update

.github/ISSUE_TEMPLATE/bug-report.yml

@@ -57,54 +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, ...): @sayakpaul @DN6
+        Questions on DiffusionPipeline (Saving, Loading, From pretrained, ...):
 
         Questions on pipelines:
-        - Stable Diffusion @yiyixuxu @asomoza
-        - Stable Diffusion XL @yiyixuxu @sayakpaul @DN6
-        - Stable Diffusion 3: @yiyixuxu @sayakpaul @DN6 @asomoza
-        - Kandinsky @yiyixuxu
-        - ControlNet @sayakpaul @yiyixuxu @DN6
-        - T2I Adapter @sayakpaul @yiyixuxu @DN6
-        - IF @DN6
-        - Text-to-Video / Video-to-Video @DN6 @a-r-r-o-w
-        - 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
-        - Improving generation quality: @asomoza
 
         Questions on models:
-        - UNet @DN6 @yiyixuxu @sayakpaul
-        - VAE @sayakpaul @DN6 @yiyixuxu
-        - Transformers/Attention @DN6 @yiyixuxu @sayakpaul
+        - UNet @DN6 @yiyixuxu @sayakpaul 
+        - VAE @sayakpaul @DN6 @yiyixuxu 
+        - Transformers/Attention @DN6 @yiyixuxu @sayakpaul @DN6 
 
-        Questions on single file checkpoints: @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: @sanchit-gandhi
-
-
+        Questions on audio pipelines: @DN6 
+        
 
+        
       placeholder: "@Username ..."

.github/ISSUE_TEMPLATE/remote-vae-pilot-feedback.yml

@@ -1,38 +0,0 @@
-name: "\U0001F31F Remote VAE"
-description: Feedback for remote VAE pilot
-labels: [ "Remote VAE" ]
-
-body:
-  - type: textarea
-    id: positive
-    validations:
-      required: true
-    attributes:
-      label: Did you like the remote VAE solution?
-      description: |
-        If you liked it, we would appreciate it if you could elaborate what you liked.
-
-  - type: textarea
-    id: feedback
-    validations:
-      required: true
-    attributes:
-      label: What can be improved about the current solution?
-      description: |
-        Let us know the things you would like to see improved. Note that we will work optimizing the solution once the pilot is over and we have usage.
-
-  - type: textarea
-    id: others
-    validations:
-      required: true
-    attributes:
-      label: What other VAEs you would like to see if the pilot goes well?
-      description: |
-        Provide a list of the VAEs you would like to see in the future if the pilot goes well.
-
-  - type: textarea
-    id: additional-info
-    attributes:
-      label: Notify the members of the team
-      description: |
-        Tag the following folks when submitting this feedback: @hlky @sayakpaul

.github/PULL_REQUEST_TEMPLATE.md

@@ -38,9 +38,9 @@ members/contributors who may be interested in your PR.
 
 Core library:
 
-- Schedulers: @yiyixuxu
-- Pipelines and pipeline callbacks: @yiyixuxu and @asomoza
-- Training examples: @sayakpaul
+- Schedulers: @yiyixuxu 
+- Pipelines:  @sayakpaul @yiyixuxu @DN6
+- Training examples: @sayakpaul 
 - Docs: @stevhliu and @sayakpaul
 - JAX and MPS: @pcuenca
 - Audio: @sanchit-gandhi
@@ -48,8 +48,7 @@ Core library:
 
 Integrations:
 
-- deepspeed: HF Trainer/Accelerate: @SunMarc
-- PEFT: @sayakpaul @BenjaminBossan
+- deepspeed: HF Trainer/Accelerate: @pacman100
 
 HF projects:
 

.github/workflows/benchmark.yml

@@ -7,25 +7,20 @@ on:
 
 env:
   DIFFUSERS_IS_CI: yes
-  HF_XET_HIGH_PERFORMANCE: 1
   HF_HOME: /mnt/cache
   OMP_NUM_THREADS: 8
   MKL_NUM_THREADS: 8
-  BASE_PATH: benchmark_outputs
 
 jobs:
-  torch_models_cuda_benchmark_tests:
-    env:
-      SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL_BENCHMARK }}
-    name: Torch Core Models CUDA Benchmarking Tests
+  torch_pipelines_cuda_benchmark_tests:
+    name: Torch Core Pipelines CUDA Benchmarking Tests
     strategy:
       fail-fast: false
       max-parallel: 1
-    runs-on:
-      group: aws-g6e-4xlarge
+    runs-on: [single-gpu, nvidia-gpu, a10, ci]
     container:
       image: diffusers/diffusers-pytorch-cuda
-      options: --shm-size "16gb" --ipc host --gpus all
+      options: --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/ --gpus 0
     steps:
       - name: Checkout diffusers
         uses: actions/checkout@v3
@@ -36,53 +31,24 @@ jobs:
           nvidia-smi
       - name: Install dependencies
         run: |
-          apt update
-          apt install -y libpq-dev postgresql-client
-          uv pip install -e ".[quality]"
-          uv pip install -r benchmarks/requirements.txt
+          apt-get update && apt-get install libsndfile1-dev libgl1 -y
+          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+          python -m uv pip install -e [quality,test]
+          python -m uv pip install pandas peft
       - name: Environment
         run: |
           python utils/print_env.py
       - name: Diffusers Benchmarking
         env:
-          HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
+            HUGGING_FACE_HUB_TOKEN: ${{ secrets.DIFFUSERS_BOT_TOKEN }}
+            BASE_PATH: benchmark_outputs
         run: |
-          cd benchmarks && python run_all.py
-
-      - name: Push results to the Hub
-        env: 
-          HF_TOKEN: ${{ secrets.DIFFUSERS_BOT_TOKEN }}
-        run: |
-          cd benchmarks && python push_results.py
-          mkdir $BASE_PATH && cp *.csv $BASE_PATH
+          export TOTAL_GPU_MEMORY=$(python -c "import torch; print(torch.cuda.get_device_properties(0).total_memory / (1024**3))")
+          cd benchmarks && mkdir ${BASE_PATH} && python run_all.py && python push_results.py
 
       - name: Test suite reports artifacts
         if: ${{ always() }}
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v2
         with:
           name: benchmark_test_reports
-          path: benchmarks/${{ env.BASE_PATH }}
-      
-      # TODO: enable this once the connection problem has been resolved.
-      - name: Update benchmarking results to DB
-        env:
-          PGDATABASE: metrics
-          PGHOST: ${{ secrets.DIFFUSERS_BENCHMARKS_PGHOST }}
-          PGUSER: transformers_benchmarks
-          PGPASSWORD: ${{ secrets.DIFFUSERS_BENCHMARKS_PGPASSWORD }}
-          BRANCH_NAME: ${{ github.head_ref || github.ref_name }}
-        run: |
-          git config --global --add safe.directory /__w/diffusers/diffusers
-          commit_id=$GITHUB_SHA
-          commit_msg=$(git show -s --format=%s "$commit_id" | cut -c1-70)
-          cd benchmarks && python populate_into_db.py "$BRANCH_NAME" "$commit_id" "$commit_msg"
-
-      - name: Report success status
-        if: ${{ success() }}
-        run: |
-          pip install requests && python utils/notify_benchmarking_status.py --status=success
-
-      - name: Report failure status
-        if: ${{ failure() }}
-        run: |
-          pip install requests && python utils/notify_benchmarking_status.py --status=failure
+          path: benchmarks/benchmark_outputs

.github/workflows/build_docker_images.yml

@@ -20,69 +20,39 @@ env:
 
 jobs:
   test-build-docker-images:
-    runs-on:
-      group: aws-general-8-plus
+    runs-on: ubuntu-latest
     if: github.event_name == 'pull_request'
     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"
+          format: 'space-delimited'
           token: ${{ secrets.GITHUB_TOKEN }}
-
+      
       - name: Build Changed Docker Images
-        env: 
-          CHANGED_FILES: ${{ steps.file_changes.outputs.all }}
         run: |
-          echo "$CHANGED_FILES"
-          ALLOWED_IMAGES=(
-            diffusers-pytorch-cpu
-            diffusers-pytorch-cuda
-            diffusers-pytorch-xformers-cuda
-            diffusers-pytorch-minimum-cuda
-            diffusers-doc-builder
-          )
-
-          declare -A IMAGES_TO_BUILD=()
-
+          CHANGED_FILES="${{ steps.file_changes.outputs.all }}"
           for FILE in $CHANGED_FILES; do
-            # skip anything that isn't still on disk
-            if [[ ! -e "$FILE" ]]; then
-              echo "Skipping removed file $FILE"
-              continue
+            if [[ "$FILE" == docker/*Dockerfile ]]; then
+              DOCKER_PATH="${FILE%/Dockerfile}"
+              DOCKER_TAG=$(basename "$DOCKER_PATH")
+              echo "Building Docker image for $DOCKER_TAG"
+              docker build -t "$DOCKER_TAG" "$DOCKER_PATH"
             fi
-
-            for IMAGE in "${ALLOWED_IMAGES[@]}"; do
-              if [[ "$FILE" == docker/${IMAGE}/* ]]; then
-                IMAGES_TO_BUILD["$IMAGE"]=1
-              fi
-            done
-          done
-
-          if [[ ${#IMAGES_TO_BUILD[@]} -eq 0 ]]; then
-            echo "No relevant Docker changes detected."
-            exit 0
-          fi
-
-          for IMAGE in "${!IMAGES_TO_BUILD[@]}"; do
-            DOCKER_PATH="docker/${IMAGE}"
-            echo "Building Docker image for $IMAGE"
-            docker build -t "$IMAGE" "$DOCKER_PATH"
           done
         if: steps.file_changes.outputs.all != ''
 
   build-and-push-docker-images:
-    runs-on:
-      group: aws-general-8-plus
+    runs-on: ubuntu-latest
     if: github.event_name != 'pull_request'
-
+    
     permissions:
       contents: read
       packages: write
@@ -93,20 +63,23 @@ jobs:
         image-name:
           - diffusers-pytorch-cpu
           - diffusers-pytorch-cuda
+          - diffusers-pytorch-compile-cuda
           - diffusers-pytorch-xformers-cuda
-          - diffusers-pytorch-minimum-cuda
-          - diffusers-doc-builder
+          - diffusers-flax-cpu
+          - diffusers-flax-tpu
+          - diffusers-onnxruntime-cpu
+          - diffusers-onnxruntime-cuda
 
     steps:
       - name: Checkout repository
         uses: actions/checkout@v3
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v1
+
       - name: Login to Docker Hub
         uses: docker/login-action@v2
         with:
           username: ${{ env.REGISTRY }}
           password: ${{ secrets.DOCKERHUB_TOKEN }}
+
       - name: Build and push
         uses: docker/build-push-action@v3
         with:
@@ -117,11 +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

@@ -12,33 +12,7 @@ concurrency:
   cancel-in-progress: true
 
 jobs:
-  check-links:
-    runs-on: ubuntu-latest
-
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@v4
-
-      - name: Set up Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: '3.10'
-
-      - name: Install uv
-        run: |
-          curl -LsSf https://astral.sh/uv/install.sh | sh
-          echo "$HOME/.cargo/bin" >> $GITHUB_PATH
-
-      - name: Install doc-builder
-        run: |
-          uv pip install --system git+https://github.com/huggingface/doc-builder.git@main
-
-      - name: Check documentation links
-        run: |
-          uv run doc-builder check-links docs/source/en
-
   build:
-    needs: check-links
     uses: huggingface/doc-builder/.github/workflows/build_pr_documentation.yml@main
     with:
       commit_sha: ${{ github.event.pull_request.head.sha }}
@@ -46,4 +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

@@ -1,102 +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:
-    env:
-      SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL_COMMUNITY_MIRROR }}
-
-    runs-on: ubuntu-22.04
-    steps:
-      # Checkout to correct ref
-      #   If workflow dispatch
-      #     If ref is 'main', set:
-      #       CHECKOUT_REF=refs/heads/main
-      #       PATH_IN_REPO=main
-      #     Else it must be a tag. Set:
-      #       CHECKOUT_REF=refs/tags/{tag}
-      #       PATH_IN_REPO={tag}
-      #   If not workflow dispatch
-      #     If ref is 'refs/heads/main' => set 'main'
-      #     Else it must be a tag => set {tag}
-      - name: Set checkout_ref and path_in_repo
-        run: |
-          if [ "${{ 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: |
-          pip install --upgrade pip
-          pip install --upgrade huggingface_hub
-
-      # Check secret is set
-      - name: whoami
-        run: hf auth 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: hf 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 }}
-
-      - name: Report success status
-        if: ${{ success() }}
-        run: |
-          pip install requests && python utils/notify_community_pipelines_mirror.py --status=success
-
-      - name: Report failure status
-        if: ${{ failure() }}
-        run: |
-          pip install requests && python utils/notify_community_pipelines_mirror.py --status=failure

.github/workflows/nightly_tests.yml

@@ -1,622 +1,186 @@
-name: Nightly and release tests on main/release branch
+name: Nightly tests on main
 
 on:
-  workflow_dispatch:
   schedule:
     - cron: "0 0 * * *" # every day at midnight
 
 env:
   DIFFUSERS_IS_CI: yes
-  HF_XET_HIGH_PERFORMANCE: 1
+  HF_HOME: /mnt/cache
   OMP_NUM_THREADS: 8
   MKL_NUM_THREADS: 8
   PYTEST_TIMEOUT: 600
   RUN_SLOW: yes
   RUN_NIGHTLY: yes
-  PIPELINE_USAGE_CUTOFF: 0
   SLACK_API_TOKEN: ${{ secrets.SLACK_CIFEEDBACK_BOT_TOKEN }}
-  CONSOLIDATED_REPORT_PATH: consolidated_test_report.md
 
 jobs:
-  setup_torch_cuda_pipeline_matrix:
-    name: Setup Torch Pipelines CUDA Slow Tests Matrix
-    runs-on:
-      group: aws-general-8-plus
-    container:
-      image: diffusers/diffusers-pytorch-cpu
-    outputs:
-      pipeline_test_matrix: ${{ steps.fetch_pipeline_matrix.outputs.pipeline_test_matrix }}
-    steps:
-      - name: Checkout diffusers
-        uses: actions/checkout@v3
-        with:
-          fetch-depth: 2
-      - name: Install dependencies
-        run: |
-          pip install -e .[test]
-          pip install huggingface_hub
-      - name: Fetch Pipeline Matrix
-        id: fetch_pipeline_matrix
-        run: |
-          matrix=$(python utils/fetch_torch_cuda_pipeline_test_matrix.py)
-          echo $matrix
-          echo "pipeline_test_matrix=$matrix" >> $GITHUB_OUTPUT
-
-      - name: Pipeline Tests Artifacts
-        if: ${{ always() }}
-        uses: actions/upload-artifact@v4
-        with:
-          name: test-pipelines.json
-          path: reports
-
-  run_nightly_tests_for_torch_pipelines:
-    name: Nightly Torch Pipelines CUDA Tests
-    needs: setup_torch_cuda_pipeline_matrix
+  run_nightly_tests:
     strategy:
       fail-fast: false
-      max-parallel: 8
-      matrix:
-        module: ${{ fromJson(needs.setup_torch_cuda_pipeline_matrix.outputs.pipeline_test_matrix) }}
-    runs-on:
-      group: aws-g4dn-2xlarge
-    container:
-      image: diffusers/diffusers-pytorch-cuda
-      options: --shm-size "16gb" --ipc host --gpus all
-    steps:
-      - name: Checkout diffusers
-        uses: actions/checkout@v3
-        with:
-          fetch-depth: 2
-      - name: NVIDIA-SMI
-        run: nvidia-smi
-      - name: Install dependencies
-        run: |
-          uv pip install -e ".[quality]"
-          uv pip uninstall accelerate && uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
-          #uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
-          uv pip uninstall transformers huggingface_hub && uv pip install transformers==4.57.1 
-          uv pip install pytest-reportlog
-      - name: Environment
-        run: |
-          python utils/print_env.py
-      - name: Pipeline CUDA Test
-        env:
-          HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
-          # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
-          CUBLAS_WORKSPACE_CONFIG: :16:8
-        run: |
-          pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-             -k "not Flax and not Onnx" \
-            --make-reports=tests_pipeline_${{ matrix.module }}_cuda \
-            --report-log=tests_pipeline_${{ matrix.module }}_cuda.log \
-            tests/pipelines/${{ matrix.module }}
-      - name: Failure short reports
-        if: ${{ failure() }}
-        run: |
-          cat reports/tests_pipeline_${{ matrix.module }}_cuda_stats.txt
-          cat reports/tests_pipeline_${{ matrix.module }}_cuda_failures_short.txt
-      - name: Test suite reports artifacts
-        if: ${{ always() }}
-        uses: actions/upload-artifact@v4
-        with:
-          name: pipeline_${{ matrix.module }}_test_reports
-          path: reports
-
-  run_nightly_tests_for_other_torch_modules:
-    name: Nightly Torch CUDA Tests
-    runs-on:
-      group: aws-g4dn-2xlarge
-    container:
-      image: diffusers/diffusers-pytorch-cuda
-      options: --shm-size "16gb" --ipc host --gpus all
-    defaults:
-      run:
-        shell: bash
-    strategy:
-      fail-fast: false
-      max-parallel: 2
-      matrix:
-        module: [models, schedulers, lora, others, single_file, examples]
-    steps:
-    - name: Checkout diffusers
-      uses: actions/checkout@v3
-      with:
-        fetch-depth: 2
-
-    - name: Install dependencies
-      run: |
-        uv pip install -e ".[quality]"
-        uv pip install peft@git+https://github.com/huggingface/peft.git
-        uv pip uninstall accelerate && uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
-        #uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
-        uv pip uninstall transformers huggingface_hub && uv pip install transformers==4.57.1 
-        uv pip install pytest-reportlog
-    - name: Environment
-      run: python utils/print_env.py
-
-    - name: Run nightly PyTorch CUDA tests for non-pipeline modules
-      if: ${{ matrix.module != 'examples'}}
-      env:
-        HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
-        # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
-        CUBLAS_WORKSPACE_CONFIG: :16:8
-      run: |
-        pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-          -k "not Flax and not Onnx" \
-          --make-reports=tests_torch_${{ matrix.module }}_cuda \
-          --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.DIFFUSERS_HF_HUB_READ_TOKEN }}
-        # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
-        CUBLAS_WORKSPACE_CONFIG: :16:8
-      run: |
-        pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-          --make-reports=examples_torch_cuda \
-          --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_failures_short.txt
-
-    - name: Test suite reports artifacts
-      if: ${{ always() }}
-      uses: actions/upload-artifact@v4
-      with:
-        name: torch_${{ matrix.module }}_cuda_test_reports
-        path: reports
-
-  run_torch_compile_tests:
-    name: PyTorch Compile CUDA tests
-
-    runs-on:
-      group: aws-g4dn-2xlarge
-
-    container:
-      image: diffusers/diffusers-pytorch-cuda
-      options: --gpus all --shm-size "16gb" --ipc host
-
-    steps:
-    - name: Checkout diffusers
-      uses: actions/checkout@v3
-      with:
-        fetch-depth: 2
-
-    - name: NVIDIA-SMI
-      run: |
-        nvidia-smi
-    - name: Install dependencies
-      run: |
-        uv pip install -e ".[quality,training]"
-        #uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
-        uv pip uninstall transformers huggingface_hub && uv pip install transformers==4.57.1 
-    - name: Environment
-      run: |
-        python utils/print_env.py
-    - name: Run torch compile tests on GPU
-      env:
-        HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
-        RUN_COMPILE: yes
-      run: |
-        pytest -n 1 --max-worker-restart=0 --dist=loadfile -k "compile" --make-reports=tests_torch_compile_cuda tests/
-    - name: Failure short reports
-      if: ${{ failure() }}
-      run: cat reports/tests_torch_compile_cuda_failures_short.txt
-
-    - name: Test suite reports artifacts
-      if: ${{ always() }}
-      uses: actions/upload-artifact@v4
-      with:
-        name: torch_compile_test_reports
-        path: reports
-
-  run_big_gpu_torch_tests:
-    name: Torch tests on big GPU
-    strategy:
-      fail-fast: false
-      max-parallel: 2
-    runs-on:
-      group: aws-g6e-xlarge-plus
-    container:
-      image: diffusers/diffusers-pytorch-cuda
-      options: --shm-size "16gb" --ipc host --gpus all
-    steps:
-      - name: Checkout diffusers
-        uses: actions/checkout@v3
-        with:
-          fetch-depth: 2
-      - name: NVIDIA-SMI
-        run: nvidia-smi
-      - name: Install dependencies
-        run: |
-          uv pip install -e ".[quality]"
-          uv pip install peft@git+https://github.com/huggingface/peft.git
-          uv pip uninstall accelerate && uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
-          #uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
-          uv pip uninstall transformers huggingface_hub && uv pip install transformers==4.57.1 
-          uv pip install pytest-reportlog
-      - name: Environment
-        run: |
-          python utils/print_env.py
-      - name: Selected Torch CUDA Test on big GPU
-        env:
-          HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
-          # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
-          CUBLAS_WORKSPACE_CONFIG: :16:8
-          BIG_GPU_MEMORY: 40
-        run: |
-          pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-            -m "big_accelerator" \
-            --make-reports=tests_big_gpu_torch_cuda \
-            --report-log=tests_big_gpu_torch_cuda.log \
-            tests/
-      - name: Failure short reports
-        if: ${{ failure() }}
-        run: |
-          cat reports/tests_big_gpu_torch_cuda_stats.txt
-          cat reports/tests_big_gpu_torch_cuda_failures_short.txt
-      - name: Test suite reports artifacts
-        if: ${{ always() }}
-        uses: actions/upload-artifact@v4
-        with:
-          name: torch_cuda_big_gpu_test_reports
-          path: reports
-
-  torch_minimum_version_cuda_tests:
-    name: Torch Minimum Version CUDA Tests
-    runs-on:
-      group: aws-g4dn-2xlarge
-    container:
-      image: diffusers/diffusers-pytorch-minimum-cuda
-      options: --shm-size "16gb" --ipc host --gpus all
-    defaults:
-      run:
-        shell: bash
-    steps:
-      - name: Checkout diffusers
-        uses: actions/checkout@v3
-        with:
-          fetch-depth: 2
-
-      - name: Install dependencies
-        run: |
-          uv pip install -e ".[quality]"
-          uv pip install peft@git+https://github.com/huggingface/peft.git
-          uv pip uninstall accelerate && uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
-          #uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
-          uv pip uninstall transformers huggingface_hub && uv pip install transformers==4.57.1 
-
-      - name: Environment
-        run: |
-          python utils/print_env.py
-
-      - name: Run PyTorch CUDA tests
-        env:
-          HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
-          # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
-          CUBLAS_WORKSPACE_CONFIG: :16:8
-        run: |
-          pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-            -k "not Flax and not Onnx" \
-            --make-reports=tests_torch_minimum_version_cuda \
-            tests/models/test_modeling_common.py \
-            tests/pipelines/test_pipelines_common.py \
-            tests/pipelines/test_pipeline_utils.py \
-            tests/pipelines/test_pipelines.py \
-            tests/pipelines/test_pipelines_auto.py \
-            tests/schedulers/test_schedulers.py \
-            tests/others
-
-      - name: Failure short reports
-        if: ${{ failure() }}
-        run: |
-          cat reports/tests_torch_minimum_version_cuda_stats.txt
-          cat reports/tests_torch_minimum_version_cuda_failures_short.txt
-
-      - name: Test suite reports artifacts
-        if: ${{ always() }}
-        uses: actions/upload-artifact@v4
-        with:
-          name: torch_minimum_version_cuda_test_reports
-          path: reports
-
-  run_nightly_quantization_tests:
-    name: Torch quantization nightly tests
-    strategy:
-      fail-fast: false
-      max-parallel: 2
       matrix:
         config:
-          - backend: "bitsandbytes"
-            test_location: "bnb"
-            additional_deps: ["peft"]
-          - backend: "gguf"
-            test_location: "gguf"
-            additional_deps: ["peft", "kernels"]
-          - backend: "torchao"
-            test_location: "torchao"
-            additional_deps: []
-          - backend: "optimum_quanto"
-            test_location: "quanto"
-            additional_deps: []
-          - backend: "nvidia_modelopt"
-            test_location: "modelopt"
-            additional_deps: []
-    runs-on:
-      group: aws-g6e-xlarge-plus
+          - name: Nightly PyTorch CUDA tests on Ubuntu
+            framework: pytorch
+            runner: docker-gpu
+            image: diffusers/diffusers-pytorch-cuda
+            report: torch_cuda
+          - name: Nightly Flax TPU tests on Ubuntu
+            framework: flax
+            runner: docker-tpu
+            image: diffusers/diffusers-flax-tpu
+            report: flax_tpu
+          - name: Nightly ONNXRuntime CUDA tests on Ubuntu
+            framework: onnxruntime
+            runner: docker-gpu
+            image: diffusers/diffusers-onnxruntime-cuda
+            report: onnx_cuda
+
+    name: ${{ matrix.config.name }}
+
+    runs-on: ${{ matrix.config.runner }}
+
     container:
-      image: diffusers/diffusers-pytorch-cuda
-      options: --shm-size "20gb" --ipc host --gpus all
+      image: ${{ matrix.config.image }}
+      options: --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/ ${{ matrix.config.runner == 'docker-tpu' && '--privileged' || '--gpus 0'}}
+
+    defaults:
+      run:
+        shell: bash
+
     steps:
       - name: Checkout diffusers
         uses: actions/checkout@v3
         with:
           fetch-depth: 2
+
       - name: NVIDIA-SMI
-        run: nvidia-smi
+        if: ${{ matrix.config.runner == 'docker-gpu' }}
+        run: |
+          nvidia-smi
+
       - name: Install dependencies
         run: |
-          uv pip install -e ".[quality]"
-          uv pip install -U ${{ matrix.config.backend }}
-          if [ "${{ join(matrix.config.additional_deps, ' ') }}" != "" ]; then
-              uv pip install ${{ join(matrix.config.additional_deps, ' ') }}
-          fi
-          uv pip install pytest-reportlog
-          #uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
-          uv pip uninstall transformers huggingface_hub && uv pip install transformers==4.57.1 
+          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+          python -m uv pip install -e [quality,test]
+          python -m uv pip install -U transformers@git+https://github.com/huggingface/transformers
+          python -m uv pip install accelerate@git+https://github.com/huggingface/accelerate
+          python -m uv pip install pytest-reportlog
+
       - name: Environment
         run: |
           python utils/print_env.py
-      - name: ${{ matrix.config.backend }} quantization tests on GPU
+
+      - name: Run nightly PyTorch CUDA tests
+        if: ${{ matrix.config.framework == 'pytorch' }}
         env:
-          HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
-          # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
-          CUBLAS_WORKSPACE_CONFIG: :16:8
-          BIG_GPU_MEMORY: 40
+          HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
         run: |
-          pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-            --make-reports=tests_${{ matrix.config.backend }}_torch_cuda \
-            --report-log=tests_${{ matrix.config.backend }}_torch_cuda.log \
-            tests/quantization/${{ matrix.config.test_location }}
+          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+          python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
+            -s -v -k "not Flax and not Onnx" \
+            --make-reports=tests_${{ matrix.config.report }} \
+            --report-log=${{ matrix.config.report }}.log \
+            tests/ 
+
+      - name: Run nightly Flax TPU tests
+        if: ${{ matrix.config.framework == 'flax' }}
+        env:
+          HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
+        run: |
+          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+          python -m pytest -n 0 \
+            -s -v -k "Flax" \
+            --make-reports=tests_${{ matrix.config.report }} \
+            --report-log=${{ matrix.config.report }}.log \
+            tests/
+
+      - name: Run nightly ONNXRuntime CUDA tests
+        if: ${{ matrix.config.framework == 'onnxruntime' }}
+        env:
+          HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
+        run: |
+          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+          python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
+            -s -v -k "Onnx" \
+            --make-reports=tests_${{ matrix.config.report }} \
+            --report-log=${{ matrix.config.report }}.log \ 
+            tests/
+
       - name: Failure short reports
         if: ${{ failure() }}
-        run: |
-          cat reports/tests_${{ matrix.config.backend }}_torch_cuda_stats.txt
-          cat reports/tests_${{ matrix.config.backend }}_torch_cuda_failures_short.txt
+        run: cat reports/tests_${{ matrix.config.report }}_failures_short.txt
+
       - name: Test suite reports artifacts
         if: ${{ always() }}
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v2
         with:
-          name: torch_cuda_${{ matrix.config.backend }}_reports
+          name: ${{ matrix.config.report }}_test_reports
           path: reports
-          
-  run_nightly_pipeline_level_quantization_tests:
-    name: Torch quantization nightly tests
-    strategy:
-      fail-fast: false
-      max-parallel: 2
-    runs-on:
-      group: aws-g6e-xlarge-plus
-    container:
-      image: diffusers/diffusers-pytorch-cuda
-      options: --shm-size "20gb" --ipc host --gpus all
-    steps:
-      - name: Checkout diffusers
-        uses: actions/checkout@v3
-        with:
-          fetch-depth: 2
-      - name: NVIDIA-SMI
-        run: nvidia-smi
-      - name: Install dependencies
+      
+      - name: Generate Report and Notify Channel
+        if: always()
         run: |
-          uv pip install -e ".[quality]"
-          uv pip install -U bitsandbytes optimum_quanto
-          #uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
-          uv pip uninstall transformers huggingface_hub && uv pip install transformers==4.57.1 
-          uv pip install pytest-reportlog
-      - name: Environment
-        run: |
-          python utils/print_env.py
-      - name: Pipeline-level quantization tests on GPU
-        env:
-          HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
-          # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
-          CUBLAS_WORKSPACE_CONFIG: :16:8
-          BIG_GPU_MEMORY: 40
-        run: |
-          pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-            --make-reports=tests_pipeline_level_quant_torch_cuda \
-            --report-log=tests_pipeline_level_quant_torch_cuda.log \
-            tests/quantization/test_pipeline_level_quantization.py
-      - name: Failure short reports
-        if: ${{ failure() }}
-        run: |
-          cat reports/tests_pipeline_level_quant_torch_cuda_stats.txt
-          cat reports/tests_pipeline_level_quant_torch_cuda_failures_short.txt
-      - name: Test suite reports artifacts
-        if: ${{ always() }}
-        uses: actions/upload-artifact@v4
-        with:
-          name: torch_cuda_pipeline_level_quant_reports
-          path: reports
-
-  generate_consolidated_report:
-    name: Generate Consolidated Test Report
-    needs: [
-      run_nightly_tests_for_torch_pipelines,
-      run_nightly_tests_for_other_torch_modules,
-      run_torch_compile_tests,
-      run_big_gpu_torch_tests,
-      run_nightly_quantization_tests,
-      run_nightly_pipeline_level_quantization_tests,
-      # run_nightly_onnx_tests,
-      torch_minimum_version_cuda_tests,
-      # run_flax_tpu_tests
-    ]
-    if: always()
-    runs-on:
-      group: aws-general-8-plus
-    container:
-      image: diffusers/diffusers-pytorch-cpu
-    steps:
-      - name: Checkout diffusers
-        uses: actions/checkout@v3
-        with:
-          fetch-depth: 2
-
-      - name: Create reports directory
-        run: mkdir -p combined_reports
-
-      - name: Download all test reports
-        uses: actions/download-artifact@v4
-        with:
-          path: artifacts
-
-      - name: Prepare reports
-        run: |
-          # Move all report files to a single directory for processing
-          find artifacts -name "*.txt" -exec cp {} combined_reports/ \;
-
-      - name: Install dependencies
-        run: |
-          pip install -e .[test]
           pip install slack_sdk tabulate
+          python scripts/log_reports.py >> $GITHUB_STEP_SUMMARY
 
