [SSD-1B](https://huggingface.co/segmind/SSD-1B) model. All the checkpoints can be found in this [collection](https://huggingface.co/collections/latent-consistency/latent-consistency-models-weights-654ce61a95edd6dffccef6a8).
+
+This guide shows how to perform inference with LCMs for 
+- text-to-image
+- image-to-image
+- combined with style LoRAs
+- ControlNet/T2I-Adapter
 
 ## Text-to-image
 
-<hfoptions id="lcm-text2img">
-<hfoption id="LCM">
-
-To use LCMs, you need to load the LCM checkpoint for your supported model into [`UNet2DConditionModel`] and replace the scheduler with the [`LCMScheduler`]. 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 LCMs are:
-
-* Typically, batch size is doubled inside the pipeline for classifier-free guidance. But LCM applies guidance with guidance embeddings and doesn't need to double the batch size, which leads to faster inference. The downside is that negative prompts don't work with LCM because they don't have any effect on the denoising process.
-* The ideal range for `guidance_scale` is [3., 13.] because that is what the UNet was trained with. However, disabling `guidance_scale` with a value of 1.0 is also effective in most cases.
+You'll use the [`StableDiffusionXLPipeline`] pipeline with the [`LCMScheduler`] and then load the LCM-LoRA. Together with the LCM-LoRA and the scheduler, the pipeline enables a fast inference workflow, overcoming the slow iterative nature of diffusion models.
 
 ```python
 from diffusers import StableDiffusionXLPipeline, UNet2DConditionModel, LCMScheduler
@@ -50,69 +49,31 @@ pipe = StableDiffusionXLPipeline.from_pretrained(
 pipe.scheduler = LCMScheduler.from_config(pipe.scheduler.config)
 
 prompt = "Self-portrait oil painting, a beautiful cyborg with golden hair, 8k"
+
 generator = torch.manual_seed(0)
 image = pipe(
     prompt=prompt, num_inference_steps=4, generator=generator, guidance_scale=8.0
 ).images[0]
-image
 ```
 
-<div class="flex justify-center">
-    <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/lcm/lcm_full_sdxl_t2i.png"/>
-</div>
+![](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/lcm/lcm_full_sdxl_t2i.png)
 
-</hfoption>
-<hfoption id="LCM-LoRA">
+Notice that we use only 4 steps for generation which is way less than what's typically used for standard SDXL.
 
-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.
+Some details to keep in mind:
 
-A couple of notes to keep in mind when using LCM-LoRAs are:
+* To perform classifier-free guidance, batch size is usually doubled inside the pipeline. LCM, however, applies guidance using guidance embeddings, so the batch size does not have to be doubled in this case. This leads to a faster inference time, with the drawback that negative prompts don't have any effect on the denoising process.
+* The UNet was trained using the [3., 13.] guidance scale range. So, that is the ideal range for `guidance_scale`. However, disabling `guidance_scale` using a value of 1.0 is also effective in most cases.
 
-* Typically, batch size is doubled inside the pipeline for classifier-free guidance. But LCM applies guidance with guidance embeddings and doesn't need to double the batch size, which leads to faster inference. The downside is that negative prompts don't work with LCM because they don't have any effect on the denoising process.
-* You could use guidance with LCM-LoRAs, but it is very sensitive to high `guidance_scale` values and can lead to artifacts in the generated image. The best values we've found are between [1.0, 2.0].
-* Replace [stabilityai/stable-diffusion-xl-base-1.0](https://hf.co/stabilityai/stable-diffusion-xl-base-1.0) with any finetuned model. For example, try using the [animagine-xl](https://huggingface.co/Linaqruf/animagine-xl) checkpoint to generate anime images with SDXL.
-
-```py
-import torch
-from diffusers import DiffusionPipeline, LCMScheduler
-
-pipe = DiffusionPipeline.from_pretrained(
-    "stabilityai/stable-diffusion-xl-base-1.0",
-    variant="fp16",
-    torch_dtype=torch.float16
-).to("cuda")
-pipe.scheduler = LCMScheduler.from_config(pipe.scheduler.config)
-pipe.load_lora_weights("latent-consistency/lcm-lora-sdxl")
-
-prompt = "Self-portrait oil painting, a beautiful cyborg with golden hair, 8k"
-generator = torch.manual_seed(42)
-image = pipe(
-    prompt=prompt, num_inference_steps=4, generator=generator, guidance_scale=1.0
-).images[0]
-image
-```
-
-<div class="flex justify-center">
-    <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/lcm/lcm_sdxl_t2i.png"/>
-</div>
-
-</hfoption>
-</hfoptions>
 
 ## Image-to-image
 
-<hfoptions id="lcm-img2img">
-<hfoption id="LCM">
-
-To use LCMs for image-to-image, you need to load the LCM checkpoint for your supported model into [`UNet2DConditionModel`] and replace the scheduler with the [`LCMScheduler`]. 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.
+LCMs can be applied to image-to-image tasks too. For this example, we'll use the [LCM_Dreamshaper_v7](https://huggingface.co/SimianLuo/LCM_Dreamshaper_v7) model, but the same steps can be applied to other LCM models as well.
 
 ```python
 import torch
 from diffusers import AutoPipelineForImage2Image, UNet2DConditionModel, LCMScheduler
-from diffusers.utils import load_image
+from diffusers.utils import make_image_grid, load_image
 
 unet = UNet2DConditionModel.from_pretrained(
     "SimianLuo/LCM_Dreamshaper_v7",
@@ -128,8 +89,12 @@ pipe = AutoPipelineForImage2Image.from_pretrained(
 ).to("cuda")
 pipe.scheduler = LCMScheduler.from_config(pipe.scheduler.config)
 
-init_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/img2img-init.png")
+# prepare image
+url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/img2img-init.png"
+init_image = load_image(url)
 prompt = "Astronauts in a jungle, cold color palette, muted colors, detailed, 8k"
+
+# pass prompt and image to pipeline
 generator = torch.manual_seed(0)
 image = pipe(
     prompt,
@@ -139,130 +104,22 @@ image = pipe(
     strength=0.5,
     generator=generator
 ).images[0]
-image
+make_image_grid([init_image, image], rows=1, cols=2)
 ```
 
-<div class="flex gap-4">
-  <div>
-    <img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/img2img-init.png"/>
-    <figcaption class="mt-2 text-center text-sm text-gray-500">initial image</figcaption>
-  </div>
-  <div>
-    <img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/lcm-img2img.png"/>
-    <figcaption class="mt-2 text-center text-sm text-gray-500">generated image</figcaption>
-  </div>
-</div>
+![](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/lcm/lcm_full_sdv1-5_i2i.png)
 
-</hfoption>
-<hfoption id="LCM-LoRA">
 
-To use LCM-LoRAs for image-to-image, you need to replace the scheduler with the [`LCMScheduler`] and load the LCM-LoRA weights with the [`~loaders.LoraLoaderMixin.load_lora_weights`] method. Then you can use the pipeline as usual, and pass a text prompt and initial image to generate an image in just 4 steps.
+<Tip>
 
-> [!TIP]
-> Experiment with different values for `num_inference_steps`, `strength`, and `guidance_scale` to get the best results.
+You can get different results based on your prompt and the image you provide. To get the best results, we recommend trying different values for `num_inference_steps`, `strength`, and `guidance_scale` parameters and choose the best one.
 