-      - name: Generate consolidated report
-        run: |
-          python utils/consolidated_test_report.py \
-            --reports_dir combined_reports \
-            --output_file $CONSOLIDATED_REPORT_PATH \
-            --slack_channel_name diffusers-ci-nightly
+  run_nightly_tests_apple_m1:
+    name: Nightly PyTorch MPS tests on MacOS
+    runs-on: [ self-hosted, apple-m1 ]
 
-      - name: Show consolidated report
-        run: |
-          cat $CONSOLIDATED_REPORT_PATH >> $GITHUB_STEP_SUMMARY
-
-      - name: Upload consolidated report
-        uses: actions/upload-artifact@v4
+    steps:
+      - name: Checkout diffusers
+        uses: actions/checkout@v3
         with:
-          name: consolidated_test_report
-          path: ${{ env.CONSOLIDATED_REPORT_PATH }}
+          fetch-depth: 2
 
-# M1 runner currently not well supported
-# TODO: (Dhruv) add these back when we setup better testing for Apple Silicon
-#  run_nightly_tests_apple_m1:
-#    name: Nightly PyTorch MPS tests on MacOS
-#    runs-on: [ self-hosted, apple-m1 ]
-#    if: github.event_name == 'schedule'
-#
-#    steps:
-#      - name: Checkout diffusers
-#        uses: actions/checkout@v3
-#        with:
-#          fetch-depth: 2
-#
-#      - name: Clean checkout
-#        shell: arch -arch arm64 bash {0}
-#        run: |
-#          git clean -fxd
-#      - name: Setup miniconda
-#        uses: ./.github/actions/setup-miniconda
-#        with:
-#          python-version: 3.9
-#
-#      - name: Install dependencies
-#        shell: arch -arch arm64 bash {0}
-#        run: |
-#          ${CONDA_RUN} pip install --upgrade pip uv
-#          ${CONDA_RUN} uv pip install -e ".[quality]"
-#          ${CONDA_RUN} uv pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cpu
-#          ${CONDA_RUN} uv pip install accelerate@git+https://github.com/huggingface/accelerate
-#          ${CONDA_RUN} uv pip install pytest-reportlog
-#      - name: Environment
-#        shell: arch -arch arm64 bash {0}
-#        run: |
-#          ${CONDA_RUN} python utils/print_env.py
-#      - name: Run nightly PyTorch tests on M1 (MPS)
-#        shell: arch -arch arm64 bash {0}
-#        env:
-#          HF_HOME: /System/Volumes/Data/mnt/cache
-#          HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
-#        run: |
-#          ${CONDA_RUN} pytest -n 1  --make-reports=tests_torch_mps \
-#            --report-log=tests_torch_mps.log \
-#            tests/
-#      - name: Failure short reports
-#        if: ${{ failure() }}
-#        run: cat reports/tests_torch_mps_failures_short.txt
-#
-#      - name: Test suite reports artifacts
-#        if: ${{ always() }}
-#        uses: actions/upload-artifact@v4
-#        with:
-#          name: torch_mps_test_reports
-#          path: reports
-#
-#      - name: Generate Report and Notify Channel
-#        if: always()
-#        run: |
-#          pip install slack_sdk tabulate
-#          python utils/log_reports.py >> $GITHUB_STEP_SUMMARY  run_nightly_tests_apple_m1:
-#    name: Nightly PyTorch MPS tests on MacOS
-#    runs-on: [ self-hosted, apple-m1 ]
-#    if: github.event_name == 'schedule'
-#
-#    steps:
-#      - name: Checkout diffusers
-#        uses: actions/checkout@v3
-#        with:
-#          fetch-depth: 2
-#
-#      - name: Clean checkout
-#        shell: arch -arch arm64 bash {0}
-#        run: |
-#          git clean -fxd
-#      - name: Setup miniconda
-#        uses: ./.github/actions/setup-miniconda
-#        with:
-#          python-version: 3.9
-#
-#      - name: Install dependencies
-#        shell: arch -arch arm64 bash {0}
-#        run: |
-#          ${CONDA_RUN} pip install --upgrade pip uv
-#          ${CONDA_RUN} uv pip install -e ".[quality]"
-#          ${CONDA_RUN} uv pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cpu
-#          ${CONDA_RUN} uv pip install accelerate@git+https://github.com/huggingface/accelerate
-#          ${CONDA_RUN} uv pip install pytest-reportlog
-#      - name: Environment
-#        shell: arch -arch arm64 bash {0}
-#        run: |
-#          ${CONDA_RUN} python utils/print_env.py
-#      - name: Run nightly PyTorch tests on M1 (MPS)
-#        shell: arch -arch arm64 bash {0}
-#        env:
-#          HF_HOME: /System/Volumes/Data/mnt/cache
-#          HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
-#        run: |
-#          ${CONDA_RUN} pytest -n 1  --make-reports=tests_torch_mps \
-#            --report-log=tests_torch_mps.log \
-#            tests/
-#      - name: Failure short reports
-#        if: ${{ failure() }}
-#        run: cat reports/tests_torch_mps_failures_short.txt
-#
-#      - name: Test suite reports artifacts
-#        if: ${{ always() }}
-#        uses: actions/upload-artifact@v4
-#        with:
-#          name: torch_mps_test_reports
-#          path: reports
-#
-#      - name: Generate Report and Notify Channel
-#        if: always()
-#        run: |
-#          pip install slack_sdk tabulate
-#          python utils/log_reports.py >> $GITHUB_STEP_SUMMARY
+      - name: Clean checkout
+        shell: arch -arch arm64 bash {0}
+        run: |
+          git clean -fxd
+
+      - name: Setup miniconda
+        uses: ./.github/actions/setup-miniconda
+        with:
+          python-version: 3.9
+
+      - name: Install dependencies
+        shell: arch -arch arm64 bash {0}
+        run: |
+          ${CONDA_RUN} python -m pip install --upgrade pip uv
+          ${CONDA_RUN} python -m uv pip install -e [quality,test]
+          ${CONDA_RUN} python -m uv pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cpu
+          ${CONDA_RUN} python -m uv pip install accelerate@git+https://github.com/huggingface/accelerate
+          ${CONDA_RUN} python -m uv pip install pytest-reportlog
+
+      - name: Environment
+        shell: arch -arch arm64 bash {0}
+        run: |
+          ${CONDA_RUN} python utils/print_env.py
+
+      - name: Run nightly PyTorch tests on M1 (MPS)
+        shell: arch -arch arm64 bash {0}
+        env:
+          HF_HOME: /System/Volumes/Data/mnt/cache
+          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 \
+            tests/
+
+      - name: Failure short reports
+        if: ${{ failure() }}
+        run: cat reports/tests_torch_mps_failures_short.txt
+
+      - name: Test suite reports artifacts
+        if: ${{ always() }}
+        uses: actions/upload-artifact@v2
+        with:
+          name: torch_mps_test_reports
+          path: reports
+
+      - name: Generate Report and Notify Channel
+        if: always()
+        run: |
+          pip install slack_sdk tabulate
+          python scripts/log_reports.py >> $GITHUB_STEP_SUMMARY

.github/workflows/notify_slack_about_release.yml

@@ -7,16 +7,16 @@ on:
 
 jobs:
   build:
-    runs-on: ubuntu-22.04
+    runs-on: ubuntu-latest
 
     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

@@ -16,7 +16,7 @@ concurrency:
 
 jobs:
   check_dependencies:
-    runs-on: ubuntu-22.04
+    runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v3
       - name: Set up Python
@@ -25,8 +25,12 @@ jobs:
           python-version: "3.8"
       - name: Install dependencies
         run: |
-          pip install -e .
-          pip install pytest
+          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+          python -m pip install --upgrade pip uv
+          python -m uv pip install -e .
+          python -m uv pip install pytest
       - name: Check for soft dependencies
         run: |
-            pytest tests/others/test_dependencies.py
+          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+          pytest tests/others/test_dependencies.py
+      

.github/workflows/pr_flax_dependency_test.yml

@@ -0,0 +1,38 @@
+name: Run Flax dependency tests
+
+on:
+  pull_request:
+    branches:
+      - main
+    paths:
+      - "src/diffusers/**.py"
+  push:
+    branches:
+      - main
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}
+  cancel-in-progress: true
+
+jobs:
+  check_flax_dependencies:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - 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:$PATH"
+          python -m pip install --upgrade pip uv
+          python -m uv pip install -e .
+          python -m uv pip install "jax[cpu]>=0.2.16,!=0.3.2"
+          python -m uv pip install "flax>=0.4.1"
+          python -m uv pip install "jaxlib>=0.1.65"
+          python -m uv pip install pytest
+      - name: Check for soft dependencies
+        run: |
+          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+          pytest tests/others/test_dependencies.py

.github/workflows/pr_modular_tests.yml

@@ -1,139 +0,0 @@
-name: Fast PR tests for Modular
-
-on:
-  pull_request:
-    branches: [main]
-    paths:
-      - "src/diffusers/modular_pipelines/**.py"
-      - "src/diffusers/models/modeling_utils.py"
-      - "src/diffusers/models/model_loading_utils.py"
-      - "src/diffusers/pipelines/pipeline_utils.py"
-      - "src/diffusers/pipeline_loading_utils.py"
-      - "src/diffusers/loaders/lora_base.py"
-      - "src/diffusers/loaders/lora_pipeline.py"
-      - "src/diffusers/loaders/peft.py"
-      - "tests/modular_pipelines/**.py"
-      - ".github/**.yml"
-      - "utils/**.py"
-      - "setup.py"
-  push:
-    branches:
-      - ci-*
-
-concurrency:
-  group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}
-  cancel-in-progress: true
-
-env:
-  DIFFUSERS_IS_CI: yes
-  HF_XET_HIGH_PERFORMANCE: 1
-  OMP_NUM_THREADS: 4
-  MKL_NUM_THREADS: 4
-  PYTEST_TIMEOUT: 60
-
-jobs:
-  check_code_quality:
-    runs-on: ubuntu-22.04
-    steps:
-      - uses: actions/checkout@v3
-      - name: Set up Python
-        uses: actions/setup-python@v4
-        with:
-          python-version: "3.10"
-      - name: Install dependencies
-        run: |
-          pip install --upgrade pip
-          pip install .[quality]
-      - name: Check quality
-        run: make quality
-      - name: Check if failure
-        if: ${{ failure() }}
-        run: |
-          echo "Quality check failed. Please ensure the right dependency versions are installed with 'pip install -e .[quality]' and run 'make style && make quality'" >> $GITHUB_STEP_SUMMARY
-
-  check_repository_consistency:
-    needs: check_code_quality
-    runs-on: ubuntu-22.04
-    steps:
-      - uses: actions/checkout@v3
-      - name: Set up Python
-        uses: actions/setup-python@v4
-        with:
-          python-version: "3.10"
-      - name: Install dependencies
-        run: |
-          pip install --upgrade pip
-          pip install .[quality]
-      - name: Check repo consistency
-        run: |
-          python utils/check_copies.py
-          python utils/check_dummies.py
-          python utils/check_support_list.py
-          make deps_table_check_updated
-      - name: Check if failure
-        if: ${{ failure() }}
-        run: |
-          echo "Repo consistency check failed. Please ensure the right dependency versions are installed with 'pip install -e .[quality]' and run 'make fix-copies'" >> $GITHUB_STEP_SUMMARY
-
-  run_fast_tests:
-    needs: [check_code_quality, check_repository_consistency]
-    strategy:
-      fail-fast: false
-      matrix:
-        config:
-          - name: Fast PyTorch Modular Pipeline CPU tests
-            framework: pytorch_pipelines
-            runner: aws-highmemory-32-plus
-            image: diffusers/diffusers-pytorch-cpu
-            report: torch_cpu_modular_pipelines
-
-    name: ${{ matrix.config.name }}
-
-    runs-on:
-      group: ${{ matrix.config.runner }}
-
-    container:
-      image: ${{ matrix.config.image }}
-      options: --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/
-
-    defaults:
-      run:
-        shell: bash
-
-    steps:
-    - name: Checkout diffusers
-      uses: actions/checkout@v3
-      with:
-        fetch-depth: 2
-
-    - name: Install dependencies
-      run: |
-        uv pip install -e ".[quality]"
-        #uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
-        uv pip uninstall transformers huggingface_hub && uv pip install transformers==4.57.1
-        uv pip uninstall accelerate && uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git --no-deps
-
-    - name: Environment
-      run: |
-        python utils/print_env.py
-
-    - name: Run fast PyTorch Pipeline CPU tests
-      if: ${{ matrix.config.framework == 'pytorch_pipelines' }}
-      run: |
-        pytest -n 8 --max-worker-restart=0 --dist=loadfile \
-          -k "not Flax and not Onnx" \
-          --make-reports=tests_${{ matrix.config.report }} \
-          tests/modular_pipelines
-
-    - name: Failure short reports
-      if: ${{ failure() }}
-      run: cat reports/tests_${{ matrix.config.report }}_failures_short.txt
-
-    - name: Test suite reports artifacts
-      if: ${{ always() }}
-      uses: actions/upload-artifact@v4
-      with:
-        name: pr_${{ matrix.config.framework }}_${{ matrix.config.report }}_test_reports
-        path: reports
-
-

.github/workflows/pr_style_bot.yml

@@ -1,17 +0,0 @@
-name: PR Style Bot
-
-on:
-  issue_comment:
-    types: [created]
-
-permissions:
-  contents: write
-  pull-requests: write
-
-jobs:
-  style:
-    uses: huggingface/huggingface_hub/.github/workflows/style-bot-action.yml@main
-    with:
-      python_quality_dependencies: "[quality]"
-    secrets:
-      bot_token: ${{ secrets.HF_STYLE_BOT_ACTION }}

.github/workflows/pr_test_fetcher.yml

@@ -15,8 +15,7 @@ concurrency:
 jobs:
   setup_pr_tests:
     name: Setup PR Tests
-    runs-on:
-      group: aws-general-8-plus
+    runs-on: docker-cpu
     container:
       image: diffusers/diffusers-pytorch-cpu
       options: --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/
@@ -33,7 +32,9 @@ jobs:
         fetch-depth: 0
     - name: Install dependencies
       run: |
-        uv pip install -e ".[quality]"
+        apt-get update && apt-get install libsndfile1-dev libgl1 -y
+        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
@@ -73,8 +74,7 @@ jobs:
       max-parallel: 2
       matrix:
         modules: ${{ fromJson(needs.setup_pr_tests.outputs.matrix) }}
-    runs-on:
-      group: aws-general-8-plus
+    runs-on: docker-cpu
     container:
       image: diffusers/diffusers-pytorch-cpu
       options: --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/
@@ -89,16 +89,20 @@ jobs:
 
     - name: Install dependencies
       run: |
-        uv pip install -e ".[quality]"
-        uv pip install accelerate
+        apt-get update && apt-get install libsndfile1-dev libgl1 -y
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+        python -m pip install -e [quality,test]
+        python -m pip install accelerate
 
     - name: Environment
       run: |
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
         python utils/print_env.py
 
     - name: Run all selected tests on CPU
       run: |
-        pytest -n 2 --dist=loadfile -v --make-reports=${{ matrix.modules }}_tests_cpu ${{ fromJson(needs.setup_pr_tests.outputs.test_map)[matrix.modules] }}
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+        python -m pytest -n 2 --dist=loadfile -v --make-reports=${{ matrix.modules }}_tests_cpu ${{ fromJson(needs.setup_pr_tests.outputs.test_map)[matrix.modules] }}
 
     - name: Failure short reports
       if: ${{ failure() }}
@@ -121,13 +125,12 @@ jobs:
         config:
           - name: Hub tests for models, schedulers, and pipelines
             framework: hub_tests_pytorch
-            runner: aws-general-8-plus
+            runner: docker-cpu
             image: diffusers/diffusers-pytorch-cpu
             report: torch_hub
 
     name: ${{ matrix.config.name }}
-    runs-on:
-      group: ${{ matrix.config.runner }}
+    runs-on: ${{ matrix.config.runner }}
     container:
       image: ${{ matrix.config.image }}
       options: --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/
@@ -144,16 +147,20 @@ jobs:
 
     - name: Install dependencies
       run: |
-        pip install -e [quality]
+        apt-get update && apt-get install libsndfile1-dev libgl1 -y
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+        python -m pip install -e [quality,test]
 
     - name: Environment
       run: |
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
         python utils/print_env.py
 
     - name: Run Hub tests for models, schedulers, and pipelines on a staging env
       if: ${{ matrix.config.framework == 'hub_tests_pytorch' }}
       run: |
-        HUGGINGFACE_CO_STAGING=true pytest \
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+        HUGGINGFACE_CO_STAGING=true python -m pytest \
           -m "is_staging_test" \
           --make-reports=tests_${{ matrix.config.report }} \
           tests
@@ -164,7 +171,7 @@ jobs:
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v4
+      uses: actions/upload-artifact@v2
       with:
         name: pr_${{ matrix.config.report }}_test_reports
         path: reports

.github/workflows/pr_test_peft_backend.yml

@@ -0,0 +1,108 @@
+name: Fast tests for PRs - PEFT backend
+
+on:
+  pull_request:
+    branches:
+      - main
+    paths:
+      - "src/diffusers/**.py"
+      - "tests/**.py"
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}
+  cancel-in-progress: true
+
+env:
+  DIFFUSERS_IS_CI: yes
+  OMP_NUM_THREADS: 4
+  MKL_NUM_THREADS: 4
+  PYTEST_TIMEOUT: 60
+
+jobs:
+  check_code_quality:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.8"
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install .[quality]
+      - name: Check quality
+        run: |
+          ruff check examples tests src utils scripts
+          ruff format examples tests src utils scripts --check
+
+  check_repository_consistency:
+    needs: check_code_quality
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.8"
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install .[quality]
+      - name: Check quality
+        run: |
+          python utils/check_copies.py
+          python utils/check_dummies.py
+          make deps_table_check_updated
+
+  run_fast_tests:
+    needs: [check_code_quality, check_repository_consistency]
+    strategy:
+      fail-fast: false
+      matrix:
+        lib-versions: ["main", "latest"]
+
+
+    name: LoRA - ${{ matrix.lib-versions }}
+
+    runs-on: docker-cpu
+
+    container:
+      image: diffusers/diffusers-pytorch-cpu
+      options: --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/
+
+    defaults:
+      run:
+        shell: bash
+
+    steps:
+    - name: Checkout diffusers
+      uses: actions/checkout@v3
+      with:
+        fetch-depth: 2
+
+    - name: Install dependencies
+      run: |
+        apt-get update && apt-get install libsndfile1-dev libgl1 -y
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+        python -m uv pip install -e [quality,test]
+        if [ "${{ matrix.lib-versions }}" == "main" ]; then
+            python -m uv pip install -U peft@git+https://github.com/huggingface/peft.git
+            python -m uv pip install -U transformers@git+https://github.com/huggingface/transformers.git
+            python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
+        else
+            python -m uv pip install -U peft transformers accelerate
+        fi
+
+    - name: Environment
+      run: |
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+        python utils/print_env.py
+
+    - name: Run fast PyTorch LoRA CPU tests with PEFT backend
+      run: |
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+        python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
+          -s -v \
+          --make-reports=tests_${{ matrix.config.report }} \
+          tests/lora/

.github/workflows/pr_tests.yml

@@ -2,7 +2,8 @@ name: Fast tests for PRs
 
 on:
   pull_request:
-    branches: [main]
+    branches:
+      - main
     paths:
       - "src/diffusers/**.py"
       - "benchmarks/**.py"
@@ -11,7 +12,6 @@ on:
       - "tests/**.py"
       - ".github/**.yml"
       - "utils/**.py"
-      - "setup.py"
   push:
     branches:
       - ci-*
@@ -22,14 +22,13 @@ concurrency:
 
 env:
   DIFFUSERS_IS_CI: yes
-  HF_XET_HIGH_PERFORMANCE: 1
   OMP_NUM_THREADS: 4
   MKL_NUM_THREADS: 4
   PYTEST_TIMEOUT: 60
 
 jobs:
   check_code_quality:
-    runs-on: ubuntu-22.04
+    runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v3
       - name: Set up Python
@@ -38,18 +37,16 @@ jobs:
           python-version: "3.8"
       - name: Install dependencies
         run: |
-          pip install --upgrade pip
+          python -m pip install --upgrade pip
           pip install .[quality]
       - name: Check quality
-        run: make quality
-      - name: Check if failure
-        if: ${{ failure() }}
         run: |
-          echo "Quality check failed. Please ensure the right dependency versions are installed with 'pip install -e .[quality]' and run 'make style && make quality'" >> $GITHUB_STEP_SUMMARY
+          ruff check examples tests src utils scripts
+          ruff format examples tests src utils scripts --check
 
   check_repository_consistency:
     needs: check_code_quality
-    runs-on: ubuntu-22.04
+    runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v3
       - name: Set up Python
@@ -58,18 +55,13 @@ jobs:
           python-version: "3.8"
       - name: Install dependencies
         run: |
-          pip install --upgrade pip
+          python -m pip install --upgrade pip
           pip install .[quality]
-      - name: Check repo consistency
+      - name: Check quality
         run: |
           python utils/check_copies.py
           python utils/check_dummies.py
-          python utils/check_support_list.py
           make deps_table_check_updated
-      - name: Check if failure
-        if: ${{ failure() }}
-        run: |
-          echo "Repo consistency check failed. Please ensure the right dependency versions are installed with 'pip install -e .[quality]' and run 'make fix-copies'" >> $GITHUB_STEP_SUMMARY
 
   run_fast_tests:
     needs: [check_code_quality, check_repository_consistency]
@@ -79,24 +71,28 @@ jobs:
         config:
           - name: Fast PyTorch Pipeline CPU tests
             framework: pytorch_pipelines
-            runner: aws-highmemory-32-plus
+            runner: docker-cpu
             image: diffusers/diffusers-pytorch-cpu
             report: torch_cpu_pipelines
           - name: Fast PyTorch Models & Schedulers CPU tests
             framework: pytorch_models
-            runner: aws-general-8-plus
+            runner: docker-cpu
             image: diffusers/diffusers-pytorch-cpu
             report: torch_cpu_models_schedulers
+          - name: Fast Flax CPU tests
+            framework: flax
+            runner: docker-cpu
+            image: diffusers/diffusers-flax-cpu
+            report: flax_cpu
           - name: PyTorch Example CPU tests
             framework: pytorch_examples
-            runner: aws-general-8-plus
+            runner: docker-cpu
             image: diffusers/diffusers-pytorch-cpu
             report: torch_example_cpu
 
     name: ${{ matrix.config.name }}
 
-    runs-on:
-      group: ${{ matrix.config.runner }}
+    runs-on: ${{ matrix.config.runner }}
 
     container:
       image: ${{ matrix.config.image }}
@@ -114,36 +110,49 @@ jobs:
 
     - name: Install dependencies
       run: |
-        uv pip install -e ".[quality]"
-        #uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
-        uv pip uninstall transformers huggingface_hub && uv pip install transformers==4.57.1
-        uv pip uninstall accelerate && uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git --no-deps
+        apt-get update && apt-get install libsndfile1-dev libgl1 -y
+        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
 
     - name: Environment
       run: |
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
         python utils/print_env.py
 
     - name: Run fast PyTorch Pipeline CPU tests
       if: ${{ matrix.config.framework == 'pytorch_pipelines' }}
       run: |
-        pytest -n 8 --max-worker-restart=0 --dist=loadfile \
-          -k "not Flax and not Onnx" \
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+        python -m pytest -n 2 --max-worker-restart=0 --dist=loadfile \
+          -s -v -k "not Flax and not Onnx" \
           --make-reports=tests_${{ matrix.config.report }} \
           tests/pipelines
 
     - name: Run fast PyTorch Model Scheduler CPU tests
       if: ${{ matrix.config.framework == 'pytorch_models' }}
       run: |
-        pytest -n 4 --max-worker-restart=0 --dist=loadfile \
-          -k "not Flax and not Onnx and not Dependency" \
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+        python -m pytest -n 2 --max-worker-restart=0 --dist=loadfile \
+          -s -v -k "not Flax and not Onnx and not Dependency" \
           --make-reports=tests_${{ matrix.config.report }} \
           tests/models tests/schedulers tests/others
 
+    - name: Run fast Flax TPU tests
+      if: ${{ matrix.config.framework == 'flax' }}
+      run: |
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+        python -m pytest -n 2 --max-worker-restart=0 --dist=loadfile \
+          -s -v -k "Flax" \
+          --make-reports=tests_${{ matrix.config.report }} \
+          tests
+
     - name: Run example PyTorch CPU tests
       if: ${{ matrix.config.framework == 'pytorch_examples' }}
       run: |
-        uv pip install ".[training]"
-        pytest -n 4 --max-worker-restart=0 --dist=loadfile \
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+        python -m uv pip install peft
+        python -m pytest -n 2 --max-worker-restart=0 --dist=loadfile \
           --make-reports=tests_${{ matrix.config.report }} \
           examples
 
@@ -153,9 +162,9 @@ jobs:
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v4
+      uses: actions/upload-artifact@v2
       with:
-        name: pr_${{ matrix.config.framework }}_${{ matrix.config.report }}_test_reports
+        name: pr_${{ matrix.config.report }}_test_reports
         path: reports
 
   run_staging_tests:
@@ -166,8 +175,7 @@ jobs:
         config:
           - name: Hub tests for models, schedulers, and pipelines
             framework: hub_tests_pytorch
-            runner:
-              group: aws-general-8-plus
+            runner: docker-cpu
             image: diffusers/diffusers-pytorch-cpu
             report: torch_hub
 
@@ -191,16 +199,20 @@ jobs:
 
     - name: Install dependencies
       run: |
-        uv pip install -e ".[quality]"
+        apt-get update && apt-get install libsndfile1-dev libgl1 -y
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+        python -m uv pip install -e [quality,test]
 
     - name: Environment
       run: |
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
         python utils/print_env.py
 
     - name: Run Hub tests for models, schedulers, and pipelines on a staging env
       if: ${{ matrix.config.framework == 'hub_tests_pytorch' }}
       run: |
-        HUGGINGFACE_CO_STAGING=true pytest \
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+        HUGGINGFACE_CO_STAGING=true python -m pytest \
           -m "is_staging_test" \
           --make-reports=tests_${{ matrix.config.report }} \
           tests
@@ -211,70 +223,7 @@ jobs:
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v4
+      uses: actions/upload-artifact@v2
       with:
         name: pr_${{ matrix.config.report }}_test_reports
         path: reports
-
-  run_lora_tests:
-    needs: [check_code_quality, check_repository_consistency]
-    strategy:
-      fail-fast: false
-
-    name: LoRA tests with PEFT main
-
-    runs-on:
-      group: aws-general-8-plus
-
-    container:
-      image: diffusers/diffusers-pytorch-cpu
-      options: --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/
-
-    defaults:
-      run:
-        shell: bash
-
-    steps:
-    - name: Checkout diffusers
-      uses: actions/checkout@v3
-      with:
-        fetch-depth: 2
-
-    - name: Install dependencies
-      run: |
-        uv pip install -e ".[quality]"
-        # TODO (sayakpaul, DN6): revisit `--no-deps`
-        uv pip install -U peft@git+https://github.com/huggingface/peft.git --no-deps
-        uv pip install -U tokenizers
-        uv pip uninstall accelerate && uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git --no-deps
-        #uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
-        uv pip uninstall transformers huggingface_hub && uv pip install transformers==4.57.1
-
-    - name: Environment
-      run: |
-        python utils/print_env.py
-
-    - name: Run fast PyTorch LoRA tests with PEFT
-      run: |
-        pytest -n 4 --max-worker-restart=0 --dist=loadfile \
-          \
-          --make-reports=tests_peft_main \
-          tests/lora/
-        pytest -n 4 --max-worker-restart=0 --dist=loadfile \
-          \
-          --make-reports=tests_models_lora_peft_main \
-          tests/models/ -k "lora"
-
-    - name: Failure short reports
-      if: ${{ failure() }}
-      run: |
-        cat reports/tests_peft_main_failures_short.txt
-        cat reports/tests_models_lora_peft_main_failures_short.txt
-
-    - name: Test suite reports artifacts
-      if: ${{ always() }}
-      uses: actions/upload-artifact@v4
-      with:
-        name: pr_main_test_reports
-        path: reports
-

.github/workflows/pr_tests_gpu.yml

@@ -1,294 +0,0 @@
-name: Fast GPU Tests on PR
-
-on:
-  pull_request:
-    branches: main
-    paths:
-      - "src/diffusers/models/modeling_utils.py"
-      - "src/diffusers/models/model_loading_utils.py"
-      - "src/diffusers/pipelines/pipeline_utils.py"
-      - "src/diffusers/pipeline_loading_utils.py"
-      - "src/diffusers/loaders/lora_base.py"
-      - "src/diffusers/loaders/lora_pipeline.py"
-      - "src/diffusers/loaders/peft.py"
-      - "tests/pipelines/test_pipelines_common.py"
-      - "tests/models/test_modeling_common.py"
-      - "examples/**/*.py"
-  workflow_dispatch:
-
-concurrency:
-  group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}
-  cancel-in-progress: true
-
-env:
-  DIFFUSERS_IS_CI: yes
-  OMP_NUM_THREADS: 8
-  MKL_NUM_THREADS: 8
-  HF_XET_HIGH_PERFORMANCE: 1
-  PYTEST_TIMEOUT: 600
-  PIPELINE_USAGE_CUTOFF: 1000000000 # set high cutoff so that only always-test pipelines run
-
-jobs:
-  check_code_quality:
-    runs-on: ubuntu-22.04
-    steps:
-      - uses: actions/checkout@v3
-      - name: Set up Python
-        uses: actions/setup-python@v4
-        with:
-          python-version: "3.8"
-      - name: Install dependencies
-        run: |
-          pip install --upgrade pip
-          pip install .[quality]
-      - name: Check quality
-        run: make quality
-      - name: Check if failure
-        if: ${{ failure() }}
-        run: |
-          echo "Quality check failed. Please ensure the right dependency versions are installed with 'pip install -e .[quality]' and run 'make style && make quality'" >> $GITHUB_STEP_SUMMARY
-
-  check_repository_consistency:
-    needs: check_code_quality
-    runs-on: ubuntu-22.04
-    steps:
-      - uses: actions/checkout@v3
-      - name: Set up Python
-        uses: actions/setup-python@v4
-        with:
-          python-version: "3.8"
-      - name: Install dependencies
-        run: |
-          pip install --upgrade pip
-          pip install .[quality]
-      - name: Check repo consistency
-        run: |
-          python utils/check_copies.py
-          python utils/check_dummies.py
-          python utils/check_support_list.py
-          make deps_table_check_updated
-      - name: Check if failure
-        if: ${{ failure() }}
-        run: |
-          echo "Repo consistency check failed. Please ensure the right dependency versions are installed with 'pip install -e .[quality]' and run 'make fix-copies'" >> $GITHUB_STEP_SUMMARY
-
-  setup_torch_cuda_pipeline_matrix:
-    needs: [check_code_quality, check_repository_consistency]
-    name: Setup Torch Pipelines CUDA Slow Tests Matrix
-    runs-on:
-      group: aws-general-8-plus
-    container:
-      image: diffusers/diffusers-pytorch-cpu
-    outputs:
-      pipeline_test_matrix: ${{ steps.fetch_pipeline_matrix.outputs.pipeline_test_matrix }}
-    steps:
-      - name: Checkout diffusers
-        uses: actions/checkout@v3
-        with:
-          fetch-depth: 2
-      - name: Install dependencies
-        run: |
-          uv pip install -e ".[quality]"
-      - name: Environment
-        run: |
-          python utils/print_env.py
-      - name: Fetch Pipeline Matrix
-        id: fetch_pipeline_matrix
-        run: |
-          matrix=$(python utils/fetch_torch_cuda_pipeline_test_matrix.py)
-          echo $matrix
-          echo "pipeline_test_matrix=$matrix" >> $GITHUB_OUTPUT
-      - name: Pipeline Tests Artifacts
-        if: ${{ always() }}
-        uses: actions/upload-artifact@v4
-        with:
-          name: test-pipelines.json
-          path: reports
-
-  torch_pipelines_cuda_tests:
-    name: Torch Pipelines CUDA Tests
-    needs: setup_torch_cuda_pipeline_matrix
-    strategy:
-      fail-fast: false
-      max-parallel: 8
-      matrix:
-        module: ${{ fromJson(needs.setup_torch_cuda_pipeline_matrix.outputs.pipeline_test_matrix) }}
-    runs-on:
-      group: aws-g4dn-2xlarge
-    container:
-      image: diffusers/diffusers-pytorch-cuda
-      options: --shm-size "16gb" --ipc host --gpus all
-    steps:
-      - name: Checkout diffusers
-        uses: actions/checkout@v3
-        with:
-          fetch-depth: 2
-
-      - name: NVIDIA-SMI
-        run: |
-          nvidia-smi
-      - name: Install dependencies
-        run: |
-          uv pip install -e ".[quality]"
-          uv pip uninstall accelerate && uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
-          #uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
-          uv pip uninstall transformers huggingface_hub && uv pip install transformers==4.57.1
-
-      - name: Environment
-        run: |
-          python utils/print_env.py
-      - name: Extract tests
-        id: extract_tests
-        run: |
-          pattern=$(python utils/extract_tests_from_mixin.py --type pipeline)
-          echo "$pattern" > /tmp/test_pattern.txt
-          echo "pattern_file=/tmp/test_pattern.txt" >> $GITHUB_OUTPUT
-
-      - name: PyTorch CUDA checkpoint tests on Ubuntu
-        env:
-          HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
-          # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
-          CUBLAS_WORKSPACE_CONFIG: :16:8
-        run: |
-          if [ "${{ matrix.module }}" = "ip_adapters" ]; then
-              pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-              -k "not Flax and not Onnx" \
-              --make-reports=tests_pipeline_${{ matrix.module }}_cuda \
-              tests/pipelines/${{ matrix.module }}
-          else
-              pattern=$(cat ${{ steps.extract_tests.outputs.pattern_file }})
-              pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-              -k "not Flax and not Onnx and $pattern" \
-              --make-reports=tests_pipeline_${{ matrix.module }}_cuda \
-              tests/pipelines/${{ matrix.module }}
-          fi
-
-      - 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: ${{ always() }}
-        uses: actions/upload-artifact@v4
-        with:
-          name: pipeline_${{ matrix.module }}_test_reports
-          path: reports
-
-  torch_cuda_tests:
-    name: Torch CUDA Tests
-    needs: [check_code_quality, check_repository_consistency]
-    runs-on:
-      group: aws-g4dn-2xlarge
-    container:
-      image: diffusers/diffusers-pytorch-cuda
-      options: --shm-size "16gb" --ipc host --gpus all
-    defaults:
-      run:
-        shell: bash
-    strategy:
-      fail-fast: false
-      max-parallel: 4
-      matrix:
-        module: [models, schedulers, lora, others]
-    steps:
-    - name: Checkout diffusers
-      uses: actions/checkout@v3
-      with:
-        fetch-depth: 2
-
-    - name: Install dependencies
-      run: |
-        uv pip install -e ".[quality]"
-        uv pip install peft@git+https://github.com/huggingface/peft.git
-        uv pip uninstall accelerate && uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
-        #uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
-        uv pip uninstall transformers huggingface_hub && uv pip install transformers==4.57.1
-
-    - name: Environment
-      run: |
-        python utils/print_env.py
-
-    - name: Extract tests
-      id: extract_tests
-      run: |
-        pattern=$(python utils/extract_tests_from_mixin.py --type ${{ matrix.module }})
-        echo "$pattern" > /tmp/test_pattern.txt
-        echo "pattern_file=/tmp/test_pattern.txt" >> $GITHUB_OUTPUT
-
-    - name: Run PyTorch CUDA tests
-      env:
-        HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
-        # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
-        CUBLAS_WORKSPACE_CONFIG: :16:8
-      run: |
-        pattern=$(cat ${{ steps.extract_tests.outputs.pattern_file }})
-        if [ -z "$pattern" ]; then
-          pytest -n 1  --max-worker-restart=0 --dist=loadfile -k "not Flax and not Onnx" tests/${{ matrix.module }} \
-          --make-reports=tests_torch_cuda_${{ matrix.module }}
-        else
-          pytest -n 1  --max-worker-restart=0 --dist=loadfile -k "not Flax and not Onnx and $pattern" tests/${{ matrix.module }} \
-          --make-reports=tests_torch_cuda_${{ matrix.module }}
-        fi
-
-    - name: Failure short reports
-      if: ${{ failure() }}
-      run: |
-        cat reports/tests_torch_cuda_${{ matrix.module }}_stats.txt
-        cat reports/tests_torch_cuda_${{ matrix.module }}_failures_short.txt
-
-    - name: Test suite reports artifacts
-      if: ${{ always() }}
-      uses: actions/upload-artifact@v4
-      with:
-        name: torch_cuda_test_reports_${{ matrix.module }}
-        path: reports
-
-  run_examples_tests:
-    name: Examples PyTorch CUDA tests on Ubuntu
-    needs: [check_code_quality, check_repository_consistency]
-    runs-on:
-      group: aws-g4dn-2xlarge
-
-    container:
-      image: diffusers/diffusers-pytorch-cuda
-      options: --gpus all --shm-size "16gb" --ipc host
-    steps:
-    - name: Checkout diffusers
-      uses: actions/checkout@v3
-      with:
-        fetch-depth: 2
-
-    - name: NVIDIA-SMI
-      run: |
-        nvidia-smi
-    - name: Install dependencies
-      run: |
-        #uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
-        uv pip uninstall transformers huggingface_hub && uv pip install transformers==4.57.1
-        uv pip install -e ".[quality,training]"
-
-    - name: Environment
-      run: |
-        python utils/print_env.py
-
-    - name: Run example tests on GPU
-      env:
-        HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
-      run: |
-        uv pip install ".[training]"
-        pytest -n 1 --max-worker-restart=0 --dist=loadfile --make-reports=examples_torch_cuda examples/
-
-    - name: Failure short reports
-      if: ${{ failure() }}
-      run: |
-        cat reports/examples_torch_cuda_stats.txt
-        cat reports/examples_torch_cuda_failures_short.txt
-
-    - name: Test suite reports artifacts
-      if: ${{ always() }}
-      uses: actions/upload-artifact@v4
-      with:
-        name: examples_test_reports
-        path: reports
-

.github/workflows/pr_torch_dependency_test.yml

@@ -16,7 +16,7 @@ concurrency:
 
 jobs:
   check_torch_dependencies:
-    runs-on: ubuntu-22.04
+    runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v3
       - name: Set up Python
@@ -25,8 +25,12 @@ jobs:
           python-version: "3.8"
       - name: Install dependencies
         run: |
-          pip install -e .
-          pip install torch torchvision torchaudio pytest
+          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+          python -m pip install --upgrade pip uv
+          python -m uv pip install -e .
+          python -m uv pip install torch torchvision torchaudio
+          python -m uv pip install pytest
       - name: Check for soft dependencies
         run: |
-            pytest tests/others/test_dependencies.py
+          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+          pytest tests/others/test_dependencies.py

.github/workflows/push_tests.yml

@@ -1,7 +1,6 @@
-name: Fast GPU Tests on main
+name: Slow Tests on main
 
 on:
-  workflow_dispatch:
   push:
     branches:
       - main
@@ -12,19 +11,17 @@ on:
 
 env:
   DIFFUSERS_IS_CI: yes
+  HF_HOME: /mnt/cache
   OMP_NUM_THREADS: 8
   MKL_NUM_THREADS: 8
-  HF_XET_HIGH_PERFORMANCE: 1
   PYTEST_TIMEOUT: 600
+  RUN_SLOW: yes
   PIPELINE_USAGE_CUTOFF: 50000
 
 jobs:
   setup_torch_cuda_pipeline_matrix:
     name: Setup Torch Pipelines CUDA Slow Tests Matrix
-    runs-on:
-      group: aws-general-8-plus
-    container:
-      image: diffusers/diffusers-pytorch-cpu
+    runs-on: ubuntu-latest
     outputs:
       pipeline_test_matrix: ${{ steps.fetch_pipeline_matrix.outputs.pipeline_test_matrix }}
     steps:
@@ -32,12 +29,14 @@ jobs:
         uses: actions/checkout@v3
         with:
           fetch-depth: 2
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.8"
       - name: Install dependencies
         run: |
-          uv pip install -e ".[quality]"
-      - name: Environment
-        run: |
-          python utils/print_env.py
+          pip install -e .
+          pip install huggingface_hub
       - name: Fetch Pipeline Matrix
         id: fetch_pipeline_matrix
         run: |
@@ -46,24 +45,22 @@ jobs:
           echo "pipeline_test_matrix=$matrix" >> $GITHUB_OUTPUT
       - name: Pipeline Tests Artifacts
         if: ${{ always() }}
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v2
         with:
           name: test-pipelines.json
           path: reports
 
   torch_pipelines_cuda_tests:
-    name: Torch Pipelines CUDA Tests
+    name: Torch Pipelines CUDA Slow Tests
     needs: setup_torch_cuda_pipeline_matrix
     strategy:
       fail-fast: false
-      max-parallel: 8
       matrix:
         module: ${{ fromJson(needs.setup_torch_cuda_pipeline_matrix.outputs.pipeline_test_matrix) }}
-    runs-on:
-      group: aws-g4dn-2xlarge
+    runs-on: [single-gpu, nvidia-gpu, t4, ci]
     container:
       image: diffusers/diffusers-pytorch-cuda
-      options: --shm-size "16gb" --ipc host --gpus all
+      options: --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/ --gpus 0
     steps:
       - name: Checkout diffusers
         uses: actions/checkout@v3
@@ -74,21 +71,21 @@ jobs:
           nvidia-smi
       - name: Install dependencies
         run: |
-          uv pip install -e ".[quality]"
-          uv pip uninstall accelerate && uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
-          #uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
-          uv pip uninstall transformers huggingface_hub && uv pip install transformers==4.57.1
+          apt-get update && apt-get install libsndfile1-dev libgl1 -y
+          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+          python -m uv pip install -e [quality,test]
+          python -m uv pip install accelerate@git+https://github.com/huggingface/accelerate.git
       - name: Environment
         run: |
           python utils/print_env.py
-      - name: PyTorch CUDA checkpoint tests on Ubuntu
+      - name: Slow PyTorch CUDA checkpoint tests on Ubuntu
         env:
-          HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
+          HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
           # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
           CUBLAS_WORKSPACE_CONFIG: :16:8
         run: |
-          pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-            -k "not Flax and not Onnx" \
+          python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
+            -s -v -k "not Flax and not Onnx" \
             --make-reports=tests_pipeline_${{ matrix.module }}_cuda \
             tests/pipelines/${{ matrix.module }}
       - name: Failure short reports
@@ -96,28 +93,26 @@ jobs:
         run: |
           cat reports/tests_pipeline_${{ matrix.module }}_cuda_stats.txt
           cat reports/tests_pipeline_${{ matrix.module }}_cuda_failures_short.txt
+
       - name: Test suite reports artifacts
         if: ${{ always() }}
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v2
         with:
           name: pipeline_${{ matrix.module }}_test_reports
           path: reports
 
   torch_cuda_tests:
     name: Torch CUDA Tests
-    runs-on:
-      group: aws-g4dn-2xlarge
+    runs-on: docker-gpu
     container:
       image: diffusers/diffusers-pytorch-cuda
-      options: --shm-size "16gb" --ipc host --gpus all
+      options: --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/ --gpus 0
     defaults:
       run:
         shell: bash
     strategy:
-      fail-fast: false
-      max-parallel: 2
       matrix:
-        module: [models, schedulers, lora, others, single_file]
+        module: [models, schedulers, lora, others]
     steps:
     - name: Checkout diffusers
       uses: actions/checkout@v3
@@ -126,49 +121,194 @@ jobs:
 
     - name: Install dependencies
       run: |
-        uv pip install -e ".[quality]"
-        uv pip install peft@git+https://github.com/huggingface/peft.git
-        uv pip uninstall accelerate && uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
-        #uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
-        uv pip uninstall transformers huggingface_hub && uv pip install transformers==4.57.1
+        apt-get update && apt-get install libsndfile1-dev libgl1 -y
+        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
 
     - name: Environment
       run: |
         python utils/print_env.py
 
-    - name: Run PyTorch CUDA tests
+    - name: Run slow PyTorch CUDA tests
       env:
-        HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
+        HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
         # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
         CUBLAS_WORKSPACE_CONFIG: :16:8
       run: |
-        pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-          -k "not Flax and not Onnx" \
-          --make-reports=tests_torch_cuda_${{ matrix.module }} \
+        python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
+          -s -v -k "not Flax and not Onnx" \
+          --make-reports=tests_torch_cuda \
           tests/${{ matrix.module }}
 
     - name: Failure short reports
       if: ${{ failure() }}
       run: |
-        cat reports/tests_torch_cuda_${{ matrix.module }}_stats.txt
-        cat reports/tests_torch_cuda_${{ matrix.module }}_failures_short.txt
+        cat reports/tests_torch_cuda_stats.txt
+        cat reports/tests_torch_cuda_failures_short.txt
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v4
+      uses: actions/upload-artifact@v2
       with:
-        name: torch_cuda_test_reports_${{ matrix.module }}
+        name: torch_cuda_test_reports
+        path: reports
+
+  peft_cuda_tests:
+    name: PEFT CUDA Tests
+    runs-on: docker-gpu
+    container:
+      image: diffusers/diffusers-pytorch-cuda
+      options: --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/ --gpus 0
+    defaults:
+      run:
+        shell: bash
+    steps:
+    - name: Checkout diffusers
+      uses: actions/checkout@v3
+      with:
+        fetch-depth: 2
+
+    - name: Install dependencies
+      run: |
+        apt-get update && apt-get install libsndfile1-dev libgl1 -y
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+        python -m uv pip install -e [quality,test]
+        python -m uv pip install accelerate@git+https://github.com/huggingface/accelerate.git
+        python -m uv pip install peft@git+https://github.com/huggingface/peft.git
+
+    - name: Environment
+      run: |
+        python utils/print_env.py
+
+    - name: Run slow PEFT CUDA tests
+      env:
+        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 and not PEFTLoRALoading" \
+          --make-reports=tests_peft_cuda \
+          tests/lora/
+
+    - name: Failure short reports
+      if: ${{ failure() }}
+      run: |
+        cat reports/tests_peft_cuda_stats.txt
+        cat reports/tests_peft_cuda_failures_short.txt
+
+    - name: Test suite reports artifacts
+      if: ${{ always() }}
+      uses: actions/upload-artifact@v2
+      with:
+        name: torch_peft_test_reports
+        path: reports
+
+  flax_tpu_tests:
+    name: Flax TPU Tests
+    runs-on: docker-tpu
+    container:
+      image: diffusers/diffusers-flax-tpu
+      options: --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/ --privileged
+    defaults:
+      run:
+        shell: bash
+    steps:
+    - name: Checkout diffusers
+      uses: actions/checkout@v3
+      with:
+        fetch-depth: 2
+
+    - name: Install dependencies
+      run: |
+        apt-get update && apt-get install libsndfile1-dev libgl1 -y
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+        python -m uv pip install -e [quality,test]
+        python -m uv pip install accelerate@git+https://github.com/huggingface/accelerate.git
+
+    - name: Environment
+      run: |
+        python utils/print_env.py
+
+    - name: Run slow Flax TPU tests
+      env:
+        HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
+      run: |
+        python -m pytest -n 0 \
+          -s -v -k "Flax" \
+          --make-reports=tests_flax_tpu \
+          tests/
+
+    - name: Failure short reports
+      if: ${{ failure() }}
+      run: |
+        cat reports/tests_flax_tpu_stats.txt
+        cat reports/tests_flax_tpu_failures_short.txt
+
+    - name: Test suite reports artifacts
+      if: ${{ always() }}
+      uses: actions/upload-artifact@v2
+      with:
+        name: flax_tpu_test_reports
+        path: reports
+
+  onnx_cuda_tests:
+    name: ONNX CUDA Tests
+    runs-on: docker-gpu
+    container:
+      image: diffusers/diffusers-onnxruntime-cuda
+      options: --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/ --gpus 0
+    defaults:
+      run:
+        shell: bash
+    steps:
+    - name: Checkout diffusers
+      uses: actions/checkout@v3
+      with:
+        fetch-depth: 2
+
+    - name: Install dependencies
+      run: |
+        apt-get update && apt-get install libsndfile1-dev libgl1 -y
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+        python -m uv pip install -e [quality,test]
+        python -m uv pip install accelerate@git+https://github.com/huggingface/accelerate.git
+
+    - name: Environment
+      run: |
+        python utils/print_env.py
+
+    - name: Run slow ONNXRuntime CUDA tests
+      env:
+        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 \
+          tests/
+
+    - name: Failure short reports
+      if: ${{ failure() }}
+      run: |
+        cat reports/tests_onnx_cuda_stats.txt
+        cat reports/tests_onnx_cuda_failures_short.txt
+
+    - name: Test suite reports artifacts
+      if: ${{ always() }}
+      uses: actions/upload-artifact@v2
+      with:
+        name: onnx_cuda_test_reports
         path: reports
 
   run_torch_compile_tests:
     name: PyTorch Compile CUDA tests
 
-    runs-on:
-      group: aws-g4dn-2xlarge
+    runs-on: docker-gpu
 
     container:
-      image: diffusers/diffusers-pytorch-cuda
-      options: --gpus all --shm-size "16gb" --ipc host
+      image: diffusers/diffusers-pytorch-compile-cuda
+      options: --gpus 0 --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/
 
     steps:
     - name: Checkout diffusers
@@ -181,25 +321,23 @@ jobs:
         nvidia-smi
     - name: Install dependencies
       run: |
-        uv pip install -e ".[quality,training]"
-        #uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
-        uv pip uninstall transformers huggingface_hub && uv pip install transformers==4.57.1
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+        python -m uv pip install -e [quality,test,training]
     - name: Environment
       run: |
         python utils/print_env.py
     - name: Run example tests on GPU
       env:
-        HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
-        RUN_COMPILE: yes
+        HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
       run: |
-        pytest -n 1 --max-worker-restart=0 --dist=loadfile -k "compile" --make-reports=tests_torch_compile_cuda tests/
+        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
       if: ${{ failure() }}
       run: cat reports/tests_torch_compile_cuda_failures_short.txt
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v4
+      uses: actions/upload-artifact@v2
       with:
         name: torch_compile_test_reports
         path: reports
@@ -207,12 +345,11 @@ jobs:
   run_xformers_tests:
     name: PyTorch xformers CUDA tests
 
-    runs-on:
-      group: aws-g4dn-2xlarge
+    runs-on: docker-gpu
 
     container:
       image: diffusers/diffusers-pytorch-xformers-cuda
-      options: --gpus all --shm-size "16gb" --ipc host
+      options: --gpus 0 --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/
 
     steps:
     - name: Checkout diffusers
@@ -225,22 +362,23 @@ jobs:
         nvidia-smi
     - name: Install dependencies
       run: |
-        uv pip install -e ".[quality,training]"
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+        python -m uv pip install -e [quality,test,training]
     - name: Environment
       run: |
         python utils/print_env.py
     - name: Run example tests on GPU
       env:
-        HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
+        HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
       run: |
-        pytest -n 1 --max-worker-restart=0 --dist=loadfile -k "xformers" --make-reports=tests_torch_xformers_cuda tests/
+        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
       if: ${{ failure() }}
       run: cat reports/tests_torch_xformers_cuda_failures_short.txt
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v4
+      uses: actions/upload-artifact@v2
       with:
         name: torch_xformers_test_reports
         path: reports
@@ -248,12 +386,12 @@ jobs:
   run_examples_tests:
     name: Examples PyTorch CUDA tests on Ubuntu
 
-    runs-on:
-      group: aws-g4dn-2xlarge
+    runs-on: docker-gpu
 
     container:
       image: diffusers/diffusers-pytorch-cuda
-      options: --gpus all --shm-size "16gb" --ipc host
+      options: --gpus 0 --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/
+
     steps:
     - name: Checkout diffusers
       uses: actions/checkout@v3
@@ -263,20 +401,23 @@ jobs:
     - name: NVIDIA-SMI
       run: |
         nvidia-smi
+
     - name: Install dependencies
       run: |
-        uv pip install -e ".[quality,training]"
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+        python -m uv pip install -e [quality,test,training]
 
     - name: Environment
       run: |
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
         python utils/print_env.py
 
     - name: Run example tests on GPU
       env:
-        HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
+        HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
       run: |
-        uv pip install ".[training]"
-        pytest -n 1 --max-worker-restart=0 --dist=loadfile --make-reports=examples_torch_cuda examples/
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+        python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile -s -v --make-reports=examples_torch_cuda examples/
 
     - name: Failure short reports
       if: ${{ failure() }}
@@ -286,7 +427,7 @@ jobs:
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v4
+      uses: actions/upload-artifact@v2
       with:
         name: examples_test_reports
-        path: reports
+        path: reports

.github/workflows/push_tests_fast.yml

@@ -18,7 +18,6 @@ env:
   HF_HOME: /mnt/cache
   OMP_NUM_THREADS: 8
   MKL_NUM_THREADS: 8
-  HF_XET_HIGH_PERFORMANCE: 1
   PYTEST_TIMEOUT: 600
   RUN_SLOW: no
 
@@ -30,19 +29,28 @@ jobs:
         config:
           - name: Fast PyTorch CPU tests on Ubuntu
             framework: pytorch
-            runner: aws-general-8-plus
+            runner: docker-cpu
             image: diffusers/diffusers-pytorch-cpu
             report: torch_cpu
+          - name: Fast Flax CPU tests on Ubuntu
+            framework: flax
+            runner: docker-cpu
+            image: diffusers/diffusers-flax-cpu
+            report: flax_cpu
+          - name: Fast ONNXRuntime CPU tests on Ubuntu
+            framework: onnxruntime
+            runner: docker-cpu
+            image: diffusers/diffusers-onnxruntime-cpu
+            report: onnx_cpu
           - name: PyTorch Example CPU tests on Ubuntu
             framework: pytorch_examples
-            runner: aws-general-8-plus
+            runner: docker-cpu
             image: diffusers/diffusers-pytorch-cpu
             report: torch_example_cpu
 
     name: ${{ matrix.config.name }}
 
-    runs-on:
-      group: ${{ matrix.config.runner }}
+    runs-on: ${{ matrix.config.runner }}
 
     container:
       image: ${{ matrix.config.image }}
@@ -60,25 +68,48 @@ jobs:
 
     - name: Install dependencies
       run: |
-        uv pip install -e ".[quality]"
+        apt-get update && apt-get install libsndfile1-dev libgl1 -y
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+        python -m uv pip install -e [quality,test]
 
     - name: Environment
       run: |
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
         python utils/print_env.py
 