-```py
-import torch
-from diffusers import AutoPipelineForImage2Image, LCMScheduler
-from diffusers.utils import make_image_grid, load_image
+</Tip>
 
-pipe = AutoPipelineForImage2Image.from_pretrained(
-    "Lykon/dreamshaper-7",
-    torch_dtype=torch.float16,
-    variant="fp16",
-).to("cuda")
 
-pipe.scheduler = LCMScheduler.from_config(pipe.scheduler.config)
+## Combine with style LoRAs
 
-pipe.load_lora_weights("latent-consistency/lcm-lora-sdv1-5")
-
-init_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/img2img-init.png")
-prompt = "Astronauts in a jungle, cold color palette, muted colors, detailed, 8k"
-
-generator = torch.manual_seed(0)
-image = pipe(
-    prompt,
-    image=init_image,
-    num_inference_steps=4,
-    guidance_scale=1,
-    strength=0.6,
-    generator=generator
-).images[0]
-image
-```
-
-<div class="flex gap-4">
-  <div>
-    <img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/img2img-init.png"/>
-    <figcaption class="mt-2 text-center text-sm text-gray-500">initial image</figcaption>
-  </div>
-  <div>
-    <img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/lcm-lora-img2img.png"/>
-    <figcaption class="mt-2 text-center text-sm text-gray-500">generated image</figcaption>
-  </div>
-</div>
-
-</hfoption>
-</hfoptions>
-
-## Inpainting
-
-To use LCM-LoRAs for inpainting, you need to replace the scheduler with the [`LCMScheduler`] and load the LCM-LoRA weights with the [`~loaders.LoraLoaderMixin.load_lora_weights`] method. Then you can use the pipeline as usual, and pass a text prompt, initial image, and mask image to generate an image in just 4 steps.
-
-```py
-import torch
-from diffusers import AutoPipelineForInpainting, LCMScheduler
-from diffusers.utils import load_image, make_image_grid
-
-pipe = AutoPipelineForInpainting.from_pretrained(
-    "runwayml/stable-diffusion-inpainting",
-    torch_dtype=torch.float16,
-    variant="fp16",
-).to("cuda")
-
-pipe.scheduler = LCMScheduler.from_config(pipe.scheduler.config)
-
-pipe.load_lora_weights("latent-consistency/lcm-lora-sdv1-5")
-
-init_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/inpaint.png")
-mask_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/inpaint_mask.png")
-
-prompt = "concept art digital painting of an elven castle, inspired by lord of the rings, highly detailed, 8k"
-generator = torch.manual_seed(0)
-image = pipe(
-    prompt=prompt,
-    image=init_image,
-    mask_image=mask_image,
-    generator=generator,
-    num_inference_steps=4,
-    guidance_scale=4,
-).images[0]
-image
-```
-
-<div class="flex gap-4">
-  <div>
-    <img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/inpaint.png"/>
-    <figcaption class="mt-2 text-center text-sm text-gray-500">initial image</figcaption>
-  </div>
-  <div>
-    <img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/lcm-lora-inpaint.png"/>
-    <figcaption class="mt-2 text-center text-sm text-gray-500">generated image</figcaption>
-  </div>
-</div>
-
-## Adapters
-
-LCMs are compatible with adapters like LoRA, ControlNet, T2I-Adapter, and AnimateDiff. You can bring the speed of LCMs to these adapters to generate images in a certain style or condition the model on another input like a canny image.
-
-### LoRA
-
-[LoRA](../using-diffusers/loading_adapters#lora) adapters can be rapidly finetuned to learn a new style from just a few images and plugged into a pretrained model to generate images in that style.
-
-<hfoptions id="lcm-lora">
-<hfoption id="LCM">
-
-Load the LCM checkpoint for your supported model into [`UNet2DConditionModel`] and replace the scheduler with the [`LCMScheduler`]. Then you can use the [`~loaders.LoraLoaderMixin.load_lora_weights`] method to load the LoRA weights into the LCM and generate a styled image in a few steps.
+LCMs can be used with other styled LoRAs to generate styled-images in very few steps (4-8). In the following example, we'll use the [papercut LoRA](TheLastBen/Papercut_SDXL). 
 
 ```python
 from diffusers import StableDiffusionXLPipeline, UNet2DConditionModel, LCMScheduler
@@ -277,9 +134,11 @@ pipe = StableDiffusionXLPipeline.from_pretrained(
     "stabilityai/stable-diffusion-xl-base-1.0", unet=unet, torch_dtype=torch.float16, variant="fp16",
 ).to("cuda")
 pipe.scheduler = LCMScheduler.from_config(pipe.scheduler.config)
+
 pipe.load_lora_weights("TheLastBen/Papercut_SDXL", weight_name="papercut.safetensors", adapter_name="papercut")
 
 prompt = "papercut, a cute fox"
+
 generator = torch.manual_seed(0)
 image = pipe(
     prompt=prompt, num_inference_steps=4, generator=generator, guidance_scale=8.0
@@ -287,58 +146,15 @@ image = pipe(
 image
 ```
 
-<div class="flex justify-center">
-    <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/lcm/lcm_full_sdx_lora_mix.png"/>
-</div>
+![](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/lcm/lcm_full_sdx_lora_mix.png)
 
-</hfoption>
-<hfoption id="LCM-LoRA">
 
-Replace the scheduler with the [`LCMScheduler`]. Then you can use the [`~loaders.LoraLoaderMixin.load_lora_weights`] method to load the LCM-LoRA weights and the style LoRA you want to use. Combine both LoRA adapters with the [`~loaders.UNet2DConditionLoadersMixin.set_adapters`] method and generate a styled image in a few steps.
+## ControlNet/T2I-Adapter
 
-```py
-import torch
-from diffusers import DiffusionPipeline, LCMScheduler
-
-pipe = DiffusionPipeline.from_pretrained(
-    "stabilityai/stable-diffusion-xl-base-1.0",
-    variant="fp16",
-    torch_dtype=torch.float16
-).to("cuda")
-
-pipe.scheduler = LCMScheduler.from_config(pipe.scheduler.config)
-
-pipe.load_lora_weights("latent-consistency/lcm-lora-sdxl", adapter_name="lcm")
-pipe.load_lora_weights("TheLastBen/Papercut_SDXL", weight_name="papercut.safetensors", adapter_name="papercut")
-
-pipe.set_adapters(["lcm", "papercut"], adapter_weights=[1.0, 0.8])
-
-prompt = "papercut, a cute fox"
-generator = torch.manual_seed(0)
-image = pipe(prompt, num_inference_steps=4, guidance_scale=1, generator=generator).images[0]
-image
-```
-
-<div class="flex justify-center">
-    <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/lcm/lcm_sdx_lora_mix.png"/>
-</div>
-
-</hfoption>
-</hfoptions>
+Let's look at how we can perform inference with ControlNet/T2I-Adapter and a LCM. 
 