     - name: Run fast PyTorch CPU tests
       if: ${{ matrix.config.framework == 'pytorch' }}
       run: |
-        pytest -n 4 --max-worker-restart=0 --dist=loadfile \
-          -k "not Flax and not Onnx" \
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+        python -m pytest -n 2 --max-worker-restart=0 --dist=loadfile \
+          -s -v -k "not Flax and not Onnx" \
+          --make-reports=tests_${{ matrix.config.report }} \
+          tests/
+
+    - name: Run fast Flax TPU tests
+      if: ${{ matrix.config.framework == 'flax' }}
+      run: |
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+        python -m pytest -n 2 --max-worker-restart=0 --dist=loadfile \
+          -s -v -k "Flax" \
+          --make-reports=tests_${{ matrix.config.report }} \
+          tests/
+
+    - name: Run fast ONNXRuntime CPU tests
+      if: ${{ matrix.config.framework == 'onnxruntime' }}
+      run: |
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+        python -m pytest -n 2 --max-worker-restart=0 --dist=loadfile \
+          -s -v -k "Onnx" \
           --make-reports=tests_${{ matrix.config.report }} \
           tests/
 
     - name: Run example PyTorch CPU tests
       if: ${{ matrix.config.framework == 'pytorch_examples' }}
       run: |
-        uv pip install ".[training]"
-        pytest -n 4 --max-worker-restart=0 --dist=loadfile \
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+        python -m uv pip install peft
+        python -m pytest -n 2 --max-worker-restart=0 --dist=loadfile \
           --make-reports=tests_${{ matrix.config.report }} \
           examples
 
@@ -88,7 +119,7 @@ jobs:
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v4
+      uses: actions/upload-artifact@v2
       with:
         name: pr_${{ matrix.config.report }}_test_reports
         path: reports

.github/workflows/push_tests_mps.yml

@@ -1,14 +1,18 @@
 name: Fast mps tests on main
 
 on:
-  workflow_dispatch:
+  push:
+    branches:
+      - main
+    paths:
+      - "src/diffusers/**.py"
+      - "tests/**.py"
 
 env:
   DIFFUSERS_IS_CI: yes
   HF_HOME: /mnt/cache
   OMP_NUM_THREADS: 8
   MKL_NUM_THREADS: 8
-  HF_XET_HIGH_PERFORMANCE: 1
   PYTEST_TIMEOUT: 600
   RUN_SLOW: no
 
@@ -19,7 +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
@@ -41,7 +45,7 @@ jobs:
       shell: arch -arch arm64 bash {0}
       run: |
         ${CONDA_RUN} python -m pip install --upgrade pip uv
-        ${CONDA_RUN} python -m uv pip install -e ".[quality,test]"
+        ${CONDA_RUN} python -m uv pip install -e [quality,test]
         ${CONDA_RUN} python -m uv pip install torch torchvision torchaudio
         ${CONDA_RUN} python -m uv pip install accelerate@git+https://github.com/huggingface/accelerate.git
         ${CONDA_RUN} python -m uv pip install transformers --upgrade
@@ -55,9 +59,9 @@ 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 --make-reports=tests_torch_mps tests/
+        ${CONDA_RUN} python -m pytest -n 0 -s -v --make-reports=tests_torch_mps tests/
 
     - name: Failure short reports
       if: ${{ failure() }}
@@ -65,7 +69,7 @@ jobs:
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v4
+      uses: actions/upload-artifact@v2
       with:
         name: pr_torch_mps_test_reports
         path: reports

.github/workflows/pypi_publish.yaml

@@ -10,7 +10,7 @@ on:
 
 jobs:
   find-and-checkout-latest-branch:
-    runs-on: ubuntu-22.04
+    runs-on: ubuntu-latest
     outputs:
       latest_branch: ${{ steps.set_latest_branch.outputs.latest_branch }}
     steps:
@@ -29,46 +29,46 @@ jobs:
           LATEST_BRANCH=$(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 }}"
 
   release:
     needs: find-and-checkout-latest-branch
-    runs-on: ubuntu-22.04
+    runs-on: ubuntu-latest
 
     steps:
       - name: Checkout Repo
         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: |
           pip install diffusers && pip uninstall diffusers -y
-          pip install -i https://test.pypi.org/simple/ diffusers
+          pip install -i https://testpypi.python.org/pypi diffusers
           python -c "from diffusers import __version__; print(__version__)"
           python -c "from diffusers import DiffusionPipeline; pipe = DiffusionPipeline.from_pretrained('fusing/unet-ldm-dummy-update'); pipe()"
           python -c "from diffusers import DiffusionPipeline; pipe = DiffusionPipeline.from_pretrained('hf-internal-testing/tiny-stable-diffusion-pipe', safety_checker=None); pipe('ah suh du')"

.github/workflows/release_tests_fast.yml

@@ -1,342 +0,0 @@
-# Duplicate workflow to push_tests.yml that is meant to run on release/patch branches as a final check
-# Creating a duplicate workflow here is simpler than adding complex path/branch parsing logic to push_tests.yml
-# Needs to be updated if push_tests.yml updated
-name: (Release) Fast GPU Tests on main
-
-on:
-  push:
-    branches:
-      - "v*.*.*-release"
-      - "v*.*.*-patch"
-
-env:
-  DIFFUSERS_IS_CI: yes
-  OMP_NUM_THREADS: 8
-  MKL_NUM_THREADS: 8
-  PYTEST_TIMEOUT: 600
-  PIPELINE_USAGE_CUTOFF: 50000
-
-jobs:
-  setup_torch_cuda_pipeline_matrix:
-    name: Setup Torch Pipelines CUDA Slow Tests Matrix
-    runs-on:
-      group: aws-general-8-plus
-    container:
-      image: diffusers/diffusers-pytorch-cpu
-    outputs:
-      pipeline_test_matrix: ${{ steps.fetch_pipeline_matrix.outputs.pipeline_test_matrix }}
-    steps:
-      - name: Checkout diffusers
-        uses: actions/checkout@v3
-        with:
-          fetch-depth: 2
-      - name: Install dependencies
-        run: |
-          uv pip install -e ".[quality]"
-      - name: Environment
-        run: |
-          python utils/print_env.py
-      - name: Fetch Pipeline Matrix
-        id: fetch_pipeline_matrix
-        run: |
-          matrix=$(python utils/fetch_torch_cuda_pipeline_test_matrix.py)
-          echo $matrix
-          echo "pipeline_test_matrix=$matrix" >> $GITHUB_OUTPUT
-      - name: Pipeline Tests Artifacts
-        if: ${{ always() }}
-        uses: actions/upload-artifact@v4
-        with:
-          name: test-pipelines.json
-          path: reports
-
-  torch_pipelines_cuda_tests:
-    name: Torch Pipelines CUDA Tests
-    needs: setup_torch_cuda_pipeline_matrix
-    strategy:
-      fail-fast: false
-      max-parallel: 8
-      matrix:
-        module: ${{ fromJson(needs.setup_torch_cuda_pipeline_matrix.outputs.pipeline_test_matrix) }}
-    runs-on:
-      group: aws-g4dn-2xlarge
-    container:
-      image: diffusers/diffusers-pytorch-cuda
-      options: --shm-size "16gb" --ipc host --gpus all
-    steps:
-      - name: Checkout diffusers
-        uses: actions/checkout@v3
-        with:
-          fetch-depth: 2
-      - name: NVIDIA-SMI
-        run: |
-          nvidia-smi
-      - name: Install dependencies
-        run: |
-          uv pip install -e ".[quality]"
-          uv pip uninstall accelerate && uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
-      - name: Environment
-        run: |
-          python utils/print_env.py
-      - name: Slow PyTorch CUDA checkpoint tests on Ubuntu
-        env:
-          HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
-          # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
-          CUBLAS_WORKSPACE_CONFIG: :16:8
-        run: |
-          pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-            -k "not Flax and not Onnx" \
-            --make-reports=tests_pipeline_${{ matrix.module }}_cuda \
-            tests/pipelines/${{ matrix.module }}
-      - name: Failure short reports
-        if: ${{ failure() }}
-        run: |
-          cat reports/tests_pipeline_${{ matrix.module }}_cuda_stats.txt
-          cat reports/tests_pipeline_${{ matrix.module }}_cuda_failures_short.txt
-      - name: Test suite reports artifacts
-        if: ${{ always() }}
-        uses: actions/upload-artifact@v4
-        with:
-          name: pipeline_${{ matrix.module }}_test_reports
-          path: reports
-
-  torch_cuda_tests:
-    name: Torch CUDA Tests
-    runs-on:
-      group: aws-g4dn-2xlarge
-    container:
-      image: diffusers/diffusers-pytorch-cuda
-      options: --shm-size "16gb" --ipc host --gpus all
-    defaults:
-      run:
-        shell: bash
-    strategy:
-      fail-fast: false
-      max-parallel: 2
-      matrix:
-        module: [models, schedulers, lora, others, single_file]
-    steps:
-    - name: Checkout diffusers
-      uses: actions/checkout@v3
-      with:
-        fetch-depth: 2
-
-    - name: Install dependencies
-      run: |
-        uv pip install -e ".[quality]"
-        uv pip install peft@git+https://github.com/huggingface/peft.git
-        uv pip uninstall accelerate && uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
-
-    - name: Environment
-      run: |
-        python utils/print_env.py
-
-    - name: Run PyTorch CUDA tests
-      env:
-        HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
-        # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
-        CUBLAS_WORKSPACE_CONFIG: :16:8
-      run: |
-        pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-          -k "not Flax and not Onnx" \
-          --make-reports=tests_torch_${{ matrix.module }}_cuda \
-          tests/${{ matrix.module }}
-
-    - name: Failure short reports
-      if: ${{ failure() }}
-      run: |
-        cat reports/tests_torch_${{ matrix.module }}_cuda_stats.txt
-        cat reports/tests_torch_${{ matrix.module }}_cuda_failures_short.txt
-
-    - name: Test suite reports artifacts
-      if: ${{ always() }}
-      uses: actions/upload-artifact@v4
-      with:
-        name: torch_cuda_${{ matrix.module }}_test_reports
-        path: reports
-
-  torch_minimum_version_cuda_tests:
-    name: Torch Minimum Version CUDA Tests
-    runs-on:
-      group: aws-g4dn-2xlarge
-    container:
-      image: diffusers/diffusers-pytorch-minimum-cuda
-      options: --shm-size "16gb" --ipc host --gpus all
-    defaults:
-      run:
-        shell: bash
-    steps:
-      - name: Checkout diffusers
-        uses: actions/checkout@v3
-        with:
-          fetch-depth: 2
-
-      - name: Install dependencies
-        run: |
-          uv pip install -e ".[quality]"
-          uv pip install peft@git+https://github.com/huggingface/peft.git
-          uv pip uninstall accelerate && uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
-
-      - name: Environment
-        run: |
-          python utils/print_env.py
-
-      - name: Run PyTorch CUDA tests
-        env:
-          HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
-          # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
-          CUBLAS_WORKSPACE_CONFIG: :16:8
-        run: |
-          pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-            -k "not Flax and not Onnx" \
-            --make-reports=tests_torch_minimum_cuda \
-            tests/models/test_modeling_common.py \
-            tests/pipelines/test_pipelines_common.py \
-            tests/pipelines/test_pipeline_utils.py \
-            tests/pipelines/test_pipelines.py \
-            tests/pipelines/test_pipelines_auto.py \
-            tests/schedulers/test_schedulers.py \
-            tests/others
-
-      - name: Failure short reports
-        if: ${{ failure() }}
-        run: |
-          cat reports/tests_torch_minimum_version_cuda_stats.txt
-          cat reports/tests_torch_minimum_version_cuda_failures_short.txt
-
-      - name: Test suite reports artifacts
-        if: ${{ always() }}
-        uses: actions/upload-artifact@v4
-        with:
-          name: torch_minimum_version_cuda_test_reports
-          path: reports
-
-  run_torch_compile_tests:
-    name: PyTorch Compile CUDA tests
-
-    runs-on:
-      group: aws-g4dn-2xlarge
-
-    container:
-      image: diffusers/diffusers-pytorch-cuda
-      options: --gpus all --shm-size "16gb" --ipc host
-
-    steps:
-    - name: Checkout diffusers
-      uses: actions/checkout@v3
-      with:
-        fetch-depth: 2
-
-    - name: NVIDIA-SMI
-      run: |
-        nvidia-smi
-    - name: Install dependencies
-      run: |
-        uv pip install -e ".[quality,training]"
-    - name: Environment
-      run: |
-        python utils/print_env.py
-    - name: Run torch compile tests on GPU
-      env:
-        HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
-        RUN_COMPILE: yes
-      run: |
-        pytest -n 1 --max-worker-restart=0 --dist=loadfile -k "compile" --make-reports=tests_torch_compile_cuda tests/
-    - name: Failure short reports
-      if: ${{ failure() }}
-      run: cat reports/tests_torch_compile_cuda_failures_short.txt
-
-    - name: Test suite reports artifacts
-      if: ${{ always() }}
-      uses: actions/upload-artifact@v4
-      with:
-        name: torch_compile_test_reports
-        path: reports
-
-  run_xformers_tests:
-    name: PyTorch xformers CUDA tests
-
-    runs-on:
-      group: aws-g4dn-2xlarge
-
-    container:
-      image: diffusers/diffusers-pytorch-xformers-cuda
-      options: --gpus all --shm-size "16gb" --ipc host
-
-    steps:
-    - name: Checkout diffusers
-      uses: actions/checkout@v3
-      with:
-        fetch-depth: 2
-
-    - name: NVIDIA-SMI
-      run: |
-        nvidia-smi
-    - name: Install dependencies
-      run: |
-        uv pip install -e ".[quality,training]"
-    - name: Environment
-      run: |
-        python utils/print_env.py
-    - name: Run example tests on GPU
-      env:
-        HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
-      run: |
-        pytest -n 1 --max-worker-restart=0 --dist=loadfile -k "xformers" --make-reports=tests_torch_xformers_cuda tests/
-    - name: Failure short reports
-      if: ${{ failure() }}
-      run: cat reports/tests_torch_xformers_cuda_failures_short.txt
-
-    - name: Test suite reports artifacts
-      if: ${{ always() }}
-      uses: actions/upload-artifact@v4
-      with:
-        name: torch_xformers_test_reports
-        path: reports
-
-  run_examples_tests:
-    name: Examples PyTorch CUDA tests on Ubuntu
-
-    runs-on:
-      group: aws-g4dn-2xlarge
-
-    container:
-      image: diffusers/diffusers-pytorch-cuda
-      options: --gpus all --shm-size "16gb" --ipc host
-
-    steps:
-    - name: Checkout diffusers
-      uses: actions/checkout@v3
-      with:
-        fetch-depth: 2
-
-    - name: NVIDIA-SMI
-      run: |
-        nvidia-smi
-
-    - name: Install dependencies
-      run: |
-        uv pip install -e ".[quality,training]"
-
-    - name: Environment
-      run: |
-        python utils/print_env.py
-
-    - name: Run example tests on GPU
-      env:
-        HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
-      run: |
-        uv pip install ".[training]"
-        pytest -n 1 --max-worker-restart=0 --dist=loadfile --make-reports=examples_torch_cuda examples/
-
-    - name: Failure short reports
-      if: ${{ failure() }}
-      run: |
-        cat reports/examples_torch_cuda_stats.txt
-        cat reports/examples_torch_cuda_failures_short.txt
-
-    - name: Test suite reports artifacts
-      if: ${{ always() }}
-      uses: actions/upload-artifact@v4
-      with:
-        name: examples_test_reports
-        path: reports

.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
-      pr_number:
-        description: 'PR number 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:
-      group: aws-g4dn-2xlarge
-    container:
-      image: ${{ github.event.inputs.docker_image }}
-      options: --gpus all --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 [[ ! "$PY_TEST" =~ ^tests/(models|pipelines|lora) ]]; then
-            echo "Error: The input string must contain either 'models', 'pipelines', or 'lora' after 'tests/'."
-            exit 1
-          fi
-
-          if [[ "$PY_TEST" == *";"* ]]; then
-            echo "Error: The input string must not contain ';'."
-            exit 1
-          fi
-          echo "$PY_TEST"
-        
-        shell: bash -e {0}
-
-      - name: Checkout PR branch
-        uses: actions/checkout@v4
-        with:
-          ref: refs/pull/${{ inputs.pr_number }}/head
-
-      - name: Install pytest
-        run: |
-          uv pip install -e ".[quality]"
-          uv pip install peft
-
-      - name: Run tests
-        env:
-            PY_TEST: ${{ github.event.inputs.test }}
-        run: |
-          pytest "$PY_TEST"

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

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

.github/workflows/ssh-runner.yml

@@ -1,52 +0,0 @@
-name: SSH into GPU runners
-
-on:
-  workflow_dispatch:
-    inputs:
-      runner_type:
-        description: 'Type of runner to test (aws-g6-4xlarge-plus: a10, aws-g4dn-2xlarge: t4, aws-g6e-xlarge-plus: L40)'
-        type: choice
-        required: true
-        options:
-          - aws-g6-4xlarge-plus
-          - aws-g4dn-2xlarge
-          - aws-g6e-xlarge-plus
-      docker_image:
-        description: 'Name of the Docker image'
-        required: true
-
-env:
-  IS_GITHUB_CI: "1"
-  HF_HUB_READ_TOKEN: ${{ secrets.HF_HUB_READ_TOKEN }}
-  HF_HOME: /mnt/cache
-  DIFFUSERS_IS_CI: yes
-  OMP_NUM_THREADS: 8
-  MKL_NUM_THREADS: 8
-  RUN_SLOW: yes
-
-jobs:
-  ssh_runner:
-    name: "SSH"
-    runs-on:
-      group: "${{ github.event.inputs.runner_type }}"
-    container:
-      image: ${{ github.event.inputs.docker_image }}
-      options: --shm-size "16gb" --ipc host -v /mnt/cache/.cache/huggingface/diffusers:/mnt/cache/ --gpus all --privileged
-
-    steps:
-      - name: Checkout diffusers
-        uses: actions/checkout@v3
-        with:
-          fetch-depth: 2
-
-      - name: NVIDIA-SMI
-        run: |
-          nvidia-smi
-
-      - name: Tailscale # In order to be able to SSH when a test fails
-        uses: huggingface/tailscale-action@main
-        with:
-          authkey: ${{ secrets.TAILSCALE_SSH_AUTHKEY }}
-          slackChannel: ${{ secrets.SLACK_CIFEEDBACK_CHANNEL }}
-          slackToken: ${{ secrets.SLACK_CIFEEDBACK_BOT_TOKEN }}
-          waitForSSH: true

.github/workflows/stale.yml

@@ -8,10 +8,7 @@ jobs:
   close_stale_issues:
     name: Close Stale Issues
     if: github.repository == 'huggingface/diffusers'
-    runs-on: ubuntu-22.04
-    permissions:
-      issues: write
-      pull-requests: write
+    runs-on: ubuntu-latest
     env:
       GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
     steps:

.github/workflows/trufflehog.yml

@@ -1,18 +0,0 @@
-on:
-  push:
-
-name: Secret Leaks
-
-jobs:
-  trufflehog:
-    runs-on: ubuntu-22.04
-    steps:
-    - name: Checkout code
-      uses: actions/checkout@v4
-      with:
-        fetch-depth: 0
-    - name: Secret Scanning
-      uses: trufflesecurity/trufflehog@main
-      with:
-        extra_args: --results=verified,unknown
-

.github/workflows/typos.yml

@@ -5,7 +5,7 @@ on:
 
 jobs:
   build:
-    runs-on: ubuntu-22.04
+    runs-on: ubuntu-latest
 
     steps:
       - uses: actions/checkout@v3

.github/workflows/update_metadata.yml

@@ -1,30 +0,0 @@
-name: Update Diffusers metadata
-
-on:
-  workflow_dispatch:
-  push:
-    branches:
-      - main
-      - update_diffusers_metadata*
-
-jobs:
-  update_metadata:
-    runs-on: ubuntu-22.04
-    defaults:
-      run:
-        shell: bash -l {0}
-
-    steps:
-      - uses: actions/checkout@v3
-
-      - name: Setup environment
-        run: |
-          pip install --upgrade pip
-          pip install datasets pandas
-          pip install .[torch]
-
-      - name: Update metadata
-        env:
-          HF_TOKEN: ${{ secrets.SAYAK_HF_TOKEN }}
-        run: |
-          python utils/update_metadata.py --commit_sha ${{ github.sha }}

.gitignore

@@ -125,9 +125,6 @@ dmypy.json
 .vs
 .vscode
 
-# Cursor
-.cursor
-
 # Pycharm
 .idea
 
@@ -178,4 +175,4 @@ tags
 .ruff_cache
 
 # wandb
-wandb
+wandb

CONTRIBUTING.md

@@ -1,4 +1,4 @@
-<!--Copyright 2025 The HuggingFace Team. All rights reserved.
+<!--Copyright 2024 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at
@@ -57,13 +57,13 @@ Any question or comment related to the Diffusers library can be asked on the [di
 - ...
 
 Every question that is asked on the forum or on Discord actively encourages the community to publicly
-share knowledge and might very well help a beginner in the future who has the same question you're
+share knowledge and might very well help a beginner in the future that has the same question you're
 having. Please do pose any questions you might have.
 In the same spirit, you are of immense help to the community by answering such questions because this way you are publicly documenting knowledge for everybody to learn from.
 
 **Please** keep in mind that the more effort you put into asking or answering a question, the higher
 the quality of the publicly documented knowledge. In the same way, well-posed and well-answered questions create a high-quality knowledge database accessible to everybody, while badly posed questions or answers reduce the overall quality of the public knowledge database.
-In short, a high quality question or answer is *precise*, *concise*, *relevant*, *easy-to-understand*, *accessible*, and *well-formatted/well-posed*. For more information, please have a look through the [How to write a good issue](#how-to-write-a-good-issue) section.
+In short, a high quality question or answer is *precise*, *concise*, *relevant*, *easy-to-understand*, *accessible*, and *well-formated/well-posed*. For more information, please have a look through the [How to write a good issue](#how-to-write-a-good-issue) section.
 
 **NOTE about channels**:
 [*The forum*](https://discuss.huggingface.co/c/discussion-related-to-httpsgithubcomhuggingfacediffusers/63) is much better indexed by search engines, such as Google. Posts are ranked by popularity rather than chronologically. Hence, it's easier to look up questions and answers that we posted some time ago.
@@ -245,7 +245,7 @@ The official training examples are maintained by the Diffusers' core maintainers
 This is because of the same reasons put forward in [6. Contribute a community pipeline](#6-contribute-a-community-pipeline) for official pipelines vs. community pipelines: It is not feasible for the core maintainers to maintain all possible training methods for diffusion models.
 If the Diffusers core maintainers and the community consider a certain training paradigm to be too experimental or not popular enough, the corresponding training code should be put in the `research_projects` folder and maintained by the author.
 
-Both official training and research examples consist of a directory that contains one or more training scripts, a `requirements.txt` file, and a `README.md` file. In order for the user to make use of the
+Both official training and research examples consist of a directory that contains one or more training scripts, a requirements.txt file, and a README.md file. In order for the user to make use of the
 training examples, it is required to clone the repository:
 
 ```bash
@@ -255,8 +255,7 @@ git clone https://github.com/huggingface/diffusers
 as well as to install all additional dependencies required for training:
 
 ```bash
-cd diffusers
-pip install -r examples/<your-example-folder>/requirements.txt
+pip install -r /examples/<your-example-folder>/requirements.txt
 ```
 
 Therefore when adding an example, the `requirements.txt` file shall define all pip dependencies required for your training example so that once all those are installed, the user can run the example's training script. See, for example, the [DreamBooth `requirements.txt` file](https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/requirements.txt).
@@ -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

Makefile

@@ -42,7 +42,6 @@ repo-consistency:
 quality:
 	ruff check $(check_dirs) setup.py
 	ruff format --check $(check_dirs) setup.py
-	doc-builder style src/diffusers docs/source --max_len 119 --check_only
 	python utils/check_doc_toc.py
 
 # Format source code automatically and check is there are any problems left that need manual fixing
@@ -56,7 +55,6 @@ extra_style_checks:
 style:
 	ruff check $(check_dirs) setup.py --fix
 	ruff format $(check_dirs) setup.py
-	doc-builder style src/diffusers docs/source --max_len 119
 	${MAKE} autogenerate_code
 	${MAKE} extra_style_checks
 

PHILOSOPHY.md

@@ -1,4 +1,4 @@
-<!--Copyright 2025 The HuggingFace Team. All rights reserved.
+<!--Copyright 2024 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at
@@ -15,7 +15,7 @@ specific language governing permissions and limitations under the License.
 🧨 Diffusers provides **state-of-the-art** pretrained diffusion models across multiple modalities.
 Its purpose is to serve as a **modular toolbox** for both inference and training.
 
-We aim to build a library that stands the test of time and therefore take API design very seriously.
+We aim at building a library that stands the test of time and therefore take API design very seriously.
 
 In a nutshell, Diffusers is built to be a natural extension of PyTorch. Therefore, most of our design choices are based on [PyTorch's Design Principles](https://pytorch.org/docs/stable/community/design.html#pytorch-design-philosophy). Let's go over the most important ones:
 
@@ -63,14 +63,14 @@ Let's walk through more detailed design decisions for each class.
 Pipelines are designed to be easy to use (therefore do not follow [*Simple over easy*](#simple-over-easy) 100%), are not feature complete, and should loosely be seen as examples of how to use [models](#models) and [schedulers](#schedulers) for inference.
 
 The following design principles are followed:
-- Pipelines follow the single-file policy. All pipelines can be found in individual directories under src/diffusers/pipelines. One pipeline folder corresponds to one diffusion paper/project/release. Multiple pipeline files can be gathered in one pipeline folder, as it’s done for [`src/diffusers/pipelines/stable-diffusion`](https://github.com/huggingface/diffusers/tree/main/src/diffusers/pipelines/stable_diffusion). If pipelines share similar functionality, one can make use of the [# Copied from mechanism](https://github.com/huggingface/diffusers/blob/125d783076e5bd9785beb05367a2d2566843a271/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_img2img.py#L251).
+- Pipelines follow the single-file policy. All pipelines can be found in individual directories under src/diffusers/pipelines. One pipeline folder corresponds to one diffusion paper/project/release. Multiple pipeline files can be gathered in one pipeline folder, as it’s done for [`src/diffusers/pipelines/stable-diffusion`](https://github.com/huggingface/diffusers/tree/main/src/diffusers/pipelines/stable_diffusion). If pipelines share similar functionality, one can make use of the [#Copied from mechanism](https://github.com/huggingface/diffusers/blob/125d783076e5bd9785beb05367a2d2566843a271/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_img2img.py#L251).
 - Pipelines all inherit from [`DiffusionPipeline`].
-- Every pipeline consists of different model and scheduler components, that are documented in the [`model_index.json` file](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5/blob/main/model_index.json), are accessible under the same name as attributes of the pipeline and can be shared between pipelines with [`DiffusionPipeline.components`](https://huggingface.co/docs/diffusers/main/en/api/diffusion_pipeline#diffusers.DiffusionPipeline.components) function.
+- Every pipeline consists of different model and scheduler components, that are documented in the [`model_index.json` file](https://huggingface.co/runwayml/stable-diffusion-v1-5/blob/main/model_index.json), are accessible under the same name as attributes of the pipeline and can be shared between pipelines with [`DiffusionPipeline.components`](https://huggingface.co/docs/diffusers/main/en/api/diffusion_pipeline#diffusers.DiffusionPipeline.components) function.
 - Every pipeline should be loadable via the [`DiffusionPipeline.from_pretrained`](https://huggingface.co/docs/diffusers/main/en/api/diffusion_pipeline#diffusers.DiffusionPipeline.from_pretrained) function.
 - Pipelines should be used **only** for inference.
 - Pipelines should be very readable, self-explanatory, and easy to tweak.
 - Pipelines should be designed to build on top of each other and be easy to integrate into higher-level APIs.
-- Pipelines are **not** intended to be feature-complete user interfaces. For feature-complete user interfaces one should rather have a look at [InvokeAI](https://github.com/invoke-ai/InvokeAI), [Diffuzers](https://github.com/abhishekkrthakur/diffuzers), and [lama-cleaner](https://github.com/Sanster/lama-cleaner).
+- Pipelines are **not** intended to be feature-complete user interfaces. For future complete user interfaces one should rather have a look at [InvokeAI](https://github.com/invoke-ai/InvokeAI), [Diffuzers](https://github.com/abhishekkrthakur/diffuzers), and [lama-cleaner](https://github.com/Sanster/lama-cleaner).
 - Every pipeline should have one and only one way to run it via a `__call__` method. The naming of the `__call__` arguments should be shared across all pipelines.
 - Pipelines should be named after the task they are intended to solve.
 - In almost all cases, novel diffusion pipelines shall be implemented in a new pipeline folder/file.
@@ -81,7 +81,7 @@ Models are designed as configurable toolboxes that are natural extensions of [Py
 
 The following design principles are followed:
 - Models correspond to **a type of model architecture**. *E.g.* the [`UNet2DConditionModel`] class is used for all UNet variations that expect 2D image inputs and are conditioned on some context.
-- All models can be found in [`src/diffusers/models`](https://github.com/huggingface/diffusers/tree/main/src/diffusers/models) and every model architecture shall be defined in its file, e.g. [`unets/unet_2d_condition.py`](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/unets/unet_2d_condition.py), [`transformers/transformer_2d.py`](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/transformers/transformer_2d.py), etc...
+- All models can be found in [`src/diffusers/models`](https://github.com/huggingface/diffusers/tree/main/src/diffusers/models) and every model architecture shall be defined in its file, e.g. [`unet_2d_condition.py`](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/unet_2d_condition.py), [`transformer_2d.py`](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/transformer_2d.py), etc...
 - Models **do not** follow the single-file policy and should make use of smaller model building blocks, such as [`attention.py`](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention.py), [`resnet.py`](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/resnet.py), [`embeddings.py`](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/embeddings.py), etc... **Note**: This is in stark contrast to Transformers' modeling files and shows that models do not really follow the single-file policy.
 - Models intend to expose complexity, just like PyTorch's `Module` class, and give clear error messages.
 - Models all inherit from `ModelMixin` and `ConfigMixin`.
@@ -90,7 +90,7 @@ The following design principles are followed:
 - To integrate new model checkpoints whose general architecture can be classified as an architecture that already exists in Diffusers, the existing model architecture shall be adapted to make it work with the new checkpoint. One should only create a new file if the model architecture is fundamentally different.
 - Models should be designed to be easily extendable to future changes. This can be achieved by limiting public function arguments, configuration arguments, and "foreseeing" future changes, *e.g.* it is usually better to add `string` "...type" arguments that can easily be extended to new future types instead of boolean `is_..._type` arguments. Only the minimum amount of changes shall be made to existing architectures to make a new model checkpoint work.
 - The model design is a difficult trade-off between keeping code readable and concise and supporting many model checkpoints. For most parts of the modeling code, classes shall be adapted for new model checkpoints, while there are some exceptions where it is preferred to add new classes to make sure the code is kept concise and
-readable long-term, such as [UNet blocks](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/unets/unet_2d_blocks.py) and [Attention processors](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_processor.py).
+readable long-term, such as [UNet blocks](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/unet_2d_blocks.py) and [Attention processors](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_processor.py).
 
 ### Schedulers
 
@@ -100,7 +100,7 @@ The following design principles are followed:
 - All schedulers are found in [`src/diffusers/schedulers`](https://github.com/huggingface/diffusers/tree/main/src/diffusers/schedulers).
 - Schedulers are **not** allowed to import from large utils files and shall be kept very self-contained.
 - One scheduler Python file corresponds to one scheduler algorithm (as might be defined in a paper).
-- If schedulers share similar functionalities, we can make use of the `# Copied from` mechanism.
+- If schedulers share similar functionalities, we can make use of the `#Copied from` mechanism.
 - Schedulers all inherit from `SchedulerMixin` and `ConfigMixin`.
 - Schedulers can be easily swapped out with the [`ConfigMixin.from_config`](https://huggingface.co/docs/diffusers/main/en/api/configuration#diffusers.ConfigMixin.from_config) method as explained in detail [here](./docs/source/en/using-diffusers/schedulers.md).
 - Every scheduler has to have a `set_num_inference_steps`, and a `step` function. `set_num_inference_steps(...)` has to be called before every denoising process, *i.e.* before `step(...)` is called.

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).
@@ -37,7 +47,7 @@ limitations under the License.
 
 ## Installation
 
-We recommend installing 🤗 Diffusers in a virtual environment from PyPI or Conda. For more details about installing [PyTorch](https://pytorch.org/get-started/locally/), please refer to their official documentation.
+We recommend installing 🤗 Diffusers in a virtual environment from PyPI or Conda. For more details about installing [PyTorch](https://pytorch.org/get-started/locally/) and [Flax](https://flax.readthedocs.io/en/latest/#installation), please refer to their official documentation.
 
 ### PyTorch
 
@@ -53,19 +63,27 @@ With `conda` (maintained by the community):
 conda install -c conda-forge diffusers
 ```
 
+### Flax
+
+With `pip` (official package):
+
+```bash
+pip install --upgrade diffusers[flax]
+```
+
 ### Apple Silicon (M1/M2) support
 
 Please refer to the [How to use Stable Diffusion in Apple Silicon](https://huggingface.co/docs/diffusers/optimization/mps) guide.
 
 ## Quickstart
 
-Generating outputs is super easy with 🤗 Diffusers. To generate an image from text, use the `from_pretrained` method to load any pretrained diffusion model (browse the [Hub](https://huggingface.co/models?library=diffusers&sort=downloads) for 30,000+ checkpoints):
+Generating outputs is super easy with 🤗 Diffusers. To generate an image from text, use the `from_pretrained` method to load any pretrained diffusion model (browse the [Hub](https://huggingface.co/models?library=diffusers&sort=downloads) for 22000+ checkpoints):
 
 ```python
 from diffusers import DiffusionPipeline
 import torch
 
-pipeline = DiffusionPipeline.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5", torch_dtype=torch.float16)
+pipeline = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16)
 pipeline.to("cuda")
 pipeline("An image of a squirrel in Picasso style").images[0]
 ```
@@ -104,9 +122,9 @@ Check out the [Quickstart](https://huggingface.co/docs/diffusers/quicktour) to l
 | **Documentation**                                                   | **What can I learn?**                                                                                                                                                                           |
 |---------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
 | [Tutorial](https://huggingface.co/docs/diffusers/tutorials/tutorial_overview)                                                            | A basic crash course for learning how to use the library's most important features like using models and schedulers to build your own diffusion system, and training your own diffusion model.  |
-| [Loading](https://huggingface.co/docs/diffusers/using-diffusers/loading)                                                             | Guides for how to load and configure all the components (pipelines, models, and schedulers) of the library, as well as how to use different schedulers.                                         |
-| [Pipelines for inference](https://huggingface.co/docs/diffusers/using-diffusers/overview_techniques)                                             | Guides for how to use pipelines for different inference tasks, batched generation, controlling generated outputs and randomness, and how to contribute a pipeline to the library.               |
-| [Optimization](https://huggingface.co/docs/diffusers/optimization/fp16)                                                        | Guides for how to optimize your diffusion model to run faster and consume less memory.                                                                                                          |
+| [Loading](https://huggingface.co/docs/diffusers/using-diffusers/loading_overview)                                                             | Guides for how to load and configure all the components (pipelines, models, and schedulers) of the library, as well as how to use different schedulers.                                         |
+| [Pipelines for inference](https://huggingface.co/docs/diffusers/using-diffusers/pipeline_overview)                                             | Guides for how to use pipelines for different inference tasks, batched generation, controlling generated outputs and randomness, and how to contribute a pipeline to the library.               |
+| [Optimization](https://huggingface.co/docs/diffusers/optimization/opt_overview)                                                        | Guides for how to optimize your diffusion model to run faster and consume less memory.                                                                                                          |
 | [Training](https://huggingface.co/docs/diffusers/training/overview) | Guides for how to train a diffusion model for different tasks with different training techniques.                                                                                               |
 ## Contribution
 
@@ -136,7 +154,7 @@ Also, say 👋 in our public Discord channel <a href="https://discord.gg/G7tWnz9
   <tr style="border-top: 2px solid black">
     <td>Text-to-Image</td>
     <td><a href="https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion/text2img">Stable Diffusion Text-to-Image</a></td>
-      <td><a href="https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5"> stable-diffusion-v1-5/stable-diffusion-v1-5 </a></td>
+      <td><a href="https://huggingface.co/runwayml/stable-diffusion-v1-5"> runwayml/stable-diffusion-v1-5 </a></td>
   </tr>
   <tr>
     <td>Text-to-Image</td>
@@ -166,12 +184,12 @@ Also, say 👋 in our public Discord channel <a href="https://discord.gg/G7tWnz9
   <tr>
     <td>Text-guided Image-to-Image</td>
     <td><a href="https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion/img2img">Stable Diffusion Image-to-Image</a></td>
-      <td><a href="https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5"> stable-diffusion-v1-5/stable-diffusion-v1-5 </a></td>
+      <td><a href="https://huggingface.co/runwayml/stable-diffusion-v1-5"> runwayml/stable-diffusion-v1-5 </a></td>
   </tr>
   <tr style="border-top: 2px solid black">
     <td>Text-guided Image Inpainting</td>
     <td><a href="https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion/inpaint">Stable Diffusion Inpainting</a></td>
-      <td><a href="https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-inpainting"> stable-diffusion-v1-5/stable-diffusion-inpainting </a></td>
+      <td><a href="https://huggingface.co/runwayml/stable-diffusion-inpainting"> runwayml/stable-diffusion-inpainting </a></td>
   </tr>
   <tr style="border-top: 2px solid black">
     <td>Image Variation</td>
@@ -194,7 +212,6 @@ Also, say 👋 in our public Discord channel <a href="https://discord.gg/G7tWnz9
 
 - https://github.com/microsoft/TaskMatrix
 - https://github.com/invoke-ai/InvokeAI
-- https://github.com/InstantID/InstantID
 - https://github.com/apple/ml-stable-diffusion
 - https://github.com/Sanster/lama-cleaner
 - https://github.com/IDEA-Research/Grounded-Segment-Anything
@@ -202,7 +219,7 @@ Also, say 👋 in our public Discord channel <a href="https://discord.gg/G7tWnz9
 - https://github.com/deep-floyd/IF
 - https://github.com/bentoml/BentoML
 - https://github.com/bmaltais/kohya_ss
-- +14,000 other amazing GitHub repositories 💪
+- +9000 other amazing GitHub repositories 💪
 
 Thank you for using us ❤️.
 

benchmarks/README.md

@@ -1,69 +0,0 @@
-# Diffusers Benchmarks
-
-Welcome to Diffusers Benchmarks. These benchmarks are use to obtain latency and memory information of the most popular models across different scenarios such as:
-
-* Base case i.e., when using `torch.bfloat16` and `torch.nn.functional.scaled_dot_product_attention`.
-* Base + `torch.compile()`
-* NF4 quantization
-* Layerwise upcasting
-
-Instead of full diffusion pipelines, only the forward pass of the respective model classes (such as `FluxTransformer2DModel`) is tested with the real checkpoints (such as `"black-forest-labs/FLUX.1-dev"`). 
-
-The entrypoint to running all the currently available benchmarks is in `run_all.py`. However, one can run the individual benchmarks, too, e.g., `python benchmarking_flux.py`. It should produce a CSV file containing various information about the benchmarks run.
-
-The benchmarks are run on a weekly basis and the CI is defined in [benchmark.yml](../.github/workflows/benchmark.yml).
-
-## Running the benchmarks manually
-
-First set up `torch` and install `diffusers` from the root of the directory:
-
-```py
-pip install -e ".[quality,test]"
-```
-
-Then make sure the other dependencies are installed:
-
-```sh
-cd benchmarks/
-pip install -r requirements.txt
-```
-
-We need to be authenticated to access some of the checkpoints used during benchmarking:
-
-```sh
-hf auth login
-```
-
-We use an L40 GPU with 128GB RAM to run the benchmark CI. As such, the benchmarks are configured to run on NVIDIA GPUs. So, make sure you have access to a similar machine (or modify the benchmarking scripts accordingly).
-
-Then you can either launch the entire benchmarking suite by running:
-
-```sh
-python run_all.py
-```
-
-Or, you can run the individual benchmarks.
-
-## Customizing the benchmarks
-
-We define "scenarios" to cover the most common ways in which these models are used. You can
-define a new scenario, modifying an existing benchmark file:
-
-```py
-BenchmarkScenario(
-    name=f"{CKPT_ID}-bnb-8bit",
-    model_cls=FluxTransformer2DModel,
-    model_init_kwargs={
-        "pretrained_model_name_or_path": CKPT_ID,
-        "torch_dtype": torch.bfloat16,
-        "subfolder": "transformer",
-        "quantization_config": BitsAndBytesConfig(load_in_8bit=True),
-    },
-    get_model_input_dict=partial(get_input_dict, device=torch_device, dtype=torch.bfloat16),
-    model_init_fn=model_init_fn,
-)
-```
-
-You can also configure a new model-level benchmark and add it to the existing suite. To do so, just defining a valid benchmarking file like `benchmarking_flux.py` should be enough.
-
-Happy benchmarking 🧨

benchmarks/base_classes.py

@@ -0,0 +1,346 @@
+import os
+import sys
+
+import torch
+
+from diffusers import (
+    AutoPipelineForImage2Image,
+    AutoPipelineForInpainting,
+    AutoPipelineForText2Image,
+    ControlNetModel,
+    LCMScheduler,
+    StableDiffusionAdapterPipeline,
+    StableDiffusionControlNetPipeline,
+    StableDiffusionXLAdapterPipeline,
+    StableDiffusionXLControlNetPipeline,
+    T2IAdapter,
+    WuerstchenCombinedPipeline,
+)
+from diffusers.utils import load_image
+
+
+sys.path.append(".")
+
+from utils import (  # noqa: E402
+    BASE_PATH,
+    PROMPT,
+    BenchmarkInfo,
+    benchmark_fn,
+    bytes_to_giga_bytes,
+    flush,
+    generate_csv_dict,
+    write_to_csv,
+)
+
+
+RESOLUTION_MAPPING = {
+    "runwayml/stable-diffusion-v1-5": (512, 512),
+    "lllyasviel/sd-controlnet-canny": (512, 512),
+    "diffusers/controlnet-canny-sdxl-1.0": (1024, 1024),
+    "TencentARC/t2iadapter_canny_sd14v1": (512, 512),
+    "TencentARC/t2i-adapter-canny-sdxl-1.0": (1024, 1024),
+    "stabilityai/stable-diffusion-2-1": (768, 768),
+    "stabilityai/stable-diffusion-xl-base-1.0": (1024, 1024),
+    "stabilityai/stable-diffusion-xl-refiner-1.0": (1024, 1024),
+    "stabilityai/sdxl-turbo": (512, 512),
+}
+
+
+class BaseBenchmak:
+    pipeline_class = None
+
+    def __init__(self, args):
+        super().__init__()
+
+    def run_inference(self, args):
+        raise NotImplementedError
+
+    def benchmark(self, args):
+        raise NotImplementedError
+
+    def get_result_filepath(self, args):
+        pipeline_class_name = str(self.pipe.__class__.__name__)
+        name = (
+            args.ckpt.replace("/", "_")
+            + "_"
+            + pipeline_class_name
+            + f"-bs@{args.batch_size}-steps@{args.num_inference_steps}-mco@{args.model_cpu_offload}-compile@{args.run_compile}.csv"
+        )
+        filepath = os.path.join(BASE_PATH, name)
+        return filepath
+
+
+class TextToImageBenchmark(BaseBenchmak):
+    pipeline_class = AutoPipelineForText2Image
+
+    def __init__(self, args):
+        pipe = self.pipeline_class.from_pretrained(args.ckpt, torch_dtype=torch.float16)
+        pipe = pipe.to("cuda")
+
+        if args.run_compile:
+            if not isinstance(pipe, WuerstchenCombinedPipeline):
+                pipe.unet.to(memory_format=torch.channels_last)
+                print("Run torch compile")
+                pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
+
+                if hasattr(pipe, "movq") and getattr(pipe, "movq", None) is not None:
+                    pipe.movq.to(memory_format=torch.channels_last)
+                    pipe.movq = torch.compile(pipe.movq, mode="reduce-overhead", fullgraph=True)
+            else:
+                print("Run torch compile")
+                pipe.decoder = torch.compile(pipe.decoder, mode="reduce-overhead", fullgraph=True)
+                pipe.vqgan = torch.compile(pipe.vqgan, mode="reduce-overhead", fullgraph=True)
+
+        pipe.set_progress_bar_config(disable=True)
+        self.pipe = pipe
+
+    def run_inference(self, pipe, args):
+        _ = pipe(
+            prompt=PROMPT,
+            num_inference_steps=args.num_inference_steps,
+            num_images_per_prompt=args.batch_size,
+        )
+
+    def benchmark(self, args):
+        flush()
+
+        print(f"[INFO] {self.pipe.__class__.__name__}: Running benchmark with: {vars(args)}\n")
+
+        time = benchmark_fn(self.run_inference, self.pipe, args)  # in seconds.
+        memory = bytes_to_giga_bytes(torch.cuda.max_memory_allocated())  # in GBs.
+        benchmark_info = BenchmarkInfo(time=time, memory=memory)
+
+        pipeline_class_name = str(self.pipe.__class__.__name__)
+        flush()
+        csv_dict = generate_csv_dict(
+            pipeline_cls=pipeline_class_name, ckpt=args.ckpt, args=args, benchmark_info=benchmark_info
+        )
+        filepath = self.get_result_filepath(args)
+        write_to_csv(filepath, csv_dict)
+        print(f"Logs written to: {filepath}")
+        flush()
+
+
+class TurboTextToImageBenchmark(TextToImageBenchmark):
+    def __init__(self, args):
+        super().__init__(args)
+
+    def run_inference(self, pipe, args):
+        _ = pipe(
+            prompt=PROMPT,
+            num_inference_steps=args.num_inference_steps,
+            num_images_per_prompt=args.batch_size,
+            guidance_scale=0.0,
+        )
+
+
+class LCMLoRATextToImageBenchmark(TextToImageBenchmark):
+    lora_id = "latent-consistency/lcm-lora-sdxl"
+
+    def __init__(self, args):
+        super().__init__(args)
+        self.pipe.load_lora_weights(self.lora_id)
+        self.pipe.fuse_lora()
+        self.pipe.unload_lora_weights()
+        self.pipe.scheduler = LCMScheduler.from_config(self.pipe.scheduler.config)
+
+    def get_result_filepath(self, args):
+        pipeline_class_name = str(self.pipe.__class__.__name__)
+        name = (
+            self.lora_id.replace("/", "_")
+            + "_"
+            + pipeline_class_name
+            + f"-bs@{args.batch_size}-steps@{args.num_inference_steps}-mco@{args.model_cpu_offload}-compile@{args.run_compile}.csv"
+        )
+        filepath = os.path.join(BASE_PATH, name)
+        return filepath
+
+    def run_inference(self, pipe, args):
+        _ = pipe(
+            prompt=PROMPT,
+            num_inference_steps=args.num_inference_steps,
+            num_images_per_prompt=args.batch_size,
+            guidance_scale=1.0,
+        )
+
+    def benchmark(self, args):
+        flush()
+
+        print(f"[INFO] {self.pipe.__class__.__name__}: Running benchmark with: {vars(args)}\n")
+
+        time = benchmark_fn(self.run_inference, self.pipe, args)  # in seconds.
+        memory = bytes_to_giga_bytes(torch.cuda.max_memory_allocated())  # in GBs.
+        benchmark_info = BenchmarkInfo(time=time, memory=memory)
+
+        pipeline_class_name = str(self.pipe.__class__.__name__)
+        flush()
+        csv_dict = generate_csv_dict(
+            pipeline_cls=pipeline_class_name, ckpt=self.lora_id, args=args, benchmark_info=benchmark_info
+        )
+        filepath = self.get_result_filepath(args)
+        write_to_csv(filepath, csv_dict)
+        print(f"Logs written to: {filepath}")
+        flush()
+
+
+class ImageToImageBenchmark(TextToImageBenchmark):
+    pipeline_class = AutoPipelineForImage2Image
+    url = "https://huggingface.co/datasets/diffusers/docs-images/resolve/main/benchmarking/1665_Girl_with_a_Pearl_Earring.jpg"
+    image = load_image(url).convert("RGB")
+
+    def __init__(self, args):
+        super().__init__(args)
+        self.image = self.image.resize(RESOLUTION_MAPPING[args.ckpt])
+
+    def run_inference(self, pipe, args):
+        _ = pipe(
+            prompt=PROMPT,
+            image=self.image,
+            num_inference_steps=args.num_inference_steps,
+            num_images_per_prompt=args.batch_size,
+        )
+
+
+class TurboImageToImageBenchmark(ImageToImageBenchmark):
+    def __init__(self, args):
+        super().__init__(args)
+
+    def run_inference(self, pipe, args):
+        _ = pipe(
+            prompt=PROMPT,
+            image=self.image,
+            num_inference_steps=args.num_inference_steps,
+            num_images_per_prompt=args.batch_size,
+            guidance_scale=0.0,
+            strength=0.5,
+        )
+
+
+class InpaintingBenchmark(ImageToImageBenchmark):
+    pipeline_class = AutoPipelineForInpainting
+    mask_url = "https://huggingface.co/datasets/diffusers/docs-images/resolve/main/benchmarking/overture-creations-5sI6fQgYIuo_mask.png"
+    mask = load_image(mask_url).convert("RGB")
+
+    def __init__(self, args):
+        super().__init__(args)
+        self.image = self.image.resize(RESOLUTION_MAPPING[args.ckpt])
+        self.mask = self.mask.resize(RESOLUTION_MAPPING[args.ckpt])
+
+    def run_inference(self, pipe, args):
+        _ = pipe(
+            prompt=PROMPT,
+            image=self.image,
+            mask_image=self.mask,
+            num_inference_steps=args.num_inference_steps,
+            num_images_per_prompt=args.batch_size,
+        )
+
+
+class IPAdapterTextToImageBenchmark(TextToImageBenchmark):
+    url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/load_neg_embed.png"
+    image = load_image(url)
+
+    def __init__(self, args):
+        pipe = self.pipeline_class.from_pretrained(args.ckpt, torch_dtype=torch.float16).to("cuda")
+        pipe.load_ip_adapter(
+            args.ip_adapter_id[0],
+            subfolder="models" if "sdxl" not in args.ip_adapter_id[1] else "sdxl_models",
+            weight_name=args.ip_adapter_id[1],
+        )
+
+        if args.run_compile:
+            pipe.unet.to(memory_format=torch.channels_last)
+            print("Run torch compile")
+            pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
+
+        pipe.set_progress_bar_config(disable=True)
+        self.pipe = pipe
+
+    def run_inference(self, pipe, args):
+        _ = pipe(
+            prompt=PROMPT,
+            ip_adapter_image=self.image,
+            num_inference_steps=args.num_inference_steps,
+            num_images_per_prompt=args.batch_size,
+        )
+
+
+class ControlNetBenchmark(TextToImageBenchmark):
+    pipeline_class = StableDiffusionControlNetPipeline
+    aux_network_class = ControlNetModel
+    root_ckpt = "runwayml/stable-diffusion-v1-5"
+
+    url = "https://huggingface.co/datasets/diffusers/docs-images/resolve/main/benchmarking/canny_image_condition.png"
+    image = load_image(url).convert("RGB")
+
+    def __init__(self, args):
+        aux_network = self.aux_network_class.from_pretrained(args.ckpt, torch_dtype=torch.float16)
+        pipe = self.pipeline_class.from_pretrained(self.root_ckpt, controlnet=aux_network, torch_dtype=torch.float16)
+        pipe = pipe.to("cuda")
+
+        pipe.set_progress_bar_config(disable=True)
+        self.pipe = pipe
+
+        if args.run_compile:
+            pipe.unet.to(memory_format=torch.channels_last)
+            pipe.controlnet.to(memory_format=torch.channels_last)
+
+            print("Run torch compile")
+            pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
+            pipe.controlnet = torch.compile(pipe.controlnet, mode="reduce-overhead", fullgraph=True)
+
+        self.image = self.image.resize(RESOLUTION_MAPPING[args.ckpt])
+
+    def run_inference(self, pipe, args):
+        _ = pipe(
+            prompt=PROMPT,
+            image=self.image,
+            num_inference_steps=args.num_inference_steps,
+            num_images_per_prompt=args.batch_size,
+        )
+
+
+class ControlNetSDXLBenchmark(ControlNetBenchmark):
+    pipeline_class = StableDiffusionXLControlNetPipeline
+    root_ckpt = "stabilityai/stable-diffusion-xl-base-1.0"
+
+    def __init__(self, args):
+        super().__init__(args)
+
+
+class T2IAdapterBenchmark(ControlNetBenchmark):
+    pipeline_class = StableDiffusionAdapterPipeline
+    aux_network_class = T2IAdapter
+    root_ckpt = "CompVis/stable-diffusion-v1-4"
+
+    url = "https://huggingface.co/datasets/diffusers/docs-images/resolve/main/benchmarking/canny_for_adapter.png"
+    image = load_image(url).convert("L")
+
+    def __init__(self, args):
+        aux_network = self.aux_network_class.from_pretrained(args.ckpt, torch_dtype=torch.float16)
+        pipe = self.pipeline_class.from_pretrained(self.root_ckpt, adapter=aux_network, torch_dtype=torch.float16)
+        pipe = pipe.to("cuda")
+
+        pipe.set_progress_bar_config(disable=True)
+        self.pipe = pipe
+
+        if args.run_compile:
+            pipe.unet.to(memory_format=torch.channels_last)
+            pipe.adapter.to(memory_format=torch.channels_last)
+
+            print("Run torch compile")
+            pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
+            pipe.adapter = torch.compile(pipe.adapter, mode="reduce-overhead", fullgraph=True)
+
+        self.image = self.image.resize(RESOLUTION_MAPPING[args.ckpt])
+
+
+class T2IAdapterSDXLBenchmark(T2IAdapterBenchmark):
+    pipeline_class = StableDiffusionXLAdapterPipeline
+    root_ckpt = "stabilityai/stable-diffusion-xl-base-1.0"
+
+    url = "https://huggingface.co/datasets/diffusers/docs-images/resolve/main/benchmarking/canny_for_adapter_sdxl.png"
+    image = load_image(url)
+
+    def __init__(self, args):
+        super().__init__(args)

benchmarks/benchmark_controlnet.py

@@ -0,0 +1,26 @@
+import argparse
+import sys
+
+
+sys.path.append(".")
+from base_classes import ControlNetBenchmark, ControlNetSDXLBenchmark  # noqa: E402
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        "--ckpt",
+        type=str,
+        default="lllyasviel/sd-controlnet-canny",
+        choices=["lllyasviel/sd-controlnet-canny", "diffusers/controlnet-canny-sdxl-1.0"],
+    )
+    parser.add_argument("--batch_size", type=int, default=1)
+    parser.add_argument("--num_inference_steps", type=int, default=50)
+    parser.add_argument("--model_cpu_offload", action="store_true")
+    parser.add_argument("--run_compile", action="store_true")
+    args = parser.parse_args()
+
+    benchmark_pipe = (
+        ControlNetBenchmark(args) if args.ckpt == "lllyasviel/sd-controlnet-canny" else ControlNetSDXLBenchmark(args)
+    )
+    benchmark_pipe.benchmark(args)

benchmarks/benchmark_ip_adapters.py

@@ -0,0 +1,32 @@
+import argparse
+import sys
+
+
+sys.path.append(".")
+from base_classes import IPAdapterTextToImageBenchmark  # noqa: E402
+
+
+IP_ADAPTER_CKPTS = {
+    "runwayml/stable-diffusion-v1-5": ("h94/IP-Adapter", "ip-adapter_sd15.bin"),
+    "stabilityai/stable-diffusion-xl-base-1.0": ("h94/IP-Adapter", "ip-adapter_sdxl.bin"),
+}
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        "--ckpt",
+        type=str,
+        default="runwayml/stable-diffusion-v1-5",
+        choices=list(IP_ADAPTER_CKPTS.keys()),
+    )
+    parser.add_argument("--batch_size", type=int, default=1)
+    parser.add_argument("--num_inference_steps", type=int, default=50)
+    parser.add_argument("--model_cpu_offload", action="store_true")
+    parser.add_argument("--run_compile", action="store_true")
+    args = parser.parse_args()
+
+    args.ip_adapter_id = IP_ADAPTER_CKPTS[args.ckpt]
+    benchmark_pipe = IPAdapterTextToImageBenchmark(args)
+    args.ckpt = f"{args.ckpt} (IP-Adapter)"
+    benchmark_pipe.benchmark(args)

benchmarks/benchmark_sd_img.py

@@ -0,0 +1,29 @@
+import argparse
+import sys
+
+
+sys.path.append(".")
+from base_classes import ImageToImageBenchmark, TurboImageToImageBenchmark  # noqa: E402
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        "--ckpt",
+        type=str,
+        default="runwayml/stable-diffusion-v1-5",
+        choices=[
+            "runwayml/stable-diffusion-v1-5",
+            "stabilityai/stable-diffusion-2-1",
+            "stabilityai/stable-diffusion-xl-refiner-1.0",
+            "stabilityai/sdxl-turbo",
+        ],
+    )
+    parser.add_argument("--batch_size", type=int, default=1)
+    parser.add_argument("--num_inference_steps", type=int, default=50)
+    parser.add_argument("--model_cpu_offload", action="store_true")
+    parser.add_argument("--run_compile", action="store_true")
+    args = parser.parse_args()
+
+    benchmark_pipe = ImageToImageBenchmark(args) if "turbo" not in args.ckpt else TurboImageToImageBenchmark(args)
+    benchmark_pipe.benchmark(args)

benchmarks/benchmark_sd_inpainting.py

@@ -0,0 +1,28 @@
+import argparse
+import sys
+
+
+sys.path.append(".")
+from base_classes import InpaintingBenchmark  # noqa: E402
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        "--ckpt",
+        type=str,
+        default="runwayml/stable-diffusion-v1-5",
+        choices=[
+            "runwayml/stable-diffusion-v1-5",
+            "stabilityai/stable-diffusion-2-1",
+            "stabilityai/stable-diffusion-xl-base-1.0",
+        ],
+    )
+    parser.add_argument("--batch_size", type=int, default=1)
+    parser.add_argument("--num_inference_steps", type=int, default=50)
+    parser.add_argument("--model_cpu_offload", action="store_true")
+    parser.add_argument("--run_compile", action="store_true")
+    args = parser.parse_args()
+
+    benchmark_pipe = InpaintingBenchmark(args)
+    benchmark_pipe.benchmark(args)