 ### ControlNet
-
-[ControlNet](./controlnet) are adapters that can be trained on a variety of inputs like canny edge, pose estimation, or depth. The ControlNet can be inserted into the pipeline to provide additional conditioning and control to the model for more accurate generation.
-
-You can find additional ControlNet models trained on other inputs in [lllyasviel's](https://hf.co/lllyasviel) repository.
-
-<hfoptions id="lcm-controlnet">
-<hfoption id="LCM">
-
-Load a ControlNet model trained on canny images and pass it to the [`ControlNetModel`]. Then you can load a LCM model into [`StableDiffusionControlNetPipeline`] and replace the scheduler with the [`LCMScheduler`]. Now 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.
+For this example, we'll use the [LCM_Dreamshaper_v7](https://huggingface.co/SimianLuo/LCM_Dreamshaper_v7) model with canny ControlNet, but the same steps can be applied to other LCM models as well.
 
 ```python
 import torch
@@ -370,6 +186,8 @@ pipe = StableDiffusionControlNetPipeline.from_pretrained(
     torch_dtype=torch.float16,
     safety_checker=None,
 ).to("cuda")
+
+# set scheduler
 pipe.scheduler = LCMScheduler.from_config(pipe.scheduler.config)
 
 generator = torch.manual_seed(0)
@@ -382,84 +200,16 @@ image = pipe(
 make_image_grid([canny_image, image], rows=1, cols=2)
 ```
 
-<div class="flex justify-center">
-    <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/lcm/lcm_full_sdv1-5_controlnet.png"/>
-</div>
+![](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/lcm/lcm_full_sdv1-5_controlnet.png)
 
-</hfoption>
-<hfoption id="LCM-LoRA">
 
-Load a ControlNet model trained on canny images and pass it to the [`ControlNetModel`]. Then you can load a Stable Diffusion v1.5 model into [`StableDiffusionControlNetPipeline`] and replace the scheduler with the [`LCMScheduler`]. Use the [`~loaders.LoraLoaderMixin.load_lora_weights`] method to load the LCM-LoRA weights, and pass the canny image to the pipeline and generate an image.
-
-> [!TIP]
-> Experiment with different values for `num_inference_steps`, `controlnet_conditioning_scale`, `cross_attention_kwargs`, and `guidance_scale` to get the best results.
-
-```py
-import torch
-import cv2
-import numpy as np
-from PIL import Image
-
-from diffusers import StableDiffusionControlNetPipeline, ControlNetModel, LCMScheduler
-from diffusers.utils import load_image
-
-image = load_image(
-    "https://hf.co/datasets/huggingface/documentation-images/resolve/main/diffusers/input_image_vermeer.png"
-).resize((512, 512))
-
-image = np.array(image)
-
-low_threshold = 100
-high_threshold = 200
-
-image = cv2.Canny(image, low_threshold, high_threshold)
-image = image[:, :, None]
-image = np.concatenate([image, image, image], axis=2)
-canny_image = Image.fromarray(image)
-
-controlnet = ControlNetModel.from_pretrained("lllyasviel/sd-controlnet-canny", torch_dtype=torch.float16)
-pipe = StableDiffusionControlNetPipeline.from_pretrained(
-    "runwayml/stable-diffusion-v1-5",
-    controlnet=controlnet,
-    torch_dtype=torch.float16,
-    safety_checker=None,
-    variant="fp16"
-).to("cuda")
-
-pipe.scheduler = LCMScheduler.from_config(pipe.scheduler.config)
-
-pipe.load_lora_weights("latent-consistency/lcm-lora-sdv1-5")
-
-generator = torch.manual_seed(0)
-image = pipe(
-    "the mona lisa",
-    image=canny_image,
-    num_inference_steps=4,
-    guidance_scale=1.5,
-    controlnet_conditioning_scale=0.8,
-    cross_attention_kwargs={"scale": 1},
-    generator=generator,
-).images[0]
-image
-```
-
-<div class="flex justify-center">
-    <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/lcm/lcm_sdv1-5_controlnet.png"/>
-</div>
-
-</hfoption>
-</hfoptions>
+<Tip>
+The inference parameters in this example might not work for all examples, so we recommend trying different values for the `num_inference_steps`, `guidance_scale`, `controlnet_conditioning_scale`, and `cross_attention_kwargs` parameters and choosing the best one. 
+</Tip>
 