benchmarks/benchmark_t2i_adapter.py

@@ -0,0 +1,28 @@
+import argparse
+import sys
+
+
+sys.path.append(".")
+from base_classes import T2IAdapterBenchmark, T2IAdapterSDXLBenchmark  # noqa: E402
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        "--ckpt",
+        type=str,
+        default="TencentARC/t2iadapter_canny_sd14v1",
+        choices=["TencentARC/t2iadapter_canny_sd14v1", "TencentARC/t2i-adapter-canny-sdxl-1.0"],
+    )
+    parser.add_argument("--batch_size", type=int, default=1)
+    parser.add_argument("--num_inference_steps", type=int, default=50)
+    parser.add_argument("--model_cpu_offload", action="store_true")
+    parser.add_argument("--run_compile", action="store_true")
+    args = parser.parse_args()
+
+    benchmark_pipe = (
+        T2IAdapterBenchmark(args)
+        if args.ckpt == "TencentARC/t2iadapter_canny_sd14v1"
+        else T2IAdapterSDXLBenchmark(args)
+    )
+    benchmark_pipe.benchmark(args)

benchmarks/benchmark_t2i_lcm_lora.py

@@ -0,0 +1,23 @@
+import argparse
+import sys
+
+
+sys.path.append(".")
+from base_classes import LCMLoRATextToImageBenchmark  # noqa: E402
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        "--ckpt",
+        type=str,
+        default="stabilityai/stable-diffusion-xl-base-1.0",
+    )
+    parser.add_argument("--batch_size", type=int, default=1)
+    parser.add_argument("--num_inference_steps", type=int, default=4)
+    parser.add_argument("--model_cpu_offload", action="store_true")
+    parser.add_argument("--run_compile", action="store_true")
+    args = parser.parse_args()
+
+    benchmark_pipe = LCMLoRATextToImageBenchmark(args)
+    benchmark_pipe.benchmark(args)

benchmarks/benchmark_text_to_image.py

@@ -0,0 +1,40 @@
+import argparse
+import sys
+
+
+sys.path.append(".")
+from base_classes import TextToImageBenchmark, TurboTextToImageBenchmark  # noqa: E402
+
+
+ALL_T2I_CKPTS = [
+    "runwayml/stable-diffusion-v1-5",
+    "segmind/SSD-1B",
+    "stabilityai/stable-diffusion-xl-base-1.0",
+    "kandinsky-community/kandinsky-2-2-decoder",
+    "warp-ai/wuerstchen",
+    "stabilityai/sdxl-turbo",
+]
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        "--ckpt",
+        type=str,
+        default="runwayml/stable-diffusion-v1-5",
+        choices=ALL_T2I_CKPTS,
+    )
+    parser.add_argument("--batch_size", type=int, default=1)
+    parser.add_argument("--num_inference_steps", type=int, default=50)
+    parser.add_argument("--model_cpu_offload", action="store_true")
+    parser.add_argument("--run_compile", action="store_true")
+    args = parser.parse_args()
+
+    benchmark_cls = None
+    if "turbo" in args.ckpt:
+        benchmark_cls = TurboTextToImageBenchmark
+    else:
+        benchmark_cls = TextToImageBenchmark
+
+    benchmark_pipe = benchmark_cls(args)
+    benchmark_pipe.benchmark(args)

benchmarks/benchmarking_flux.py

@@ -1,98 +0,0 @@
-from functools import partial
-
-import torch
-from benchmarking_utils import BenchmarkMixin, BenchmarkScenario, model_init_fn
-
-from diffusers import BitsAndBytesConfig, FluxTransformer2DModel
-from diffusers.utils.testing_utils import torch_device
-
-
-CKPT_ID = "black-forest-labs/FLUX.1-dev"
-RESULT_FILENAME = "flux.csv"
-
-
-def get_input_dict(**device_dtype_kwargs):
-    # resolution: 1024x1024
-    # maximum sequence length 512
-    hidden_states = torch.randn(1, 4096, 64, **device_dtype_kwargs)
-    encoder_hidden_states = torch.randn(1, 512, 4096, **device_dtype_kwargs)
-    pooled_prompt_embeds = torch.randn(1, 768, **device_dtype_kwargs)
-    image_ids = torch.ones(512, 3, **device_dtype_kwargs)
-    text_ids = torch.ones(4096, 3, **device_dtype_kwargs)
-    timestep = torch.tensor([1.0], **device_dtype_kwargs)
-    guidance = torch.tensor([1.0], **device_dtype_kwargs)
-
-    return {
-        "hidden_states": hidden_states,
-        "encoder_hidden_states": encoder_hidden_states,
-        "img_ids": image_ids,
-        "txt_ids": text_ids,
-        "pooled_projections": pooled_prompt_embeds,
-        "timestep": timestep,
-        "guidance": guidance,
-    }
-
-
-if __name__ == "__main__":
-    scenarios = [
-        BenchmarkScenario(
-            name=f"{CKPT_ID}-bf16",
-            model_cls=FluxTransformer2DModel,
-            model_init_kwargs={
-                "pretrained_model_name_or_path": CKPT_ID,
-                "torch_dtype": torch.bfloat16,
-                "subfolder": "transformer",
-            },
-            get_model_input_dict=partial(get_input_dict, device=torch_device, dtype=torch.bfloat16),
-            model_init_fn=model_init_fn,
-            compile_kwargs={"fullgraph": True},
-        ),
-        BenchmarkScenario(
-            name=f"{CKPT_ID}-bnb-nf4",
-            model_cls=FluxTransformer2DModel,
-            model_init_kwargs={
-                "pretrained_model_name_or_path": CKPT_ID,
-                "torch_dtype": torch.bfloat16,
-                "subfolder": "transformer",
-                "quantization_config": BitsAndBytesConfig(
-                    load_in_4bit=True, bnb_4bit_compute_dtype=torch.bfloat16, bnb_4bit_quant_type="nf4"
-                ),
-            },
-            get_model_input_dict=partial(get_input_dict, device=torch_device, dtype=torch.bfloat16),
-            model_init_fn=model_init_fn,
-        ),
-        BenchmarkScenario(
-            name=f"{CKPT_ID}-layerwise-upcasting",
-            model_cls=FluxTransformer2DModel,
-            model_init_kwargs={
-                "pretrained_model_name_or_path": CKPT_ID,
-                "torch_dtype": torch.bfloat16,
-                "subfolder": "transformer",
-            },
-            get_model_input_dict=partial(get_input_dict, device=torch_device, dtype=torch.bfloat16),
-            model_init_fn=partial(model_init_fn, layerwise_upcasting=True),
-        ),
-        BenchmarkScenario(
-            name=f"{CKPT_ID}-group-offload-leaf",
-            model_cls=FluxTransformer2DModel,
-            model_init_kwargs={
-                "pretrained_model_name_or_path": CKPT_ID,
-                "torch_dtype": torch.bfloat16,
-                "subfolder": "transformer",
-            },
-            get_model_input_dict=partial(get_input_dict, device=torch_device, dtype=torch.bfloat16),
-            model_init_fn=partial(
-                model_init_fn,
-                group_offload_kwargs={
-                    "onload_device": torch_device,
-                    "offload_device": torch.device("cpu"),
-                    "offload_type": "leaf_level",
-                    "use_stream": True,
-                    "non_blocking": True,
-                },
-            ),
-        ),
-    ]
-
-    runner = BenchmarkMixin()
-    runner.run_bencmarks_and_collate(scenarios, filename=RESULT_FILENAME)

benchmarks/benchmarking_ltx.py

@@ -1,80 +0,0 @@
-from functools import partial
-
-import torch
-from benchmarking_utils import BenchmarkMixin, BenchmarkScenario, model_init_fn
-
-from diffusers import LTXVideoTransformer3DModel
-from diffusers.utils.testing_utils import torch_device
-
-
-CKPT_ID = "Lightricks/LTX-Video-0.9.7-dev"
-RESULT_FILENAME = "ltx.csv"
-
-
-def get_input_dict(**device_dtype_kwargs):
-    # 512x704 (161 frames)
-    # `max_sequence_length`: 256
-    hidden_states = torch.randn(1, 7392, 128, **device_dtype_kwargs)
-    encoder_hidden_states = torch.randn(1, 256, 4096, **device_dtype_kwargs)
-    encoder_attention_mask = torch.ones(1, 256, **device_dtype_kwargs)
-    timestep = torch.tensor([1.0], **device_dtype_kwargs)
-    video_coords = torch.randn(1, 3, 7392, **device_dtype_kwargs)
-
-    return {
-        "hidden_states": hidden_states,
-        "encoder_hidden_states": encoder_hidden_states,
-        "encoder_attention_mask": encoder_attention_mask,
-        "timestep": timestep,
-        "video_coords": video_coords,
-    }
-
-
-if __name__ == "__main__":
-    scenarios = [
-        BenchmarkScenario(
-            name=f"{CKPT_ID}-bf16",
-            model_cls=LTXVideoTransformer3DModel,
-            model_init_kwargs={
-                "pretrained_model_name_or_path": CKPT_ID,
-                "torch_dtype": torch.bfloat16,
-                "subfolder": "transformer",
-            },
-            get_model_input_dict=partial(get_input_dict, device=torch_device, dtype=torch.bfloat16),
-            model_init_fn=model_init_fn,
-            compile_kwargs={"fullgraph": True},
-        ),
-        BenchmarkScenario(
-            name=f"{CKPT_ID}-layerwise-upcasting",
-            model_cls=LTXVideoTransformer3DModel,
-            model_init_kwargs={
-                "pretrained_model_name_or_path": CKPT_ID,
-                "torch_dtype": torch.bfloat16,
-                "subfolder": "transformer",
-            },
-            get_model_input_dict=partial(get_input_dict, device=torch_device, dtype=torch.bfloat16),
-            model_init_fn=partial(model_init_fn, layerwise_upcasting=True),
-        ),
-        BenchmarkScenario(
-            name=f"{CKPT_ID}-group-offload-leaf",
-            model_cls=LTXVideoTransformer3DModel,
-            model_init_kwargs={
-                "pretrained_model_name_or_path": CKPT_ID,
-                "torch_dtype": torch.bfloat16,
-                "subfolder": "transformer",
-            },
-            get_model_input_dict=partial(get_input_dict, device=torch_device, dtype=torch.bfloat16),
-            model_init_fn=partial(
-                model_init_fn,
-                group_offload_kwargs={
-                    "onload_device": torch_device,
-                    "offload_device": torch.device("cpu"),
-                    "offload_type": "leaf_level",
-                    "use_stream": True,
-                    "non_blocking": True,
-                },
-            ),
-        ),
-    ]
-
-    runner = BenchmarkMixin()
-    runner.run_bencmarks_and_collate(scenarios, filename=RESULT_FILENAME)

benchmarks/benchmarking_sdxl.py

@@ -1,82 +0,0 @@
-from functools import partial
-
-import torch
-from benchmarking_utils import BenchmarkMixin, BenchmarkScenario, model_init_fn
-
-from diffusers import UNet2DConditionModel
-from diffusers.utils.testing_utils import torch_device
-
-
-CKPT_ID = "stabilityai/stable-diffusion-xl-base-1.0"
-RESULT_FILENAME = "sdxl.csv"
-
-
-def get_input_dict(**device_dtype_kwargs):
-    # height: 1024
-    # width: 1024
-    # max_sequence_length: 77
-    hidden_states = torch.randn(1, 4, 128, 128, **device_dtype_kwargs)
-    encoder_hidden_states = torch.randn(1, 77, 2048, **device_dtype_kwargs)
-    timestep = torch.tensor([1.0], **device_dtype_kwargs)
-    added_cond_kwargs = {
-        "text_embeds": torch.randn(1, 1280, **device_dtype_kwargs),
-        "time_ids": torch.ones(1, 6, **device_dtype_kwargs),
-    }
-
-    return {
-        "sample": hidden_states,
-        "encoder_hidden_states": encoder_hidden_states,
-        "timestep": timestep,
-        "added_cond_kwargs": added_cond_kwargs,
-    }
-
-
-if __name__ == "__main__":
-    scenarios = [
-        BenchmarkScenario(
-            name=f"{CKPT_ID}-bf16",
-            model_cls=UNet2DConditionModel,
-            model_init_kwargs={
-                "pretrained_model_name_or_path": CKPT_ID,
-                "torch_dtype": torch.bfloat16,
-                "subfolder": "unet",
-            },
-            get_model_input_dict=partial(get_input_dict, device=torch_device, dtype=torch.bfloat16),
-            model_init_fn=model_init_fn,
-            compile_kwargs={"fullgraph": True},
-        ),
-        BenchmarkScenario(
-            name=f"{CKPT_ID}-layerwise-upcasting",
-            model_cls=UNet2DConditionModel,
-            model_init_kwargs={
-                "pretrained_model_name_or_path": CKPT_ID,
-                "torch_dtype": torch.bfloat16,
-                "subfolder": "unet",
-            },
-            get_model_input_dict=partial(get_input_dict, device=torch_device, dtype=torch.bfloat16),
-            model_init_fn=partial(model_init_fn, layerwise_upcasting=True),
-        ),
-        BenchmarkScenario(
-            name=f"{CKPT_ID}-group-offload-leaf",
-            model_cls=UNet2DConditionModel,
-            model_init_kwargs={
-                "pretrained_model_name_or_path": CKPT_ID,
-                "torch_dtype": torch.bfloat16,
-                "subfolder": "unet",
-            },
-            get_model_input_dict=partial(get_input_dict, device=torch_device, dtype=torch.bfloat16),
-            model_init_fn=partial(
-                model_init_fn,
-                group_offload_kwargs={
-                    "onload_device": torch_device,
-                    "offload_device": torch.device("cpu"),
-                    "offload_type": "leaf_level",
-                    "use_stream": True,
-                    "non_blocking": True,
-                },
-            ),
-        ),
-    ]
-
-    runner = BenchmarkMixin()
-    runner.run_bencmarks_and_collate(scenarios, filename=RESULT_FILENAME)

benchmarks/benchmarking_utils.py

@@ -1,244 +0,0 @@
-import gc
-import inspect
-import logging
-import os
-import queue
-import threading
-from contextlib import nullcontext
-from dataclasses import dataclass
-from typing import Any, Callable, Dict, Optional, Union
-
-import pandas as pd
-import torch
-import torch.utils.benchmark as benchmark
-
-from diffusers.models.modeling_utils import ModelMixin
-from diffusers.utils.testing_utils import require_torch_gpu, torch_device
-
-
-logging.basicConfig(level=logging.INFO, format="%(asctime)s %(levelname)s %(name)s: %(message)s")
-logger = logging.getLogger(__name__)
-
-NUM_WARMUP_ROUNDS = 5
-
-
-def benchmark_fn(f, *args, **kwargs):
-    t0 = benchmark.Timer(
-        stmt="f(*args, **kwargs)",
-        globals={"args": args, "kwargs": kwargs, "f": f},
-        num_threads=1,
-    )
-    return float(f"{(t0.blocked_autorange().mean):.3f}")
-
-
-def flush():
-    gc.collect()
-    torch.cuda.empty_cache()
-    torch.cuda.reset_max_memory_allocated()
-    torch.cuda.reset_peak_memory_stats()
-
-
-# Adapted from https://github.com/lucasb-eyer/cnn_vit_benchmarks/blob/15b665ff758e8062131353076153905cae00a71f/main.py
-def calculate_flops(model, input_dict):
-    try:
-        from torchprofile import profile_macs
-    except ModuleNotFoundError:
-        raise
-
-    # This is a hacky way to convert the kwargs to args as `profile_macs` cries about kwargs.
-    sig = inspect.signature(model.forward)
-    param_names = [
-        p.name
-        for p in sig.parameters.values()
-        if p.kind
-        in (
-            inspect.Parameter.POSITIONAL_ONLY,
-            inspect.Parameter.POSITIONAL_OR_KEYWORD,
-        )
-        and p.name != "self"
-    ]
-    bound = sig.bind_partial(**input_dict)
-    bound.apply_defaults()
-    args = tuple(bound.arguments[name] for name in param_names)
-
-    model.eval()
-    with torch.no_grad():
-        macs = profile_macs(model, args)
-    flops = 2 * macs  # 1 MAC operation = 2 FLOPs (1 multiplication + 1 addition)
-    return flops
-
-
-def calculate_params(model):
-    return sum(p.numel() for p in model.parameters())
-
-
-# Users can define their own in case this doesn't suffice. For most cases,
-# it should be sufficient.
-def model_init_fn(model_cls, group_offload_kwargs=None, layerwise_upcasting=False, **init_kwargs):
-    model = model_cls.from_pretrained(**init_kwargs).eval()
-    if group_offload_kwargs and isinstance(group_offload_kwargs, dict):
-        model.enable_group_offload(**group_offload_kwargs)
-    else:
-        model.to(torch_device)
-    if layerwise_upcasting:
-        model.enable_layerwise_casting(
-            storage_dtype=torch.float8_e4m3fn, compute_dtype=init_kwargs.get("torch_dtype", torch.bfloat16)
-        )
-    return model
-
-
-@dataclass
-class BenchmarkScenario:
-    name: str
-    model_cls: ModelMixin
-    model_init_kwargs: Dict[str, Any]
-    model_init_fn: Callable
-    get_model_input_dict: Callable
-    compile_kwargs: Optional[Dict[str, Any]] = None
-
-
-@require_torch_gpu
-class BenchmarkMixin:
-    def pre_benchmark(self):
-        flush()
-        torch.compiler.reset()
-
-    def post_benchmark(self, model):
-        model.cpu()
-        flush()
-        torch.compiler.reset()
-
-    @torch.no_grad()
-    def run_benchmark(self, scenario: BenchmarkScenario):
-        # 0) Basic stats
-        logger.info(f"Running scenario: {scenario.name}.")
-        try:
-            model = model_init_fn(scenario.model_cls, **scenario.model_init_kwargs)
-            num_params = round(calculate_params(model) / 1e9, 2)
-            try:
-                flops = round(calculate_flops(model, input_dict=scenario.get_model_input_dict()) / 1e9, 2)
-            except Exception as e:
-                logger.info(f"Problem in calculating FLOPs:\n{e}")
-                flops = None
-            model.cpu()
-            del model
-        except Exception as e:
-            logger.info(f"Error while initializing the model and calculating FLOPs:\n{e}")
-            return {}
-        self.pre_benchmark()
-
-        # 1) plain stats
-        results = {}
-        plain = None
-        try:
-            plain = self._run_phase(
-                model_cls=scenario.model_cls,
-                init_fn=scenario.model_init_fn,
-                init_kwargs=scenario.model_init_kwargs,
-                get_input_fn=scenario.get_model_input_dict,
-                compile_kwargs=None,
-            )
-        except Exception as e:
-            logger.info(f"Benchmark could not be run with the following error:\n{e}")
-            return results
-
-        # 2) compiled stats (if any)
-        compiled = {"time": None, "memory": None}
-        if scenario.compile_kwargs:
-            try:
-                compiled = self._run_phase(
-                    model_cls=scenario.model_cls,
-                    init_fn=scenario.model_init_fn,
-                    init_kwargs=scenario.model_init_kwargs,
-                    get_input_fn=scenario.get_model_input_dict,
-                    compile_kwargs=scenario.compile_kwargs,
-                )
-            except Exception as e:
-                logger.info(f"Compilation benchmark could not be run with the following error\n: {e}")
-                if plain is None:
-                    return results
-
-        # 3) merge
-        result = {
-            "scenario": scenario.name,
-            "model_cls": scenario.model_cls.__name__,
-            "num_params_B": num_params,
-            "flops_G": flops,
-            "time_plain_s": plain["time"],
-            "mem_plain_GB": plain["memory"],
-            "time_compile_s": compiled["time"],
-            "mem_compile_GB": compiled["memory"],
-        }
-        if scenario.compile_kwargs:
-            result["fullgraph"] = scenario.compile_kwargs.get("fullgraph", False)
-            result["mode"] = scenario.compile_kwargs.get("mode", "default")
-        else:
-            result["fullgraph"], result["mode"] = None, None
-        return result
-
-    def run_bencmarks_and_collate(self, scenarios: Union[BenchmarkScenario, list[BenchmarkScenario]], filename: str):
-        if not isinstance(scenarios, list):
-            scenarios = [scenarios]
-        record_queue = queue.Queue()
-        stop_signal = object()
-
-        def _writer_thread():
-            while True:
-                item = record_queue.get()
-                if item is stop_signal:
-                    break
-                df_row = pd.DataFrame([item])
-                write_header = not os.path.exists(filename)
-                df_row.to_csv(filename, mode="a", header=write_header, index=False)
-                record_queue.task_done()
-
-            record_queue.task_done()
-
-        writer = threading.Thread(target=_writer_thread, daemon=True)
-        writer.start()
-
-        for s in scenarios:
-            try:
-                record = self.run_benchmark(s)
-                if record:
-                    record_queue.put(record)
-                else:
-                    logger.info(f"Record empty from scenario: {s.name}.")
-            except Exception as e:
-                logger.info(f"Running scenario ({s.name}) led to error:\n{e}")
-        record_queue.put(stop_signal)
-        logger.info(f"Results serialized to {filename=}.")
-
-    def _run_phase(
-        self,
-        *,
-        model_cls: ModelMixin,
-        init_fn: Callable,
-        init_kwargs: Dict[str, Any],
-        get_input_fn: Callable,
-        compile_kwargs: Optional[Dict[str, Any]],
-    ) -> Dict[str, float]:
-        # setup
-        self.pre_benchmark()
-
-        # init & (optional) compile
-        model = init_fn(model_cls, **init_kwargs)
-        if compile_kwargs:
-            model.compile(**compile_kwargs)
-
-        # build inputs
-        inp = get_input_fn()
-
-        # measure
-        run_ctx = torch._inductor.utils.fresh_inductor_cache() if compile_kwargs else nullcontext()
-        with run_ctx:
-            for _ in range(NUM_WARMUP_ROUNDS):
-                _ = model(**inp)
-            time_s = benchmark_fn(lambda m, d: m(**d), model, inp)
-        mem_gb = torch.cuda.max_memory_allocated() / (1024**3)
-        mem_gb = round(mem_gb, 2)
-
-        # teardown
-        self.post_benchmark(model)
-        del model
-        return {"time": time_s, "memory": mem_gb}

benchmarks/benchmarking_wan.py

@@ -1,74 +0,0 @@
-from functools import partial
-
-import torch
-from benchmarking_utils import BenchmarkMixin, BenchmarkScenario, model_init_fn
-
-from diffusers import WanTransformer3DModel
-from diffusers.utils.testing_utils import torch_device
-
-
-CKPT_ID = "Wan-AI/Wan2.1-T2V-14B-Diffusers"
-RESULT_FILENAME = "wan.csv"
-
-
-def get_input_dict(**device_dtype_kwargs):
-    # height: 480
-    # width: 832
-    # num_frames: 81
-    # max_sequence_length: 512
-    hidden_states = torch.randn(1, 16, 21, 60, 104, **device_dtype_kwargs)
-    encoder_hidden_states = torch.randn(1, 512, 4096, **device_dtype_kwargs)
-    timestep = torch.tensor([1.0], **device_dtype_kwargs)
-
-    return {"hidden_states": hidden_states, "encoder_hidden_states": encoder_hidden_states, "timestep": timestep}
-
-
-if __name__ == "__main__":
-    scenarios = [
-        BenchmarkScenario(
-            name=f"{CKPT_ID}-bf16",
-            model_cls=WanTransformer3DModel,
-            model_init_kwargs={
-                "pretrained_model_name_or_path": CKPT_ID,
-                "torch_dtype": torch.bfloat16,
-                "subfolder": "transformer",
-            },
-            get_model_input_dict=partial(get_input_dict, device=torch_device, dtype=torch.bfloat16),
-            model_init_fn=model_init_fn,
-            compile_kwargs={"fullgraph": True},
-        ),
-        BenchmarkScenario(
-            name=f"{CKPT_ID}-layerwise-upcasting",
-            model_cls=WanTransformer3DModel,
-            model_init_kwargs={
-                "pretrained_model_name_or_path": CKPT_ID,
-                "torch_dtype": torch.bfloat16,
-                "subfolder": "transformer",
-            },
-            get_model_input_dict=partial(get_input_dict, device=torch_device, dtype=torch.bfloat16),
-            model_init_fn=partial(model_init_fn, layerwise_upcasting=True),
-        ),
-        BenchmarkScenario(
-            name=f"{CKPT_ID}-group-offload-leaf",
-            model_cls=WanTransformer3DModel,
-            model_init_kwargs={
-                "pretrained_model_name_or_path": CKPT_ID,
-                "torch_dtype": torch.bfloat16,
-                "subfolder": "transformer",
-            },
-            get_model_input_dict=partial(get_input_dict, device=torch_device, dtype=torch.bfloat16),
-            model_init_fn=partial(
-                model_init_fn,
-                group_offload_kwargs={
-                    "onload_device": torch_device,
-                    "offload_device": torch.device("cpu"),
-                    "offload_type": "leaf_level",
-                    "use_stream": True,
-                    "non_blocking": True,
-                },
-            ),
-        ),
-    ]
-
-    runner = BenchmarkMixin()
-    runner.run_bencmarks_and_collate(scenarios, filename=RESULT_FILENAME)

benchmarks/populate_into_db.py

@@ -1,166 +0,0 @@
-import argparse
-import os
-import sys
-
-import gpustat
-import pandas as pd
-import psycopg2
-import psycopg2.extras
-from psycopg2.extensions import register_adapter
-from psycopg2.extras import Json
-
-
-register_adapter(dict, Json)
-
-FINAL_CSV_FILENAME = "collated_results.csv"
-# https://github.com/huggingface/transformers/blob/593e29c5e2a9b17baec010e8dc7c1431fed6e841/benchmark/init_db.sql#L27
-BENCHMARKS_TABLE_NAME = "benchmarks"
-MEASUREMENTS_TABLE_NAME = "model_measurements"
-
-
-def _init_benchmark(conn, branch, commit_id, commit_msg):
-    gpu_stats = gpustat.GPUStatCollection.new_query()
-    metadata = {"gpu_name": gpu_stats[0]["name"]}
-    repository = "huggingface/diffusers"
-    with conn.cursor() as cur:
-        cur.execute(
-            f"INSERT INTO {BENCHMARKS_TABLE_NAME} (repository, branch, commit_id, commit_message, metadata) VALUES (%s, %s, %s, %s, %s) RETURNING benchmark_id",
-            (repository, branch, commit_id, commit_msg, metadata),
-        )
-        benchmark_id = cur.fetchone()[0]
-        print(f"Initialised benchmark #{benchmark_id}")
-        return benchmark_id
-
-
-def parse_args():
-    parser = argparse.ArgumentParser()
-    parser.add_argument(
-        "branch",
-        type=str,
-        help="The branch name on which the benchmarking is performed.",
-    )
-
-    parser.add_argument(
-        "commit_id",
-        type=str,
-        help="The commit hash on which the benchmarking is performed.",
-    )
-
-    parser.add_argument(
-        "commit_msg",
-        type=str,
-        help="The commit message associated with the commit, truncated to 70 characters.",
-    )
-    args = parser.parse_args()
-    return args
-
-
-if __name__ == "__main__":
-    args = parse_args()
-    try:
-        conn = psycopg2.connect(
-            host=os.getenv("PGHOST"),
-            database=os.getenv("PGDATABASE"),
-            user=os.getenv("PGUSER"),
-            password=os.getenv("PGPASSWORD"),
-        )
-        print("DB connection established successfully.")
-    except Exception as e:
-        print(f"Problem during DB init: {e}")
-        sys.exit(1)
-
-    try:
-        benchmark_id = _init_benchmark(
-            conn=conn,
-            branch=args.branch,
-            commit_id=args.commit_id,
-            commit_msg=args.commit_msg,
-        )
-    except Exception as e:
-        print(f"Problem during initializing benchmark: {e}")
-        sys.exit(1)
-
-    cur = conn.cursor()
-
-    df = pd.read_csv(FINAL_CSV_FILENAME)
-
-    # Helper to cast values (or None) given a dtype
-    def _cast_value(val, dtype: str):
-        if pd.isna(val):
-            return None
-
-        if dtype == "text":
-            return str(val).strip()
-
-        if dtype == "float":
-            try:
-                return float(val)
-            except ValueError:
-                return None
-
-        if dtype == "bool":
-            s = str(val).strip().lower()
-            if s in ("true", "t", "yes", "1"):
-                return True
-            if s in ("false", "f", "no", "0"):
-                return False
-            if val in (1, 1.0):
-                return True
-            if val in (0, 0.0):
-                return False
-            return None
-
-        return val
-
-    try:
-        rows_to_insert = []
-        for _, row in df.iterrows():
-            scenario = _cast_value(row.get("scenario"), "text")
-            model_cls = _cast_value(row.get("model_cls"), "text")
-            num_params_B = _cast_value(row.get("num_params_B"), "float")
-            flops_G = _cast_value(row.get("flops_G"), "float")
-            time_plain_s = _cast_value(row.get("time_plain_s"), "float")
-            mem_plain_GB = _cast_value(row.get("mem_plain_GB"), "float")
-            time_compile_s = _cast_value(row.get("time_compile_s"), "float")
-            mem_compile_GB = _cast_value(row.get("mem_compile_GB"), "float")
-            fullgraph = _cast_value(row.get("fullgraph"), "bool")
-            mode = _cast_value(row.get("mode"), "text")
-
-            # If "github_sha" column exists in the CSV, cast it; else default to None
-            if "github_sha" in df.columns:
-                github_sha = _cast_value(row.get("github_sha"), "text")
-            else:
-                github_sha = None
-
-            measurements = {
-                "scenario": scenario,
-                "model_cls": model_cls,
-                "num_params_B": num_params_B,
-                "flops_G": flops_G,
-                "time_plain_s": time_plain_s,
-                "mem_plain_GB": mem_plain_GB,
-                "time_compile_s": time_compile_s,
-                "mem_compile_GB": mem_compile_GB,
-                "fullgraph": fullgraph,
-                "mode": mode,
-                "github_sha": github_sha,
-            }
-            rows_to_insert.append((benchmark_id, measurements))
-
-        # Batch-insert all rows
-        insert_sql = f"""
-        INSERT INTO {MEASUREMENTS_TABLE_NAME} (
-            benchmark_id,
-            measurements
-        )
-        VALUES (%s, %s);
-        """
-
-        psycopg2.extras.execute_batch(cur, insert_sql, rows_to_insert)
-        conn.commit()
-
-        cur.close()
-        conn.close()
-    except Exception as e:
-        print(f"Exception: {e}")
-        sys.exit(1)

benchmarks/push_results.py

@@ -1,19 +1,19 @@
-import os
+import glob
+import sys
 
 import pandas as pd
 from huggingface_hub import hf_hub_download, upload_file
-from huggingface_hub.utils import EntryNotFoundError
+from huggingface_hub.utils._errors import EntryNotFoundError
 
 
-REPO_ID = "diffusers/benchmarks"
+sys.path.append(".")
+from utils import BASE_PATH, FINAL_CSV_FILE, GITHUB_SHA, REPO_ID, collate_csv  # noqa: E402
 
 
 def has_previous_benchmark() -> str:
-    from run_all import FINAL_CSV_FILENAME
-
     csv_path = None
     try:
-        csv_path = hf_hub_download(repo_id=REPO_ID, repo_type="dataset", filename=FINAL_CSV_FILENAME)
+        csv_path = hf_hub_download(repo_id=REPO_ID, repo_type="dataset", filename=FINAL_CSV_FILE)
     except EntryNotFoundError:
         csv_path = None
     return csv_path
@@ -26,50 +26,46 @@ def filter_float(value):
 
 
 def push_to_hf_dataset():
-    from run_all import FINAL_CSV_FILENAME, GITHUB_SHA
+    all_csvs = sorted(glob.glob(f"{BASE_PATH}/*.csv"))
+    collate_csv(all_csvs, FINAL_CSV_FILE)
 
+    # If there's an existing benchmark file, we should report the changes.
     csv_path = has_previous_benchmark()
     if csv_path is not None:
-        current_results = pd.read_csv(FINAL_CSV_FILENAME)
+        current_results = pd.read_csv(FINAL_CSV_FILE)
         previous_results = pd.read_csv(csv_path)
 
         numeric_columns = current_results.select_dtypes(include=["float64", "int64"]).columns
+        numeric_columns = [
+            c for c in numeric_columns if c not in ["batch_size", "num_inference_steps", "actual_gpu_memory (gbs)"]
+        ]
 
         for column in numeric_columns:
-            # get previous values as floats, aligned to current index
-            prev_vals = previous_results[column].map(filter_float).reindex(current_results.index)
+            previous_results[column] = previous_results[column].map(lambda x: filter_float(x))
 
-            # get current values as floats
-            curr_vals = current_results[column].astype(float)
+            # Calculate the percentage change
+            current_results[column] = current_results[column].astype(float)
+            previous_results[column] = previous_results[column].astype(float)
+            percent_change = ((current_results[column] - previous_results[column]) / previous_results[column]) * 100
 
-            # stringify the current values
-            curr_str = curr_vals.map(str)
-
-            # build an appendage only when prev exists and differs
-            append_str = prev_vals.where(prev_vals.notnull() & (prev_vals != curr_vals), other=pd.NA).map(
-                lambda x: f" ({x})" if pd.notnull(x) else ""
+            # Format the values with '+' or '-' sign and append to original values
+            current_results[column] = current_results[column].map(str) + percent_change.map(
+                lambda x: f" ({'+' if x > 0 else ''}{x:.2f}%)"
             )
+            # There might be newly added rows. So, filter out the NaNs.
+            current_results[column] = current_results[column].map(lambda x: x.replace(" (nan%)", ""))
 
-            # combine
-            current_results[column] = curr_str + append_str
-        os.remove(FINAL_CSV_FILENAME)
-        current_results.to_csv(FINAL_CSV_FILENAME, index=False)
+        # Overwrite the current result file.
+        current_results.to_csv(FINAL_CSV_FILE, index=False)
 
     commit_message = f"upload from sha: {GITHUB_SHA}" if GITHUB_SHA is not None else "upload benchmark results"
     upload_file(
         repo_id=REPO_ID,
-        path_in_repo=FINAL_CSV_FILENAME,
-        path_or_fileobj=FINAL_CSV_FILENAME,
+        path_in_repo=FINAL_CSV_FILE,
+        path_or_fileobj=FINAL_CSV_FILE,
         repo_type="dataset",
         commit_message=commit_message,
     )
-    upload_file(
-        repo_id="diffusers/benchmark-analyzer",
-        path_in_repo=FINAL_CSV_FILENAME,
-        path_or_fileobj=FINAL_CSV_FILENAME,
-        repo_type="space",
-        commit_message=commit_message,
-    )
 
 
 if __name__ == "__main__":

benchmarks/requirements.txt

@@ -1,6 +0,0 @@
-pandas 
-psutil
-gpustat
-torchprofile
-bitsandbytes
-psycopg2==2.9.9

benchmarks/run_all.py

@@ -1,84 +1,97 @@
 import glob
-import logging
-import os
 import subprocess
-
-import pandas as pd
+import sys
+from typing import List
 
 
-logging.basicConfig(level=logging.INFO, format="%(asctime)s %(levelname)s %(name)s: %(message)s")
-logger = logging.getLogger(__name__)
+sys.path.append(".")
+from benchmark_text_to_image import ALL_T2I_CKPTS  # noqa: E402
 
-PATTERN = "benchmarking_*.py"
-FINAL_CSV_FILENAME = "collated_results.csv"
-GITHUB_SHA = os.getenv("GITHUB_SHA", None)
+
+PATTERN = "benchmark_*.py"
 
 
 class SubprocessCallException(Exception):
     pass
 
 
-def run_command(command: list[str], return_stdout=False):
+# Taken from `test_examples_utils.py`
+def run_command(command: List[str], return_stdout=False):
+    """
+    Runs `command` with `subprocess.check_output` and will potentially return the `stdout`. Will also properly capture
+    if an error occurred while running `command`
+    """
     try:
         output = subprocess.check_output(command, stderr=subprocess.STDOUT)
-        if return_stdout and hasattr(output, "decode"):
-            return output.decode("utf-8")
+        if return_stdout:
+            if hasattr(output, "decode"):
+                output = output.decode("utf-8")
+            return output
     except subprocess.CalledProcessError as e:
-        raise SubprocessCallException(f"Command `{' '.join(command)}` failed with:\n{e.output.decode()}") from e
+        raise SubprocessCallException(
+            f"Command `{' '.join(command)}` failed with the following error:\n\n{e.output.decode()}"
+        ) from e
 
 
-def merge_csvs(final_csv: str = "collated_results.csv"):
-    all_csvs = glob.glob("*.csv")
-    all_csvs = [f for f in all_csvs if f != final_csv]
-    if not all_csvs:
-        logger.info("No result CSVs found to merge.")
-        return
-
-    df_list = []
-    for f in all_csvs:
-        try:
-            d = pd.read_csv(f)
-        except pd.errors.EmptyDataError:
-            # If a file existed but was zero‐bytes or corrupted, skip it
-            continue
-        df_list.append(d)
-
-    if not df_list:
-        logger.info("All result CSVs were empty or invalid; nothing to merge.")
-        return
-
-    final_df = pd.concat(df_list, ignore_index=True)
-    if GITHUB_SHA is not None:
-        final_df["github_sha"] = GITHUB_SHA
-    final_df.to_csv(final_csv, index=False)
-    logger.info(f"Merged {len(all_csvs)} partial CSVs → {final_csv}.")
-
-
-def run_scripts():
-    python_files = sorted(glob.glob(PATTERN))
-    python_files = [f for f in python_files if f != "benchmarking_utils.py"]
+def main():
+    python_files = glob.glob(PATTERN)
 
     for file in python_files:
-        script_name = file.split(".py")[0].split("_")[-1]  # example: benchmarking_foo.py -> foo
-        logger.info(f"\n****** Running file: {file} ******")
+        print(f"****** Running file: {file} ******")
 
-        partial_csv = f"{script_name}.csv"
-        if os.path.exists(partial_csv):
-            logger.info(f"Found {partial_csv}. Removing for safer numbers and duplication.")
-            os.remove(partial_csv)
+        # Run with canonical settings.
+        if file != "benchmark_text_to_image.py":
+            command = f"python {file}"
+            run_command(command.split())
 
-        command = ["python", file]
-        try:
-            run_command(command)
-            logger.info(f"→ {file} finished normally.")
-        except SubprocessCallException as e:
-            logger.info(f"Error running {file}:\n{e}")
-        finally:
-            logger.info(f"→ Merging partial CSVs after {file} …")
-            merge_csvs(final_csv=FINAL_CSV_FILENAME)
+            command += " --run_compile"
+            run_command(command.split())
 
-    logger.info(f"\nAll scripts attempted. Final collated CSV: {FINAL_CSV_FILENAME}")
+    # Run variants.
+    for file in python_files:
+        if file == "benchmark_text_to_image.py":
+            for ckpt in ALL_T2I_CKPTS:
+                command = f"python {file} --ckpt {ckpt}"
+
+                if "turbo" in ckpt:
+                    command += " --num_inference_steps 1"
+
+                run_command(command.split())
+
+                command += " --run_compile"
+                run_command(command.split())
+
+        elif file == "benchmark_sd_img.py":
+            for ckpt in ["stabilityai/stable-diffusion-xl-refiner-1.0", "stabilityai/sdxl-turbo"]:
+                command = f"python {file} --ckpt {ckpt}"
+
+                if ckpt == "stabilityai/sdxl-turbo":
+                    command += " --num_inference_steps 2"
+
+                run_command(command.split())
+                command += " --run_compile"
+                run_command(command.split())
+
+        elif file in ["benchmark_sd_inpainting.py", "benchmark_ip_adapters.py"]:
+            sdxl_ckpt = "stabilityai/stable-diffusion-xl-base-1.0"
+            command = f"python {file} --ckpt {sdxl_ckpt}"
+            run_command(command.split())
+
+            command += " --run_compile"
+            run_command(command.split())
+
+        elif file in ["benchmark_controlnet.py", "benchmark_t2i_adapter.py"]:
+            sdxl_ckpt = (
+                "diffusers/controlnet-canny-sdxl-1.0"
+                if "controlnet" in file
+                else "TencentARC/t2i-adapter-canny-sdxl-1.0"
+            )
+            command = f"python {file} --ckpt {sdxl_ckpt}"
+            run_command(command.split())
+
+            command += " --run_compile"
+            run_command(command.split())
 
 
 if __name__ == "__main__":
-    run_scripts()
+    main()

benchmarks/utils.py

@@ -0,0 +1,98 @@
+import argparse
+import csv
+import gc
+import os
+from dataclasses import dataclass
+from typing import Dict, List, Union
+
+import torch
+import torch.utils.benchmark as benchmark
+
+
+GITHUB_SHA = os.getenv("GITHUB_SHA", None)
+BENCHMARK_FIELDS = [
+    "pipeline_cls",
+    "ckpt_id",
+    "batch_size",
+    "num_inference_steps",
+    "model_cpu_offload",
+    "run_compile",
+    "time (secs)",
+    "memory (gbs)",
+    "actual_gpu_memory (gbs)",
+    "github_sha",
+]
+
+PROMPT = "ghibli style, a fantasy landscape with castles"
+BASE_PATH = os.getenv("BASE_PATH", ".")
+TOTAL_GPU_MEMORY = float(os.getenv("TOTAL_GPU_MEMORY", torch.cuda.get_device_properties(0).total_memory / (1024**3)))
+
+REPO_ID = "diffusers/benchmarks"
+FINAL_CSV_FILE = "collated_results.csv"
+
+
+@dataclass
+class BenchmarkInfo:
+    time: float
+    memory: float
+
+
+def flush():
+    """Wipes off memory."""
+    gc.collect()
+    torch.cuda.empty_cache()
+    torch.cuda.reset_max_memory_allocated()
+    torch.cuda.reset_peak_memory_stats()
+
+
+def bytes_to_giga_bytes(bytes):
+    return f"{(bytes / 1024 / 1024 / 1024):.3f}"
+
+
+def benchmark_fn(f, *args, **kwargs):
+    t0 = benchmark.Timer(
+        stmt="f(*args, **kwargs)",
+        globals={"args": args, "kwargs": kwargs, "f": f},
+        num_threads=torch.get_num_threads(),
+    )
+    return f"{(t0.blocked_autorange().mean):.3f}"
+
+
+def generate_csv_dict(
+    pipeline_cls: str, ckpt: str, args: argparse.Namespace, benchmark_info: BenchmarkInfo
+) -> Dict[str, Union[str, bool, float]]:
+    """Packs benchmarking data into a dictionary for latter serialization."""
+    data_dict = {
+        "pipeline_cls": pipeline_cls,
+        "ckpt_id": ckpt,
+        "batch_size": args.batch_size,
+        "num_inference_steps": args.num_inference_steps,
+        "model_cpu_offload": args.model_cpu_offload,
+        "run_compile": args.run_compile,
+        "time (secs)": benchmark_info.time,
+        "memory (gbs)": benchmark_info.memory,
+        "actual_gpu_memory (gbs)": f"{(TOTAL_GPU_MEMORY):.3f}",
+        "github_sha": GITHUB_SHA,
+    }
+    return data_dict
+
+
+def write_to_csv(file_name: str, data_dict: Dict[str, Union[str, bool, float]]):
+    """Serializes a dictionary into a CSV file."""
+    with open(file_name, mode="w", newline="") as csvfile:
+        writer = csv.DictWriter(csvfile, fieldnames=BENCHMARK_FIELDS)
+        writer.writeheader()
+        writer.writerow(data_dict)
+
+
+def collate_csv(input_files: List[str], output_file: str):
+    """Collates multiple identically structured CSVs into a single CSV file."""
+    with open(output_file, mode="w", newline="") as outfile:
+        writer = csv.DictWriter(outfile, fieldnames=BENCHMARK_FIELDS)
+        writer.writeheader()
+
+        for file in input_files:
+            with open(file, mode="r") as infile:
+                reader = csv.DictReader(infile)
+                for row in reader:
+                    writer.writerow(row)

docker/diffusers-doc-builder/Dockerfile

@@ -1,45 +0,0 @@
-FROM python:3.10-slim
-ENV PYTHONDONTWRITEBYTECODE=1
-LABEL maintainer="Hugging Face"
-LABEL repository="diffusers"
-
-ENV DEBIAN_FRONTEND=noninteractive
-
-RUN apt-get -y update && apt-get install -y bash \
-    build-essential \
-    git \
-    git-lfs \
-    curl \
-    ca-certificates \
-    libglib2.0-0 \
-    libsndfile1-dev \
-    libgl1 \
-    zip \
-    wget
-
-ENV UV_PYTHON=/usr/local/bin/python
-
-# pre-install the heavy dependencies (these can later be overridden by the deps from setup.py)
-RUN pip install uv
-RUN uv pip install --no-cache-dir \
-    torch \
-    torchvision \
-    torchaudio \
-    --extra-index-url https://download.pytorch.org/whl/cpu
-
-RUN uv pip install --no-cache-dir "git+https://github.com/huggingface/diffusers.git@main#egg=diffusers[test]"
-
-# Extra dependencies
-RUN uv pip install --no-cache-dir \
-    accelerate \
-    numpy==1.26.4 \
-    hf_xet \
-    setuptools==69.5.1 \
-    bitsandbytes \
-    torchao \
-    gguf \
-    optimum-quanto
-
-RUN apt-get clean && rm -rf /var/lib/apt/lists/* && apt-get autoremove && apt-get autoclean
-
-CMD ["/bin/bash"]

docker/diffusers-flax-cpu/Dockerfile

@@ -0,0 +1,44 @@
+FROM ubuntu:20.04
+LABEL maintainer="Hugging Face"
+LABEL repository="diffusers"
+
+ENV DEBIAN_FRONTEND=noninteractive
+
+RUN apt update && \
+    apt install -y bash \
+                   build-essential \
+                   git \
+                   git-lfs \
+                   curl \
+                   ca-certificates \
+                   libsndfile1-dev \
+                   python3.8 \
+                   python3-pip \
+                   python3.8-venv && \
+    rm -rf /var/lib/apt/lists
+
+# make sure to use 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)
+# follow the instructions here: https://cloud.google.com/tpu/docs/run-in-container#train_a_jax_model_in_a_docker_container
+RUN python3 -m pip install --no-cache-dir --upgrade pip uv==0.1.11 && \
+    python3 -m uv pip install --upgrade --no-cache-dir \
+        clu \
+        "jax[cpu]>=0.2.16,!=0.3.2" \
+        "flax>=0.4.1" \
+        "jaxlib>=0.1.65" && \
+    python3 -m uv pip install --no-cache-dir \
+        accelerate \
+        datasets \
+        hf-doc-builder \
+        huggingface-hub \
+        Jinja2 \
+        librosa \
+        numpy \
+        scipy \
+        tensorboard \
+        transformers
+
+CMD ["/bin/bash"]

docker/diffusers-flax-tpu/Dockerfile

@@ -0,0 +1,46 @@
+FROM ubuntu:20.04
+LABEL maintainer="Hugging Face"
+LABEL repository="diffusers"
+
+ENV DEBIAN_FRONTEND=noninteractive
+
+RUN apt update && \
+    apt install -y bash \
+                   build-essential \
+                   git \
+                   git-lfs \
+                   curl \
+                   ca-certificates \
+                   libsndfile1-dev \
+                   python3.8 \
+                   python3-pip \
+                   python3.8-venv && \
+    rm -rf /var/lib/apt/lists
+
+# make sure to use 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)
+# follow the instructions here: https://cloud.google.com/tpu/docs/run-in-container#train_a_jax_model_in_a_docker_container
+RUN python3 -m pip install --no-cache-dir --upgrade pip uv==0.1.11 && \
+    python3 -m pip install --no-cache-dir \
+        "jax[tpu]>=0.2.16,!=0.3.2" \
+        -f https://storage.googleapis.com/jax-releases/libtpu_releases.html && \
+    python3 -m uv pip install --upgrade --no-cache-dir \
+        clu \
+        "flax>=0.4.1" \
+        "jaxlib>=0.1.65" && \
+    python3 -m uv pip install --no-cache-dir \
+        accelerate \
+        datasets \
+        hf-doc-builder \
+        huggingface-hub \
+        Jinja2 \
+        librosa \        
+        numpy \
+        scipy \
+        tensorboard \
+        transformers
+
+CMD ["/bin/bash"]

docker/diffusers-onnxruntime-cpu/Dockerfile

@@ -4,33 +4,29 @@ 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 \
-                   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 -m pip install --no-cache-dir --upgrade pip uv==0.1.11 && \
     python3 -m uv pip install --no-cache-dir \
-        torch \
-        torchvision \
-        torchaudio\
+        torch==2.1.2 \
+        torchvision==0.16.2 \
+        torchaudio==2.1.2 \
         onnxruntime \
         --extra-index-url https://download.pytorch.org/whl/cpu && \
     python3 -m uv pip install --no-cache-dir \
@@ -40,10 +36,9 @@ 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 \
-        hf_xet
+        transformers
 
 CMD ["/bin/bash"]

docker/diffusers-onnxruntime-cuda/Dockerfile

@@ -4,44 +4,39 @@ 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 \
-                   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 \
-        hf_xet \
         Jinja2 \
         librosa \
-        numpy==1.26.4 \
+        numpy \
         scipy \
         tensorboard \
         transformers

docker/diffusers-pytorch-compile-cuda/Dockerfile

@@ -0,0 +1,45 @@
+FROM nvidia/cuda:12.1.0-runtime-ubuntu20.04
+LABEL maintainer="Hugging Face"
+LABEL repository="diffusers"
+
+ENV DEBIAN_FRONTEND=noninteractive
+
+RUN apt update && \
+    apt install -y bash \
+    build-essential \
+    git \
+    git-lfs \
+    curl \
+    ca-certificates \
+    libsndfile1-dev \
+    libgl1 \
+    python3.9 \
+    python3.9-dev \
+    python3-pip \
+    python3.9-venv && \
+    rm -rf /var/lib/apt/lists
+
+# make sure to use 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 python3.9 -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 && \
+    python3.9 -m pip install --no-cache-dir \
+    accelerate \
+    datasets \
+    hf-doc-builder \
+    huggingface-hub \
+    Jinja2 \
+    librosa \
+    numpy \
+    scipy \
+    tensorboard \
+    transformers
+
+CMD ["/bin/bash"]

docker/diffusers-pytorch-cpu/Dockerfile

@@ -1,38 +1,45 @@
-FROM python:3.10-slim
-ENV PYTHONDONTWRITEBYTECODE=1
+FROM ubuntu:20.04
 LABEL maintainer="Hugging Face"
 LABEL repository="diffusers"
 
 ENV DEBIAN_FRONTEND=noninteractive
 
-RUN apt-get -y update && apt-get install -y bash \
-    build-essential \
-    git \
-    git-lfs \
-    curl \
-    ca-certificates \
-    libglib2.0-0 \
-    libsndfile1-dev \
-    libgl1
+RUN apt update && \
+    apt install -y bash \
+                   build-essential \
+                   git \
+                   git-lfs \
+                   curl \
+                   ca-certificates \
+                   libsndfile1-dev \
+                   python3.8 \
+                   python3-pip \
+                   libgl1 \
+                   python3.8-venv && \
+    rm -rf /var/lib/apt/lists
 
-ENV UV_PYTHON=/usr/local/bin/python
+# make sure to use 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 pip install uv
-RUN uv pip install --no-cache-dir \
-    torch \
-    torchvision \
-    torchaudio \
-    --extra-index-url https://download.pytorch.org/whl/cpu
-
-RUN uv pip install --no-cache-dir "git+https://github.com/huggingface/diffusers.git@main#egg=diffusers[test]"
-
-# Extra dependencies
-RUN uv pip install --no-cache-dir \
-    accelerate \
-    numpy==1.26.4 \
-    hf_xet
-
-RUN apt-get clean && rm -rf /var/lib/apt/lists/* && apt-get autoremove && apt-get autoclean
+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 -m uv pip install --no-cache-dir \
+        accelerate \
+        datasets \
+        hf-doc-builder \
+        huggingface-hub \
+        Jinja2 \
+        librosa \
+        numpy \
+        scipy \
+        tensorboard \
+        transformers matplotlib
 
 CMD ["/bin/bash"]

docker/diffusers-pytorch-cuda/Dockerfile

@@ -2,48 +2,44 @@ FROM nvidia/cuda:12.1.0-runtime-ubuntu20.04
 LABEL maintainer="Hugging Face"
 LABEL repository="diffusers"
 
-ARG PYTHON_VERSION=3.12
 ENV DEBIAN_FRONTEND=noninteractive
 
-RUN apt-get -y update \
-    && apt-get install -y software-properties-common \
-    && add-apt-repository ppa:deadsnakes/ppa && \
-    apt-get update
-
-RUN apt install -y bash \
+RUN apt update && \
+    apt install -y bash \
     build-essential \
     git \
     git-lfs \
     curl \
     ca-certificates \
-    libglib2.0-0 \
     libsndfile1-dev \
     libgl1 \
-    python3 \
+    python3.8 \
     python3-pip \
-    && apt-get clean \
-    && rm -rf /var/lib/apt/lists/*
+    python3.8-venv && \
+    rm -rf /var/lib/apt/lists
 
-RUN curl -LsSf https://astral.sh/uv/install.sh | sh
-ENV PATH="/root/.local/bin:$PATH"
-ENV VIRTUAL_ENV="/opt/venv"
-ENV UV_PYTHON_INSTALL_DIR=/opt/uv/python
-RUN uv venv --python ${PYTHON_VERSION} --seed ${VIRTUAL_ENV}
-ENV PATH="$VIRTUAL_ENV/bin:$PATH"
+# make sure to use venv
+RUN python3 -m venv /opt/venv
+ENV PATH="/opt/venv/bin:$PATH"
 
 # pre-install the heavy dependencies (these can later be overridden by the deps from setup.py)
-RUN 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
-
-RUN uv pip install --no-cache-dir "git+https://github.com/huggingface/diffusers.git@main#egg=diffusers[test]"
-
-# Extra dependencies
-RUN uv pip install --no-cache-dir \
+    torchaudio \
+    invisible_watermark && \
+    python3 -m pip install --no-cache-dir \
     accelerate \
-    numpy==1.26.4 \
-    pytorch-lightning \
-    hf_xet
+    datasets \
+    hf-doc-builder \
+    huggingface-hub \
+    Jinja2 \
+    librosa \
+    numpy \
+    scipy \
+    tensorboard \
+    transformers \
+    pytorch-lightning
 
 CMD ["/bin/bash"]

docker/diffusers-pytorch-minimum-cuda/Dockerfile

@@ -1,52 +0,0 @@
-FROM nvidia/cuda:12.1.0-runtime-ubuntu20.04
-LABEL maintainer="Hugging Face"
-LABEL repository="diffusers"
-
-ARG PYTHON_VERSION=3.10
-ENV DEBIAN_FRONTEND=noninteractive
-ENV MINIMUM_SUPPORTED_TORCH_VERSION="2.1.0"
-ENV MINIMUM_SUPPORTED_TORCHVISION_VERSION="0.16.0"
-ENV MINIMUM_SUPPORTED_TORCHAUDIO_VERSION="2.1.0"
-
-RUN apt-get -y update \
-    && apt-get install -y software-properties-common \
-    && add-apt-repository ppa:deadsnakes/ppa && \
-    apt-get update
-
-RUN apt install -y bash \
-    build-essential \
-    git \
-    git-lfs \
-    curl \
-    ca-certificates \
-    libglib2.0-0 \
-    libsndfile1-dev \
-    libgl1 \
-    python3 \
-    python3-pip \
-    && apt-get clean \
-    && rm -rf /var/lib/apt/lists/*
-
-RUN curl -LsSf https://astral.sh/uv/install.sh | sh
-ENV PATH="/root/.local/bin:$PATH"
-ENV VIRTUAL_ENV="/opt/venv"
-ENV UV_PYTHON_INSTALL_DIR=/opt/uv/python
-RUN uv venv --python ${PYTHON_VERSION} --seed ${VIRTUAL_ENV}
-ENV PATH="$VIRTUAL_ENV/bin:$PATH"
-
-# pre-install the heavy dependencies (these can later be overridden by the deps from setup.py)
-RUN uv pip install --no-cache-dir \
-    torch==$MINIMUM_SUPPORTED_TORCH_VERSION \
-    torchvision==$MINIMUM_SUPPORTED_TORCHVISION_VERSION \
-    torchaudio==$MINIMUM_SUPPORTED_TORCHAUDIO_VERSION
-
-RUN uv pip install --no-cache-dir "git+https://github.com/huggingface/diffusers.git@main#egg=diffusers[test]"
-
-# Extra dependencies
-RUN uv pip install --no-cache-dir \
-    accelerate \
-    numpy==1.26.4 \
-    pytorch-lightning \
-    hf_xet
-
-CMD ["/bin/bash"]

docker/diffusers-pytorch-xformers-cuda/Dockerfile

@@ -2,49 +2,44 @@ FROM nvidia/cuda:12.1.0-runtime-ubuntu20.04
 LABEL maintainer="Hugging Face"
 LABEL repository="diffusers"
 
-ARG PYTHON_VERSION=3.12
 ENV DEBIAN_FRONTEND=noninteractive
 
-RUN apt-get -y update \
-    && apt-get install -y software-properties-common \
-    && add-apt-repository ppa:deadsnakes/ppa && \
-    apt-get update
+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
 
-RUN apt install -y bash \
-    build-essential \
-    git \
-    git-lfs \
-    curl \
-    ca-certificates \
-    libglib2.0-0 \
-    libsndfile1-dev \
-    libgl1 \
-    python3 \
-    python3-pip \
-    && apt-get clean \
-    && rm -rf /var/lib/apt/lists/*
-
-RUN curl -LsSf https://astral.sh/uv/install.sh | sh
-ENV PATH="/root/.local/bin:$PATH"
-ENV VIRTUAL_ENV="/opt/venv"
-ENV UV_PYTHON_INSTALL_DIR=/opt/uv/python
-RUN uv venv --python ${PYTHON_VERSION} --seed ${VIRTUAL_ENV}
-ENV PATH="$VIRTUAL_ENV/bin:$PATH"
+# make sure to use venv
+RUN python3 -m venv /opt/venv
+ENV PATH="/opt/venv/bin:$PATH"
 
 # pre-install the heavy dependencies (these can later be overridden by the deps from setup.py)
-RUN uv pip install --no-cache-dir \
-    torch \
-    torchvision \
-    torchaudio
-
-RUN uv pip install --no-cache-dir "git+https://github.com/huggingface/diffusers.git@main#egg=diffusers[test]"
-
-# Extra dependencies
-RUN uv pip install --no-cache-dir \
-    accelerate \
-    numpy==1.26.4 \
-    pytorch-lightning \
-    hf_xet \
-    xformers
+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 -m uv pip install --no-cache-dir \
+        accelerate \
+        datasets \
+        hf-doc-builder \
+        huggingface-hub \
+        Jinja2 \
+        librosa \
+        numpy \
+        scipy \
+        tensorboard \
+        transformers \
+        xformers
 
 CMD ["/bin/bash"]

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/TRANSLATING.md

@@ -1,4 +1,4 @@
-<!--Copyright 2025 The HuggingFace Team. All rights reserved.
+<!--Copyright 2024 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at

docs/source/en/advanced_inference/outpaint.md

@@ -1,231 +0,0 @@
-<!--Copyright 2025 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/activations.md

@@ -1,4 +1,4 @@
-<!--Copyright 2025 The HuggingFace Team. All rights reserved.
+<!--Copyright 2024 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at
@@ -25,16 +25,3 @@ Customized activation functions for supporting various models in 🤗 Diffusers.
 ## ApproximateGELU
 
 [[autodoc]] models.activations.ApproximateGELU
-
-
-## SwiGLU
-
-[[autodoc]] models.activations.SwiGLU
-
-## FP32SiLU
-
-[[autodoc]] models.activations.FP32SiLU
-
-## LinearActivation
-
-[[autodoc]] models.activations.LinearActivation

docs/source/en/api/attnprocessor.md

@@ -1,4 +1,4 @@
-<!--Copyright 2025 The HuggingFace Team. All rights reserved.
+<!--Copyright 2024 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at
@@ -15,152 +15,43 @@ specific language governing permissions and limitations under the License.
 An attention processor is a class for applying different types of attention mechanisms.
 