 ### T2I-Adapter
 
-[T2I-Adapter](./t2i_adapter) is an even more lightweight adapter than ControlNet, that provides an additional input to condition a pretrained model with. It is faster than ControlNet but the results may be slightly worse.
-
-You can find additional T2I-Adapter checkpoints trained on other inputs in [TencentArc's](https://hf.co/TencentARC) repository.
-
-<hfoptions id="lcm-t2i">
-<hfoption id="LCM">
-
-Load a T2IAdapter trained on canny images and pass it to the [`StableDiffusionXLAdapterPipeline`]. Then load a LCM checkpoint into [`UNet2DConditionModel`] and replace the scheduler with the [`LCMScheduler`]. Now pass the canny image to the pipeline and generate an image.
+This example shows how to use the `lcm-sdxl` with the [Canny T2I-Adapter](TencentARC/t2i-adapter-canny-sdxl-1.0).
 
 ```python
 import torch
@@ -470,9 +220,10 @@ from PIL import Image
 from diffusers import StableDiffusionXLAdapterPipeline, UNet2DConditionModel, T2IAdapter, LCMScheduler
 from diffusers.utils import load_image, make_image_grid
 
-# detect the canny map in low resolution to avoid high-frequency details
+# Prepare image
+# Detect the canny map in low resolution to avoid high-frequency details
 image = load_image(
-    "https://hf.co/datasets/huggingface/documentation-images/resolve/main/diffusers/input_image_vermeer.png"
+    "https://huggingface.co/Adapter/t2iadapter/resolve/main/figs_SDXLV1.0/org_canny.jpg"
 ).resize((384, 384))
 
 image = np.array(image)
@@ -485,6 +236,7 @@ image = image[:, :, None]
 image = np.concatenate([image, image, image], axis=2)
 canny_image = Image.fromarray(image).resize((1024, 1216))
 
+# load adapter
 adapter = T2IAdapter.from_pretrained("TencentARC/t2i-adapter-canny-sdxl-1.0", torch_dtype=torch.float16, varient="fp16").to("cuda")
 
 unet = UNet2DConditionModel.from_pretrained(
@@ -497,12 +249,12 @@ pipe = StableDiffusionXLAdapterPipeline.from_pretrained(
     unet=unet,
     adapter=adapter,
     torch_dtype=torch.float16,
-    variant="fp16",
+    variant="fp16", 
 ).to("cuda")
 
 pipe.scheduler = LCMScheduler.from_config(pipe.scheduler.config)
 
-prompt = "the mona lisa, 4k picture, high quality"
+prompt = "Mystical fairy in real, magic, 4k picture, high quality"
 negative_prompt = "extra digit, fewer digits, cropped, worst quality, low quality, glitch, deformed, mutated, ugly, disfigured"
 
 generator = torch.manual_seed(0)
@@ -512,120 +264,11 @@ image = pipe(
     image=canny_image,
     num_inference_steps=4,
     guidance_scale=5,
-    adapter_conditioning_scale=0.8,
+    adapter_conditioning_scale=0.8, 
     adapter_conditioning_factor=1,
     generator=generator,
 ).images[0]
+grid = make_image_grid([canny_image, image], rows=1, cols=2)
 ```
 
-<div class="flex justify-center">
-    <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/lcm-t2i.png"/>
-</div>
-
-</hfoption>
-<hfoption id="LCM-LoRA">
-
-Load a T2IAdapter trained on canny images and pass it to the [`StableDiffusionXLAdapterPipeline`]. Replace the scheduler with the [`LCMScheduler`], and use the [`~loaders.LoraLoaderMixin.load_lora_weights`] method to load the LCM-LoRA weights. Pass the canny image to the pipeline and generate an image.
-
-```py
-import torch
-import cv2
-import numpy as np
-from PIL import Image
-
-from diffusers import StableDiffusionXLAdapterPipeline, UNet2DConditionModel, T2IAdapter, LCMScheduler
-from diffusers.utils import load_image, make_image_grid
-
-# detect the canny map in low resolution to avoid high-frequency details
-image = load_image(
-    "https://hf.co/datasets/huggingface/documentation-images/resolve/main/diffusers/input_image_vermeer.png"
-).resize((384, 384))
-
-image = np.array(image)
-
-low_threshold = 100
-high_threshold = 200
-
-image = cv2.Canny(image, low_threshold, high_threshold)
-image = image[:, :, None]
-image = np.concatenate([image, image, image], axis=2)
-canny_image = Image.fromarray(image).resize((1024, 1024))
-
-adapter = T2IAdapter.from_pretrained("TencentARC/t2i-adapter-canny-sdxl-1.0", torch_dtype=torch.float16, varient="fp16").to("cuda")
-
-pipe = StableDiffusionXLAdapterPipeline.from_pretrained(
-    "stabilityai/stable-diffusion-xl-base-1.0",
-    adapter=adapter,
-    torch_dtype=torch.float16,
-    variant="fp16",
-).to("cuda")
-
-pipe.scheduler = LCMScheduler.from_config(pipe.scheduler.config)
-
-pipe.load_lora_weights("latent-consistency/lcm-lora-sdxl")
-
-prompt = "the mona lisa, 4k picture, high quality"
-negative_prompt = "extra digit, fewer digits, cropped, worst quality, low quality, glitch, deformed, mutated, ugly, disfigured"
-
-generator = torch.manual_seed(0)
-image = pipe(
-    prompt=prompt,
-    negative_prompt=negative_prompt,
-    image=canny_image,
-    num_inference_steps=4,
-    guidance_scale=1.5,
-    adapter_conditioning_scale=0.8,
-    adapter_conditioning_factor=1,
-    generator=generator,
-).images[0]
-```
-
-<div class="flex justify-center">
-    <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/lcm-lora-t2i.png"/>
-</div>
-
-</hfoption>
-</hfoptions>
-
-### AnimateDiff
-
-[AnimateDiff](../api/pipelines/animatediff) is an adapter that adds motion to an image. It can be used with most Stable Diffusion models, effectively turning them into "video generation" models. Generating good results with a video model usually requires generating multiple frames (16-24), which can be very slow with a regular Stable Diffusion model. LCM-LoRA can speed up this process by only taking 4-8 steps for each frame.
-
-Load a [`AnimateDiffPipeline`] and pass a [`MotionAdapter`] to it. Then replace the scheduler with the [`LCMScheduler`], and combine both LoRA adapters with the [`~loaders.UNet2DConditionLoadersMixin.set_adapters`] method. Now you can pass a prompt to the pipeline and generate an animated image.
-
-```py
-import torch
-from diffusers import MotionAdapter, AnimateDiffPipeline, DDIMScheduler, LCMScheduler
-from diffusers.utils import export_to_gif
-
-adapter = MotionAdapter.from_pretrained("guoyww/animatediff-motion-adapter-v1-5")
-pipe = AnimateDiffPipeline.from_pretrained(
-    "frankjoshua/toonyou_beta6",
-    motion_adapter=adapter,
-).to("cuda")
-
-# set scheduler
-pipe.scheduler = LCMScheduler.from_config(pipe.scheduler.config)
-
-# load LCM-LoRA
-pipe.load_lora_weights("latent-consistency/lcm-lora-sdv1-5", adapter_name="lcm")
-pipe.load_lora_weights("guoyww/animatediff-motion-lora-zoom-in", weight_name="diffusion_pytorch_model.safetensors", adapter_name="motion-lora")
-
-pipe.set_adapters(["lcm", "motion-lora"], adapter_weights=[0.55, 1.2])
-
-prompt = "best quality, masterpiece, 1girl, looking at viewer, blurry background, upper body, contemporary, dress"
-generator = torch.manual_seed(0)
-frames = pipe(
-    prompt=prompt,
-    num_inference_steps=5,
-    guidance_scale=1.25,
-    cross_attention_kwargs={"scale": 1},
-    num_frames=24,
-    generator=generator
-).frames[0]
-export_to_gif(frames, "animation.gif")
-```
-
-<div class="flex justify-center">
-    <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/lcm-lora-animatediff.gif"/>
-</div>
+![](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/lcm/lcm_full_sdxl_t2iadapter.png)

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

@@ -0,0 +1,422 @@
+<!--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.
+-->
+
+[[open-in-colab]]
+
+# Performing inference with LCM-LoRA
+
+Latent Consistency Models (LCM) enable quality image generation in typically 2-4 steps making it possible to use diffusion models in almost real-time settings. 
+
+From the [official website](https://latent-consistency-models.github.io/):
+
+> LCMs can be distilled from any pre-trained Stable Diffusion (SD) in only 4,000 training steps (~32 A100 GPU Hours) for generating high quality 768 x 768 resolution images in 2~4 steps or even one step, significantly accelerating text-to-image generation. We employ LCM to distill the Dreamshaper-V7 version of SD in just 4,000 training iterations.
+
+For a more technical overview of LCMs, refer to [the paper](https://huggingface.co/papers/2310.04378).
+
+However, each model needs to be distilled separately for latent consistency distillation. The core idea with LCM-LoRA is to train just a few adapter layers, the adapter being LoRA in this case. 
+This way, we don't have to train the full model and keep the number of trainable parameters manageable. The resulting LoRAs can then be applied to any fine-tuned version of the model without distilling them separately.
+Additionally, the LoRAs can be applied to image-to-image, ControlNet/T2I-Adapter, inpainting, AnimateDiff etc. 
+The LCM-LoRA can also be combined with other LoRAs to generate styled images in very few steps (4-8).
+
+LCM-LoRAs are available for [stable-diffusion-v1-5](https://huggingface.co/runwayml/stable-diffusion-v1-5), [stable-diffusion-xl-base-1.0](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0), and the [SSD-1B](https://huggingface.co/segmind/SSD-1B) model. All the checkpoints can be found in this [collection](https://huggingface.co/collections/latent-consistency/latent-consistency-models-loras-654cdd24e111e16f0865fba6).
+
+For more details about LCM-LoRA, refer to [the technical report](https://huggingface.co/papers/2311.05556).
+
+This guide shows how to perform inference with LCM-LoRAs for 
+- text-to-image
+- image-to-image
+- combined with styled LoRAs
+- ControlNet/T2I-Adapter
+- inpainting
+- AnimateDiff
+
+Before going through this guide, we'll take a look at the general workflow for performing inference with LCM-LoRAs.
+LCM-LoRAs are similar to other Stable Diffusion LoRAs so they can be used with any [`DiffusionPipeline`] that supports LoRAs.
+
+- Load the task specific pipeline and model.
+- Set the scheduler to [`LCMScheduler`].
+- Load the LCM-LoRA weights for the model.
+- Reduce the `guidance_scale` between `[1.0, 2.0]` and set the `num_inference_steps` between [4, 8].
+- Perform inference with the pipeline with the usual parameters.
+
+Let's look at how we can perform inference with LCM-LoRAs for different tasks.
+
+First, make sure you have [peft](https://github.com/huggingface/peft) installed, for better LoRA support.
+
+```bash
+pip install -U peft
+```
+
+## Text-to-image
+
+You'll use the [`StableDiffusionXLPipeline`] with the scheduler: [`LCMScheduler`] and then load the LCM-LoRA. Together with the LCM-LoRA and the scheduler, the pipeline enables a fast inference workflow overcoming the slow iterative nature of diffusion models.
+
+```python
+import torch
+from diffusers import DiffusionPipeline, LCMScheduler
+
+pipe = DiffusionPipeline.from_pretrained(
+    "stabilityai/stable-diffusion-xl-base-1.0",
+    variant="fp16",
+    torch_dtype=torch.float16
+).to("cuda")
+
+# set scheduler
+pipe.scheduler = LCMScheduler.from_config(pipe.scheduler.config)
+
+# load LCM-LoRA
+pipe.load_lora_weights("latent-consistency/lcm-lora-sdxl")
+
+prompt = "Self-portrait oil painting, a beautiful cyborg with golden hair, 8k"
+
+generator = torch.manual_seed(42)
+image = pipe(
+    prompt=prompt, num_inference_steps=4, generator=generator, guidance_scale=1.0
+).images[0]
+```
+
+![](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/lcm/lcm_sdxl_t2i.png)
+
+Notice that we use only 4 steps for generation which is way less than what's typically used for standard SDXL.
+
+<Tip>
+
+You may have noticed that we set `guidance_scale=1.0`, which disables classifer-free-guidance. This is because the LCM-LoRA is trained with guidance, so the batch size does not have to be doubled in this case. This leads to a faster inference time, with the drawback that negative prompts don't have any effect on the denoising process.
+
+You can also use guidance with LCM-LoRA, but due to the nature of training the model is very sensitve to the `guidance_scale` values, high values can lead to artifacts in the generated images. In our experiments, we found that the best values are in the range of [1.0, 2.0].
+
+</Tip>
+
+### Inference with a fine-tuned model
+
+As mentioned above, the LCM-LoRA can be applied to any fine-tuned version of the model without having to distill them separately. Let's look at how we can perform inference with a fine-tuned model. In this example, we'll use the [animagine-xl](https://huggingface.co/Linaqruf/animagine-xl) model, which is a fine-tuned version of the SDXL model for generating anime.
+
+```python
+from diffusers import DiffusionPipeline, LCMScheduler
+
+pipe = DiffusionPipeline.from_pretrained(
+    "Linaqruf/animagine-xl",
+    variant="fp16",
+    torch_dtype=torch.float16
+).to("cuda")
+
+# set scheduler
+pipe.scheduler = LCMScheduler.from_config(pipe.scheduler.config)
+
+# load LCM-LoRA
+pipe.load_lora_weights("latent-consistency/lcm-lora-sdxl")
+
+prompt = "face focus, cute, masterpiece, best quality, 1girl, green hair, sweater, looking at viewer, upper body, beanie, outdoors, night, turtleneck"
+
+generator = torch.manual_seed(0)
+image = pipe(
+    prompt=prompt, num_inference_steps=4, generator=generator, guidance_scale=1.0
+).images[0]
+```
+
+![](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/lcm/lcm_sdxl_t2i_finetuned.png)
+
+
+## Image-to-image
+
+LCM-LoRA can be applied to image-to-image tasks too. Let's look at how we can perform image-to-image generation with LCMs. For this example we'll use the [dreamshaper-7](https://huggingface.co/Lykon/dreamshaper-7) model and the LCM-LoRA for `stable-diffusion-v1-5 `.
+
+```python
+import torch
+from diffusers import AutoPipelineForImage2Image, LCMScheduler
+from diffusers.utils import make_image_grid, load_image
+
+pipe = AutoPipelineForImage2Image.from_pretrained(
+    "Lykon/dreamshaper-7",
+    torch_dtype=torch.float16,
+    variant="fp16",
+).to("cuda")
+
+# set scheduler
+pipe.scheduler = LCMScheduler.from_config(pipe.scheduler.config)
+
+# load LCM-LoRA
+pipe.load_lora_weights("latent-consistency/lcm-lora-sdv1-5")
+
+# prepare image
+url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/img2img-init.png"
+init_image = load_image(url)
+prompt = "Astronauts in a jungle, cold color palette, muted colors, detailed, 8k"
+
+# pass prompt and image to pipeline
+generator = torch.manual_seed(0)
+image = pipe(
+    prompt,
+    image=init_image,
+    num_inference_steps=4,
+    guidance_scale=1,
+    strength=0.6,
+    generator=generator
+).images[0]
+make_image_grid([init_image, image], rows=1, cols=2)
+```
+
+![](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/lcm/lcm_sdv1-5_i2i.png)
+
+
+<Tip>
+
+You can get different results based on your prompt and the image you provide. To get the best results, we recommend trying different values for `num_inference_steps`, `strength`, and `guidance_scale` parameters and choose the best one.
+
+</Tip>
+
+
+## Combine with styled LoRAs
+
+LCM-LoRA can be combined with other LoRAs to generate styled-images in very few steps (4-8). In the following example, we'll use the LCM-LoRA with the [papercut LoRA](TheLastBen/Papercut_SDXL). 
+To learn more about how to combine LoRAs, refer to [this guide](https://huggingface.co/docs/diffusers/tutorials/using_peft_for_inference#combine-multiple-adapters).
+
+```python
+import torch
+from diffusers import DiffusionPipeline, LCMScheduler
+
+pipe = DiffusionPipeline.from_pretrained(
+    "stabilityai/stable-diffusion-xl-base-1.0",
+    variant="fp16",
+    torch_dtype=torch.float16
+).to("cuda")
+
+# set scheduler
+pipe.scheduler = LCMScheduler.from_config(pipe.scheduler.config)
+
+# load LoRAs
+pipe.load_lora_weights("latent-consistency/lcm-lora-sdxl", adapter_name="lcm")
+pipe.load_lora_weights("TheLastBen/Papercut_SDXL", weight_name="papercut.safetensors", adapter_name="papercut")
+
+# Combine LoRAs
+pipe.set_adapters(["lcm", "papercut"], adapter_weights=[1.0, 0.8])
+
+prompt = "papercut, a cute fox"
+generator = torch.manual_seed(0)
+image = pipe(prompt, num_inference_steps=4, guidance_scale=1, generator=generator).images[0]
+image
+```
+
+![](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/lcm/lcm_sdx_lora_mix.png)
+
+
+## ControlNet/T2I-Adapter
+
+Let's look at how we can perform inference with ControlNet/T2I-Adapter and LCM-LoRA. 
+
+### ControlNet
+For this example, we'll use the SD-v1-5 model and the LCM-LoRA for SD-v1-5 with canny ControlNet.
+
+```python
+import torch
+import cv2
+import numpy as np
+from PIL import Image
+
+from diffusers import StableDiffusionControlNetPipeline, ControlNetModel, LCMScheduler
+from diffusers.utils import load_image
+
+image = load_image(
+    "https://hf.co/datasets/huggingface/documentation-images/resolve/main/diffusers/input_image_vermeer.png"
+).resize((512, 512))
+
+image = np.array(image)
+
+low_threshold = 100
+high_threshold = 200
+
+image = cv2.Canny(image, low_threshold, high_threshold)
+image = image[:, :, None]
+image = np.concatenate([image, image, image], axis=2)
+canny_image = Image.fromarray(image)
+
+controlnet = ControlNetModel.from_pretrained("lllyasviel/sd-controlnet-canny", torch_dtype=torch.float16)
+pipe = StableDiffusionControlNetPipeline.from_pretrained(
+    "runwayml/stable-diffusion-v1-5",
+    controlnet=controlnet,
+    torch_dtype=torch.float16,
+    safety_checker=None,
+    variant="fp16"
+).to("cuda")
+
+# set scheduler
+pipe.scheduler = LCMScheduler.from_config(pipe.scheduler.config)
+
+# load LCM-LoRA
+pipe.load_lora_weights("latent-consistency/lcm-lora-sdv1-5")
+
+generator = torch.manual_seed(0)
+image = pipe(
+    "the mona lisa",
+    image=canny_image,
+    num_inference_steps=4,
+    guidance_scale=1.5,
+    controlnet_conditioning_scale=0.8,
+    cross_attention_kwargs={"scale": 1},
+    generator=generator,
+).images[0]
+make_image_grid([canny_image, image], rows=1, cols=2)
+```
+
+![](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/lcm/lcm_sdv1-5_controlnet.png)
+
+
+<Tip>
+The inference parameters in this example might not work for all examples, so we recommend you to try different values for `num_inference_steps`, `guidance_scale`, `controlnet_conditioning_scale` and `cross_attention_kwargs` parameters and choose the best one. 
+</Tip>
+
+### T2I-Adapter
+
+This example shows how to use the LCM-LoRA with the [Canny T2I-Adapter](TencentARC/t2i-adapter-canny-sdxl-1.0) and SDXL.
+
+```python
+import torch
+import cv2
+import numpy as np
+from PIL import Image
+
+from diffusers import StableDiffusionXLAdapterPipeline, T2IAdapter, LCMScheduler
+from diffusers.utils import load_image, make_image_grid
+
+# Prepare image
+# Detect the canny map in low resolution to avoid high-frequency details
+image = load_image(
+    "https://huggingface.co/Adapter/t2iadapter/resolve/main/figs_SDXLV1.0/org_canny.jpg"
+).resize((384, 384))
+
+image = np.array(image)
+
+low_threshold = 100
+high_threshold = 200
+
+image = cv2.Canny(image, low_threshold, high_threshold)
+image = image[:, :, None]
+image = np.concatenate([image, image, image], axis=2)
+canny_image = Image.fromarray(image).resize((1024, 1024))
+
+# load adapter
+adapter = T2IAdapter.from_pretrained("TencentARC/t2i-adapter-canny-sdxl-1.0", torch_dtype=torch.float16, varient="fp16").to("cuda")
+
+pipe = StableDiffusionXLAdapterPipeline.from_pretrained(
+    "stabilityai/stable-diffusion-xl-base-1.0", 
+    adapter=adapter,
+    torch_dtype=torch.float16,
+    variant="fp16", 
+).to("cuda")
+
+# set scheduler
+pipe.scheduler = LCMScheduler.from_config(pipe.scheduler.config)
+
+# load LCM-LoRA
+pipe.load_lora_weights("latent-consistency/lcm-lora-sdxl")
+
+prompt = "Mystical fairy in real, magic, 4k picture, high quality"
+negative_prompt = "extra digit, fewer digits, cropped, worst quality, low quality, glitch, deformed, mutated, ugly, disfigured"
+
+generator = torch.manual_seed(0)
+image = pipe(
+    prompt=prompt,
+    negative_prompt=negative_prompt,
+    image=canny_image,
+    num_inference_steps=4,
+    guidance_scale=1.5, 
+    adapter_conditioning_scale=0.8, 
+    adapter_conditioning_factor=1,
+    generator=generator,
+).images[0]
+make_image_grid([canny_image, image], rows=1, cols=2)
+```
+
+![](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/lcm/lcm_sdxl_t2iadapter.png)
+
+
+## Inpainting
+
+LCM-LoRA can be used for inpainting as well. 
+
+```python
+import torch
+from diffusers import AutoPipelineForInpainting, LCMScheduler
+from diffusers.utils import load_image, make_image_grid
+
+pipe = AutoPipelineForInpainting.from_pretrained(
+    "runwayml/stable-diffusion-inpainting",
+    torch_dtype=torch.float16,
+    variant="fp16",
+).to("cuda")
+
+# set scheduler
+pipe.scheduler = LCMScheduler.from_config(pipe.scheduler.config)
+
+# load LCM-LoRA
+pipe.load_lora_weights("latent-consistency/lcm-lora-sdv1-5")
+
+# load base and mask image
+init_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/inpaint.png")
+mask_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/inpaint_mask.png")
+
+# generator = torch.Generator("cuda").manual_seed(92)
+prompt = "concept art digital painting of an elven castle, inspired by lord of the rings, highly detailed, 8k"
+generator = torch.manual_seed(0)
+image = pipe(
+    prompt=prompt,
+    image=init_image,
+    mask_image=mask_image,
+    generator=generator,
+    num_inference_steps=4,
+    guidance_scale=4, 
+).images[0]
+make_image_grid([init_image, mask_image, image], rows=1, cols=3)
+```
+
+![](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/lcm/lcm_sdv1-5_inpainting.png)
+
+
+## AnimateDiff
+
+[`AnimateDiff`] allows you to animate images using Stable Diffusion models. To get good results, we need to generate multiple frames (16-24), and doing this with standard SD models can be very slow. 
+LCM-LoRA can be used to speed up the process significantly, as you just need to do 4-8 steps for each frame. Let's look at how we can perform animation with LCM-LoRA and AnimateDiff.
+
+```python
+import torch
+from diffusers import MotionAdapter, AnimateDiffPipeline, DDIMScheduler, LCMScheduler
+from diffusers.utils import export_to_gif
+
+adapter = MotionAdapter.from_pretrained("diffusers/animatediff-motion-adapter-v1-5")
+pipe = AnimateDiffPipeline.from_pretrained(
+    "frankjoshua/toonyou_beta6",
+    motion_adapter=adapter,
+).to("cuda")
+
+# set scheduler
+pipe.scheduler = LCMScheduler.from_config(pipe.scheduler.config)
+
+# load LCM-LoRA
+pipe.load_lora_weights("latent-consistency/lcm-lora-sdv1-5", adapter_name="lcm")
+pipe.load_lora_weights("guoyww/animatediff-motion-lora-zoom-in", weight_name="diffusion_pytorch_model.safetensors", adapter_name="motion-lora")
+
+pipe.set_adapters(["lcm", "motion-lora"], adapter_weights=[0.55, 1.2])
+
+prompt = "best quality, masterpiece, 1girl, looking at viewer, blurry background, upper body, contemporary, dress"
+generator = torch.manual_seed(0)
+frames = pipe(
+    prompt=prompt,
+    num_inference_steps=5,
+    guidance_scale=1.25,
+    cross_attention_kwargs={"scale": 1},
+    num_frames=24,
+    generator=generator
+).frames[0]
+export_to_gif(frames, "animation.gif")
+```
+
+![](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/lcm/lcm_sdv1-5_animatediff.gif)

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

@@ -78,7 +78,7 @@ image = pipe(
     prompt=prompt,
     num_inference_steps=4,
     guidance_scale=0,
-    eta=0.3,
+    eta=0.3, 
     generator=torch.Generator(device=device).manual_seed(0),
 ).images[0]
 ```
@@ -156,14 +156,14 @@ image = pipe(
     prompt=prompt,
     num_inference_steps=8,
     guidance_scale=0,
-    eta=0.3,
+    eta=0.3, 
     generator=torch.Generator(device=device).manual_seed(0),
 ).images[0]
 ```
 
 ![](https://github.com/jabir-zheng/TCD/raw/main/assets/animagine_xl.png)
 
-TCD-LoRA also supports other LoRAs trained on different styles. For example, let's load the [TheLastBen/Papercut_SDXL](https://huggingface.co/TheLastBen/Papercut_SDXL) LoRA and fuse it with the TCD-LoRA with the [`~loaders.UNet2DConditionLoadersMixin.set_adapters`] method.
+TCD-LoRA also supports other LoRAs trained on different styles. For example, let's load the [TheLastBen/Papercut_SDXL](https://huggingface.co/TheLastBen/Papercut_SDXL) LoRA and fuse it with the TCD-LoRA with the [`~loaders.UNet2DConditionLoadersMixin.set_adapters`] method. 
 
 > [!TIP]
 > Check out the [Merge LoRAs](merge_loras) guide to learn more about efficient merging methods.
@@ -171,7 +171,7 @@ TCD-LoRA also supports other LoRAs trained on different styles. For example, let
 ```python
 import torch
 from diffusers import StableDiffusionXLPipeline
-from scheduling_tcd import TCDScheduler
+from scheduling_tcd import TCDScheduler 
 
 device = "cuda"
 base_model_id = "stabilityai/stable-diffusion-xl-base-1.0"
@@ -191,7 +191,7 @@ image = pipe(
     prompt=prompt,
     num_inference_steps=4,
     guidance_scale=0,
-    eta=0.3,
+    eta=0.3, 
     generator=torch.Generator(device=device).manual_seed(0),
 ).images[0]
 ```
@@ -215,7 +215,7 @@ from PIL import Image
 from transformers import DPTFeatureExtractor, DPTForDepthEstimation
 from diffusers import ControlNetModel, StableDiffusionXLControlNetPipeline
 from diffusers.utils import load_image, make_image_grid
-from scheduling_tcd import TCDScheduler
+from scheduling_tcd import TCDScheduler 
 
 device = "cuda"
 depth_estimator = DPTForDepthEstimation.from_pretrained("Intel/dpt-hybrid-midas").to(device)
@@ -249,13 +249,13 @@ controlnet = ControlNetModel.from_pretrained(
     controlnet_id,
     torch_dtype=torch.float16,
     variant="fp16",
-)
+).to(device)
 pipe = StableDiffusionXLControlNetPipeline.from_pretrained(
     base_model_id,
     controlnet=controlnet,
     torch_dtype=torch.float16,
     variant="fp16",
-)
+).to(device)
 pipe.enable_model_cpu_offload()
 
 pipe.scheduler = TCDScheduler.from_config(pipe.scheduler.config)
@@ -271,9 +271,9 @@ depth_image = get_depth_map(image)
 controlnet_conditioning_scale = 0.5  # recommended for good generalization
 
 image = pipe(
-    prompt,
-    image=depth_image,
-    num_inference_steps=4,
+    prompt, 
+    image=depth_image, 
+    num_inference_steps=4, 
     guidance_scale=0,
     eta=0.3,
     controlnet_conditioning_scale=controlnet_conditioning_scale,
@@ -290,7 +290,7 @@ grid_image = make_image_grid([depth_image, image], rows=1, cols=2)
 import torch
 from diffusers import ControlNetModel, StableDiffusionXLControlNetPipeline
 from diffusers.utils import load_image, make_image_grid
-from scheduling_tcd import TCDScheduler
+from scheduling_tcd import TCDScheduler 
 
 device = "cuda"
 base_model_id = "stabilityai/stable-diffusion-xl-base-1.0"
@@ -301,13 +301,13 @@ controlnet = ControlNetModel.from_pretrained(
     controlnet_id,
     torch_dtype=torch.float16,
     variant="fp16",
-)
+).to(device)
 pipe = StableDiffusionXLControlNetPipeline.from_pretrained(
     base_model_id,
     controlnet=controlnet,
     torch_dtype=torch.float16,
     variant="fp16",
-)
+).to(device)
 pipe.enable_model_cpu_offload()
 
 pipe.scheduler = TCDScheduler.from_config(pipe.scheduler.config)
@@ -322,9 +322,9 @@ canny_image = load_image("https://huggingface.co/datasets/hf-internal-testing/di
 controlnet_conditioning_scale = 0.5  # recommended for good generalization
 
 image = pipe(
-    prompt,
-    image=canny_image,
-    num_inference_steps=4,
+    prompt, 
+    image=canny_image, 
+    num_inference_steps=4, 
     guidance_scale=0,
     eta=0.3,
     controlnet_conditioning_scale=controlnet_conditioning_scale,
@@ -336,7 +336,7 @@ grid_image = make_image_grid([canny_image, image], rows=1, cols=2)
 ![](https://github.com/jabir-zheng/TCD/raw/main/assets/controlnet_canny_tcd.png)
 
 <Tip>
-The inference parameters in this example might not work for all examples, so we recommend you to try different values for `num_inference_steps`, `guidance_scale`, `controlnet_conditioning_scale` and `cross_attention_kwargs` parameters and choose the best one.
+The inference parameters in this example might not work for all examples, so we recommend you to try different values for `num_inference_steps`, `guidance_scale`, `controlnet_conditioning_scale` and `cross_attention_kwargs` parameters and choose the best one. 
 </Tip>
 
 </hfoption>
@@ -350,7 +350,7 @@ from diffusers import StableDiffusionXLPipeline
 from diffusers.utils import load_image, make_image_grid
 
 from ip_adapter import IPAdapterXL
-from scheduling_tcd import TCDScheduler
+from scheduling_tcd import TCDScheduler 
 
 device = "cuda"
 base_model_path = "stabilityai/stable-diffusion-xl-base-1.0"
@@ -359,8 +359,8 @@ ip_ckpt = "sdxl_models/ip-adapter_sdxl.bin"
 tcd_lora_id = "h1t/TCD-SDXL-LoRA"
 
 pipe = StableDiffusionXLPipeline.from_pretrained(
-    base_model_path,
-    torch_dtype=torch.float16,
+    base_model_path, 
+    torch_dtype=torch.float16, 
     variant="fp16"
 )
 pipe.scheduler = TCDScheduler.from_config(pipe.scheduler.config)
@@ -375,13 +375,13 @@ ref_image = load_image("https://raw.githubusercontent.com/tencent-ailab/IP-Adapt
 prompt = "best quality, high quality, wearing sunglasses"
 
 image = ip_model.generate(
-    pil_image=ref_image,
+    pil_image=ref_image, 
     prompt=prompt,
     scale=0.5,
-    num_samples=1,
-    num_inference_steps=4,
+    num_samples=1, 
+    num_inference_steps=4, 
     guidance_scale=0,
-    eta=0.3,
+    eta=0.3, 
     seed=0,
 )[0]
 

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

@@ -230,7 +230,7 @@ from diffusers.utils import load_image, make_image_grid
 
 pipeline = AutoPipelineForInpainting.from_pretrained(
     "runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16, variant="fp16"
-)
+).to("cuda")
 pipeline.enable_model_cpu_offload()
 # remove following line if xFormers is not installed or you have PyTorch 2.0 or higher installed
 pipeline.enable_xformers_memory_efficient_attention()
@@ -255,7 +255,7 @@ from diffusers.utils import load_image, make_image_grid
 
 pipeline = AutoPipelineForInpainting.from_pretrained(
     "runwayml/stable-diffusion-inpainting", torch_dtype=torch.float16, variant="fp16"
-)
+).to("cuda")
 pipeline.enable_model_cpu_offload()
 # remove following line if xFormers is not installed or you have PyTorch 2.0 or higher installed
 pipeline.enable_xformers_memory_efficient_attention()
@@ -296,7 +296,7 @@ from diffusers.utils import load_image, make_image_grid
 
 pipeline = AutoPipelineForInpainting.from_pretrained(
     "runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16, variant="fp16"
-)
+).to("cuda")
 pipeline.enable_model_cpu_offload()
 # remove following line if xFormers is not installed or you have PyTorch 2.0 or higher installed
 pipeline.enable_xformers_memory_efficient_attention()
@@ -319,7 +319,7 @@ from diffusers.utils import load_image, make_image_grid
 
 pipeline = AutoPipelineForInpainting.from_pretrained(
     "runwayml/stable-diffusion-inpainting", torch_dtype=torch.float16, variant="fp16"
-)
+).to("cuda")
 pipeline.enable_model_cpu_offload()
 # remove following line if xFormers is not installed or you have PyTorch 2.0 or higher installed
 pipeline.enable_xformers_memory_efficient_attention()