 ## AttnProcessor
-
 [[autodoc]] models.attention_processor.AttnProcessor
 
+## AttnProcessor2_0
 [[autodoc]] models.attention_processor.AttnProcessor2_0
 
+## AttnAddedKVProcessor
 [[autodoc]] models.attention_processor.AttnAddedKVProcessor
 
+## AttnAddedKVProcessor2_0
 [[autodoc]] models.attention_processor.AttnAddedKVProcessor2_0
 
-[[autodoc]] models.attention_processor.AttnProcessorNPU
-
-[[autodoc]] models.attention_processor.FusedAttnProcessor2_0
-
-## Allegro
-
-[[autodoc]] models.attention_processor.AllegroAttnProcessor2_0
-
-## AuraFlow
-
-[[autodoc]] models.attention_processor.AuraFlowAttnProcessor2_0
-
-[[autodoc]] models.attention_processor.FusedAuraFlowAttnProcessor2_0
-
-## CogVideoX
-
-[[autodoc]] models.attention_processor.CogVideoXAttnProcessor2_0
-
-[[autodoc]] models.attention_processor.FusedCogVideoXAttnProcessor2_0
-
 ## CrossFrameAttnProcessor
-
 [[autodoc]] pipelines.text_to_video_synthesis.pipeline_text_to_video_zero.CrossFrameAttnProcessor
 
-## Custom Diffusion
-
+## CustomDiffusionAttnProcessor
 [[autodoc]] models.attention_processor.CustomDiffusionAttnProcessor
 
+## CustomDiffusionAttnProcessor2_0
 [[autodoc]] models.attention_processor.CustomDiffusionAttnProcessor2_0
 
+## CustomDiffusionXFormersAttnProcessor
 [[autodoc]] models.attention_processor.CustomDiffusionXFormersAttnProcessor
 
-## Flux
-
-[[autodoc]] models.attention_processor.FluxAttnProcessor2_0
-
-[[autodoc]] models.attention_processor.FusedFluxAttnProcessor2_0
-
-[[autodoc]] models.attention_processor.FluxSingleAttnProcessor2_0
-
-## Hunyuan
-
-[[autodoc]] models.attention_processor.HunyuanAttnProcessor2_0
-
-[[autodoc]] models.attention_processor.FusedHunyuanAttnProcessor2_0
-
-[[autodoc]] models.attention_processor.PAGHunyuanAttnProcessor2_0
-
-[[autodoc]] models.attention_processor.PAGCFGHunyuanAttnProcessor2_0
-
-## IdentitySelfAttnProcessor2_0
-
-[[autodoc]] models.attention_processor.PAGIdentitySelfAttnProcessor2_0
-
-[[autodoc]] models.attention_processor.PAGCFGIdentitySelfAttnProcessor2_0
-
-## IP-Adapter
-
-[[autodoc]] models.attention_processor.IPAdapterAttnProcessor
-
-[[autodoc]] models.attention_processor.IPAdapterAttnProcessor2_0
-
-[[autodoc]] models.attention_processor.SD3IPAdapterJointAttnProcessor2_0
-
-## JointAttnProcessor2_0
-
-[[autodoc]] models.attention_processor.JointAttnProcessor2_0
-
-[[autodoc]] models.attention_processor.PAGJointAttnProcessor2_0
-
-[[autodoc]] models.attention_processor.PAGCFGJointAttnProcessor2_0
-
-[[autodoc]] models.attention_processor.FusedJointAttnProcessor2_0
-
-## LoRA
-
-[[autodoc]] models.attention_processor.LoRAAttnProcessor
-
-[[autodoc]] models.attention_processor.LoRAAttnProcessor2_0
+## FusedAttnProcessor2_0
+[[autodoc]] models.attention_processor.FusedAttnProcessor2_0
 
+## LoRAAttnAddedKVProcessor
 [[autodoc]] models.attention_processor.LoRAAttnAddedKVProcessor
 
+## LoRAXFormersAttnProcessor
 [[autodoc]] models.attention_processor.LoRAXFormersAttnProcessor
 
-## Lumina-T2X
-
-[[autodoc]] models.attention_processor.LuminaAttnProcessor2_0
-
-## Mochi
-
-[[autodoc]] models.attention_processor.MochiAttnProcessor2_0
-
-[[autodoc]] models.attention_processor.MochiVaeAttnProcessor2_0
-
-## Sana
-
-[[autodoc]] models.attention_processor.SanaLinearAttnProcessor2_0
-
-[[autodoc]] models.attention_processor.SanaMultiscaleAttnProcessor2_0
-
-[[autodoc]] models.attention_processor.PAGCFGSanaLinearAttnProcessor2_0
-
-[[autodoc]] models.attention_processor.PAGIdentitySanaLinearAttnProcessor2_0
-
-## Stable Audio
-
-[[autodoc]] models.attention_processor.StableAudioAttnProcessor2_0
-
 ## SlicedAttnProcessor
-
 [[autodoc]] models.attention_processor.SlicedAttnProcessor
 
+## SlicedAttnAddedKVProcessor
 [[autodoc]] models.attention_processor.SlicedAttnAddedKVProcessor
 
 ## XFormersAttnProcessor
-
 [[autodoc]] models.attention_processor.XFormersAttnProcessor
-
-[[autodoc]] models.attention_processor.XFormersAttnAddedKVProcessor
-
-## XLAFlashAttnProcessor2_0
-
-[[autodoc]] models.attention_processor.XLAFlashAttnProcessor2_0
-
-## XFormersJointAttnProcessor
-
-[[autodoc]] models.attention_processor.XFormersJointAttnProcessor
-
-## IPAdapterXFormersAttnProcessor
-
-[[autodoc]] models.attention_processor.IPAdapterXFormersAttnProcessor
-
-## FluxIPAdapterJointAttnProcessor2_0
-
-[[autodoc]] models.attention_processor.FluxIPAdapterJointAttnProcessor2_0
-
-
-## XLAFluxFlashAttnProcessor2_0
-
-[[autodoc]] models.attention_processor.XLAFluxFlashAttnProcessor2_0

docs/source/en/api/cache.md

@@ -1,36 +0,0 @@
-<!-- Copyright 2025 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. -->
-
-# Caching methods
-
-Cache methods speedup diffusion transformers by storing and reusing intermediate outputs of specific layers, such as attention and feedforward layers, instead of recalculating them at each inference step.
-
-## CacheMixin
-
-[[autodoc]] CacheMixin
-
-## PyramidAttentionBroadcastConfig
-
-[[autodoc]] PyramidAttentionBroadcastConfig
-
-[[autodoc]] apply_pyramid_attention_broadcast
-
-## FasterCacheConfig
-
-[[autodoc]] FasterCacheConfig
-
-[[autodoc]] apply_faster_cache
-
-### FirstBlockCacheConfig
-
-[[autodoc]] FirstBlockCacheConfig
-
-[[autodoc]] apply_first_block_cache

docs/source/en/api/configuration.md

@@ -1,4 +1,4 @@
-<!--Copyright 2025 The HuggingFace Team. All rights reserved.
+<!--Copyright 2024 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at
@@ -14,8 +14,11 @@ specific language governing permissions and limitations under the License.
 
 Schedulers from [`~schedulers.scheduling_utils.SchedulerMixin`] and models from [`ModelMixin`] inherit from [`ConfigMixin`] which stores all the parameters that are passed to their respective `__init__` methods in a JSON-configuration file.
 
-> [!TIP]
-> To use private or [gated](https://huggingface.co/docs/hub/models-gated#gated-models) models, log-in with `hf auth login`.
+<Tip>
+
+To use private or [gated](https://huggingface.co/docs/hub/models-gated#gated-models) models, log-in with `huggingface-cli login`.
+
+</Tip>
 
 ## ConfigMixin
 

docs/source/en/api/image_processor.md

@@ -1,4 +1,4 @@
-<!--Copyright 2025 The HuggingFace Team. All rights reserved.
+<!--Copyright 2024 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at
@@ -20,22 +20,8 @@ All pipelines with [`VaeImageProcessor`] accept PIL Image, PyTorch tensor, or Nu
 
 [[autodoc]] image_processor.VaeImageProcessor
 
-## InpaintProcessor
-
-The [`InpaintProcessor`] accepts `mask` and `image` inputs and process them together. Optionally, it can accept padding_mask_crop and apply mask overlay.
-
-[[autodoc]] image_processor.InpaintProcessor
-
 ## VaeImageProcessorLDM3D
 
 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/internal_classes_overview.md

@@ -1,4 +1,4 @@
-<!--Copyright 2025 The HuggingFace Team. All rights reserved.
+<!--Copyright 2024 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at

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

@@ -1,4 +1,4 @@
-<!--Copyright 2025 The HuggingFace Team. All rights reserved.
+<!--Copyright 2024 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at
@@ -14,19 +14,16 @@ specific language governing permissions and limitations under the License.
 
 [IP-Adapter](https://hf.co/papers/2308.06721) is a lightweight adapter that enables prompting a diffusion model with an image. This method decouples the cross-attention layers of the image and text features. The image features are generated from an image encoder.
 
-> [!TIP]
-> Learn how to load and use an IP-Adapter checkpoint and image in the [IP-Adapter](../../using-diffusers/ip_adapter) guide,.
+<Tip>
+
+Learn how to load an IP-Adapter checkpoint and image in the IP-Adapter [loading](../../using-diffusers/loading_adapters#ip-adapter) guide, and you can see how to use it in the [usage](../../using-diffusers/ip_adapter) guide.
+
+</Tip>
 
 ## IPAdapterMixin
 
 [[autodoc]] loaders.ip_adapter.IPAdapterMixin
 
-## SD3IPAdapterMixin
-
-[[autodoc]] loaders.ip_adapter.SD3IPAdapterMixin
-    - all
-    - is_ip_adapter_active
-
 ## IPAdapterMaskProcessor
 
 [[autodoc]] image_processor.IPAdapterMaskProcessor

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

@@ -1,4 +1,4 @@
-<!--Copyright 2025 The HuggingFace Team. All rights reserved.
+<!--Copyright 2024 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at
@@ -12,114 +12,21 @@ specific language governing permissions and limitations under the License.
 
 # LoRA
 
-LoRA is a fast and lightweight training method that inserts and trains a significantly smaller number of parameters instead of all the model parameters. This produces a smaller file (~100 MBs) and makes it easier to quickly train a model to learn a new concept. LoRA weights are typically loaded into the denoiser, text encoder or both. The denoiser usually corresponds to a UNet ([`UNet2DConditionModel`], for example) or a Transformer ([`SD3Transformer2DModel`], for example). There are several classes for loading LoRA weights:
+LoRA is a fast and lightweight training method that inserts and trains a significantly smaller number of parameters instead of all the model parameters. This produces a smaller file (~100 MBs) and makes it easier to quickly train a model to learn a new concept. LoRA weights are typically loaded into the UNet, text encoder or both. There are two classes for loading LoRA weights:
 
-- [`StableDiffusionLoraLoaderMixin`] provides functions for loading and unloading, fusing and unfusing, enabling and disabling, and more functions for managing LoRA weights. This class can be used with any model.
-- [`StableDiffusionXLLoraLoaderMixin`] is a [Stable Diffusion (SDXL)](../../api/pipelines/stable_diffusion/stable_diffusion_xl) version of the [`StableDiffusionLoraLoaderMixin`] class for loading and saving LoRA weights. It can only be used with the SDXL model.
-- [`SD3LoraLoaderMixin`] provides similar functions for [Stable Diffusion 3](https://huggingface.co/blog/sd3).
-- [`FluxLoraLoaderMixin`] provides similar functions for [Flux](https://huggingface.co/docs/diffusers/main/en/api/pipelines/flux).
-- [`CogVideoXLoraLoaderMixin`] provides similar functions for [CogVideoX](https://huggingface.co/docs/diffusers/main/en/api/pipelines/cogvideox).
-- [`Mochi1LoraLoaderMixin`] provides similar functions for [Mochi](https://huggingface.co/docs/diffusers/main/en/api/pipelines/mochi).
-- [`AuraFlowLoraLoaderMixin`] provides similar functions for [AuraFlow](https://huggingface.co/fal/AuraFlow).
-- [`LTXVideoLoraLoaderMixin`] provides similar functions for [LTX-Video](https://huggingface.co/docs/diffusers/main/en/api/pipelines/ltx_video).
-- [`SanaLoraLoaderMixin`] provides similar functions for [Sana](https://huggingface.co/docs/diffusers/main/en/api/pipelines/sana).
-- [`HunyuanVideoLoraLoaderMixin`] provides similar functions for [HunyuanVideo](https://huggingface.co/docs/diffusers/main/en/api/pipelines/hunyuan_video).
-- [`Lumina2LoraLoaderMixin`] provides similar functions for [Lumina2](https://huggingface.co/docs/diffusers/main/en/api/pipelines/lumina2).
-- [`WanLoraLoaderMixin`] provides similar functions for [Wan](https://huggingface.co/docs/diffusers/main/en/api/pipelines/wan).
-- [`SkyReelsV2LoraLoaderMixin`] provides similar functions for [SkyReels-V2](https://huggingface.co/docs/diffusers/main/en/api/pipelines/skyreels_v2).
-- [`CogView4LoraLoaderMixin`] provides similar functions for [CogView4](https://huggingface.co/docs/diffusers/main/en/api/pipelines/cogview4).
-- [`AmusedLoraLoaderMixin`] is for the [`AmusedPipeline`].
-- [`HiDreamImageLoraLoaderMixin`] provides similar functions for [HiDream Image](https://huggingface.co/docs/diffusers/main/en/api/pipelines/hidream)
-- [`QwenImageLoraLoaderMixin`] provides similar functions for [Qwen Image](https://huggingface.co/docs/diffusers/main/en/api/pipelines/qwen).
-- [`ZImageLoraLoaderMixin`] provides similar functions for [Z-Image](https://huggingface.co/docs/diffusers/main/en/api/pipelines/zimage).
-- [`Flux2LoraLoaderMixin`] provides similar functions for [Flux2](https://huggingface.co/docs/diffusers/main/en/api/pipelines/flux2).
-- [`LoraBaseMixin`] provides a base class with several utility methods to fuse, unfuse, unload, LoRAs and more.
+- [`LoraLoaderMixin`] provides functions for loading and unloading, fusing and unfusing, enabling and disabling, and more functions for managing LoRA weights. This class can be used with any model.
+- [`StableDiffusionXLLoraLoaderMixin`] is a [Stable Diffusion (SDXL)](../../api/pipelines/stable_diffusion/stable_diffusion_xl) version of the [`LoraLoaderMixin`] class for loading and saving LoRA weights. It can only be used with the SDXL model.
 
-> [!TIP]
-> To learn more about how to load LoRA weights, see the [LoRA](../../tutorials/using_peft_for_inference) loading guide.
+<Tip>
 
-## LoraBaseMixin
+To learn more about how to load LoRA weights, see the [LoRA](../../using-diffusers/loading_adapters#lora) loading guide.
 
-[[autodoc]] loaders.lora_base.LoraBaseMixin
+</Tip>
 
-## StableDiffusionLoraLoaderMixin
+## LoraLoaderMixin
 
-[[autodoc]] loaders.lora_pipeline.StableDiffusionLoraLoaderMixin
+[[autodoc]] loaders.lora.LoraLoaderMixin
 
 ## StableDiffusionXLLoraLoaderMixin
 
-[[autodoc]] loaders.lora_pipeline.StableDiffusionXLLoraLoaderMixin
-
-## SD3LoraLoaderMixin
-
-[[autodoc]] loaders.lora_pipeline.SD3LoraLoaderMixin
-
-## FluxLoraLoaderMixin
-
-[[autodoc]] loaders.lora_pipeline.FluxLoraLoaderMixin
-
-## Flux2LoraLoaderMixin
-
-[[autodoc]] loaders.lora_pipeline.Flux2LoraLoaderMixin
-
-## CogVideoXLoraLoaderMixin
-
-[[autodoc]] loaders.lora_pipeline.CogVideoXLoraLoaderMixin
-
-## Mochi1LoraLoaderMixin
-
-[[autodoc]] loaders.lora_pipeline.Mochi1LoraLoaderMixin
-## AuraFlowLoraLoaderMixin
-
-[[autodoc]] loaders.lora_pipeline.AuraFlowLoraLoaderMixin
-
-## LTXVideoLoraLoaderMixin
-
-[[autodoc]] loaders.lora_pipeline.LTXVideoLoraLoaderMixin
-
-## SanaLoraLoaderMixin
-
-[[autodoc]] loaders.lora_pipeline.SanaLoraLoaderMixin
-
-## HunyuanVideoLoraLoaderMixin
-
-[[autodoc]] loaders.lora_pipeline.HunyuanVideoLoraLoaderMixin
-
-## Lumina2LoraLoaderMixin
-
-[[autodoc]] loaders.lora_pipeline.Lumina2LoraLoaderMixin
-
-## CogView4LoraLoaderMixin
-
-[[autodoc]] loaders.lora_pipeline.CogView4LoraLoaderMixin
-
-## WanLoraLoaderMixin
-
-[[autodoc]] loaders.lora_pipeline.WanLoraLoaderMixin
-
-## SkyReelsV2LoraLoaderMixin
-
-[[autodoc]] loaders.lora_pipeline.SkyReelsV2LoraLoaderMixin
-
-## AmusedLoraLoaderMixin
-
-[[autodoc]] loaders.lora_pipeline.AmusedLoraLoaderMixin
-
-## HiDreamImageLoraLoaderMixin
-
-[[autodoc]] loaders.lora_pipeline.HiDreamImageLoraLoaderMixin
-
-## QwenImageLoraLoaderMixin
-
-[[autodoc]] loaders.lora_pipeline.QwenImageLoraLoaderMixin
-
-## ZImageLoraLoaderMixin
-
-[[autodoc]] loaders.lora_pipeline.ZImageLoraLoaderMixin
-
-## KandinskyLoraLoaderMixin
-[[autodoc]] loaders.lora_pipeline.KandinskyLoraLoaderMixin
-
-## LoraBaseMixin
-
-[[autodoc]] loaders.lora_base.LoraBaseMixin
+[[autodoc]] loaders.lora.StableDiffusionXLLoraLoaderMixin

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

@@ -1,4 +1,4 @@
-<!--Copyright 2025 The HuggingFace Team. All rights reserved.
+<!--Copyright 2024 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at
@@ -12,10 +12,13 @@ specific language governing permissions and limitations under the License.
 
 # PEFT
 
-Diffusers supports loading adapters such as [LoRA](../../tutorials/using_peft_for_inference) with the [PEFT](https://huggingface.co/docs/peft/index) library with the [`~loaders.peft.PeftAdapterMixin`] class. This allows modeling classes in Diffusers like [`UNet2DConditionModel`], [`SD3Transformer2DModel`] to operate with an adapter.
+Diffusers supports loading adapters such as [LoRA](../../using-diffusers/loading_adapters) with the [PEFT](https://huggingface.co/docs/peft/index) library with the [`~loaders.peft.PeftAdapterMixin`] class. This allows modeling classes in Diffusers like [`UNet2DConditionModel`] to load an adapter.
 
-> [!TIP]
-> Refer to the [Inference with PEFT](../../tutorials/using_peft_for_inference.md) tutorial for an overview of how to use PEFT in Diffusers for inference.
+<Tip>
+
+Refer to the [Inference with PEFT](../../tutorials/using_peft_for_inference.md) tutorial for an overview of how to use PEFT in Diffusers for inference.
+
+</Tip>
 
 ## PeftAdapterMixin
 

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

@@ -1,4 +1,4 @@
-<!--Copyright 2025 The HuggingFace Team. All rights reserved.
+<!--Copyright 2024 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at
@@ -12,51 +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`]
-- [`FluxTransformer2DModel`]
+</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/loaders/textual_inversion.md

@@ -1,4 +1,4 @@
-<!--Copyright 2025 The HuggingFace Team. All rights reserved.
+<!--Copyright 2024 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at
@@ -16,8 +16,11 @@ Textual Inversion is a training method for personalizing models by learning new
 
 [`TextualInversionLoaderMixin`] provides a function for loading Textual Inversion embeddings from Diffusers and Automatic1111 into the text encoder and loading a special token to activate the embeddings.
 
-> [!TIP]
-> To learn more about how to load Textual Inversion embeddings, see the [Textual Inversion](../../using-diffusers/textual_inversion_inference) loading guide.
+<Tip>
+
+To learn more about how to load Textual Inversion embeddings, see the [Textual Inversion](../../using-diffusers/loading_adapters#textual-inversion) loading guide.
+
+</Tip>
 
 ## TextualInversionLoaderMixin
 

docs/source/en/api/loaders/transformer_sd3.md

@@ -1,26 +0,0 @@
-<!--Copyright 2025 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.
--->
-
-# SD3Transformer2D
-
-This class is useful when *only* loading weights into a [`SD3Transformer2DModel`]. If you need to load weights into the text encoder or a text encoder and SD3Transformer2DModel, check [`SD3LoraLoaderMixin`](lora#diffusers.loaders.SD3LoraLoaderMixin) class instead.
-
-The [`SD3Transformer2DLoadersMixin`] class currently only loads IP-Adapter weights, but will be used in the future to save weights and load LoRAs.
-
-> [!TIP]
-> To learn more about how to load LoRA weights, see the [LoRA](../../tutorials/using_peft_for_inference) loading guide.
-
-## SD3Transformer2DLoadersMixin
-
-[[autodoc]] loaders.transformer_sd3.SD3Transformer2DLoadersMixin
-    - all
-    - _load_ip_adapter_weights

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

@@ -1,4 +1,4 @@
-<!--Copyright 2025 The HuggingFace Team. All rights reserved.
+<!--Copyright 2024 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at
@@ -12,12 +12,15 @@ specific language governing permissions and limitations under the License.
 
 # UNet
 
-Some training methods - like LoRA and Custom Diffusion - typically target the UNet's attention layers, but these training methods can also target other non-attention layers. Instead of training all of a model's parameters, only a subset of the parameters are trained, which is faster and more efficient. This class is useful if you're *only* loading weights into a UNet. If you need to load weights into the text encoder or a text encoder and UNet, try using the [`~loaders.StableDiffusionLoraLoaderMixin.load_lora_weights`] function instead.
+Some training methods - like LoRA and Custom Diffusion - typically target the UNet's attention layers, but these training methods can also target other non-attention layers. Instead of training all of a model's parameters, only a subset of the parameters are trained, which is faster and more efficient. This class is useful if you're *only* loading weights into a UNet. If you need to load weights into the text encoder or a text encoder and UNet, try using the [`~loaders.LoraLoaderMixin.load_lora_weights`] function instead.
 
 The [`UNet2DConditionLoadersMixin`] class provides functions for loading and saving weights, fusing and unfusing LoRAs, disabling and enabling LoRAs, and setting and deleting adapters.
 
-> [!TIP]
-> To learn more about how to load LoRA weights, see the [LoRA](../../tutorials/using_peft_for_inference) guide.
+<Tip>
+
+To learn more about how to load LoRA weights, see the [LoRA](../../using-diffusers/loading_adapters#lora) loading guide.
+
+</Tip>
 
 ## UNet2DConditionLoadersMixin
 

docs/source/en/api/logging.md

@@ -1,4 +1,4 @@
-<!--Copyright 2025 The HuggingFace Team. All rights reserved.
+<!--Copyright 2024 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at

docs/source/en/api/models/allegro_transformer3d.md

@@ -1,30 +0,0 @@
-<!-- Copyright 2025 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. -->
-
-# AllegroTransformer3DModel
-
-A Diffusion Transformer model for 3D data from [Allegro](https://github.com/rhymes-ai/Allegro) was introduced in [Allegro: Open the Black Box of Commercial-Level Video Generation Model](https://huggingface.co/papers/2410.15458) by RhymesAI.
-
-The model can be loaded with the following code snippet.
-
-```python
-from diffusers import AllegroTransformer3DModel
-
-transformer = AllegroTransformer3DModel.from_pretrained("rhymes-ai/Allegro", subfolder="transformer", torch_dtype=torch.bfloat16).to("cuda")
-```
-
-## AllegroTransformer3DModel
-
-[[autodoc]] AllegroTransformer3DModel
-
-## Transformer2DModelOutput
-
-[[autodoc]] models.modeling_outputs.Transformer2DModelOutput

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

@@ -1,4 +1,4 @@
-<!--Copyright 2025 The HuggingFace Team. All rights reserved.
+<!--Copyright 2024 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at
@@ -12,7 +12,7 @@ specific language governing permissions and limitations under the License.
 
 # AsymmetricAutoencoderKL
 
-Improved larger variational autoencoder (VAE) model with KL loss for inpainting task: [Designing a Better Asymmetric VQGAN for StableDiffusion](https://huggingface.co/papers/2306.04632) by Zixin Zhu, Xuelu Feng, Dongdong Chen, Jianmin Bao, Le Wang, Yinpeng Chen, Lu Yuan, Gang Hua.
+Improved larger variational autoencoder (VAE) model with KL loss for inpainting task: [Designing a Better Asymmetric VQGAN for StableDiffusion](https://arxiv.org/abs/2306.04632) by Zixin Zhu, Xuelu Feng, Dongdong Chen, Jianmin Bao, Le Wang, Yinpeng Chen, Lu Yuan, Gang Hua.
 
 The abstract from the paper is:
 
@@ -39,7 +39,7 @@ mask_url = "https://huggingface.co/datasets/hf-internal-testing/diffusers-images
 original_image = load_image(img_url).resize((512, 512))
 mask_image = load_image(mask_url).resize((512, 512))
 
-pipe = StableDiffusionInpaintPipeline.from_pretrained("stable-diffusion-v1-5/stable-diffusion-inpainting")
+pipe = StableDiffusionInpaintPipeline.from_pretrained("runwayml/stable-diffusion-inpainting")
 pipe.vae = AsymmetricAutoencoderKL.from_pretrained("cross-attention/asymmetric-autoencoder-kl-x-1-5")
 pipe.to("cuda")
 

docs/source/en/api/models/aura_flow_transformer2d.md

@@ -1,19 +0,0 @@
-<!--Copyright 2025 The HuggingFace Team. All rights reserved.
-
-Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
-the License. You may obtain a copy of the License at
-
-http://www.apache.org/licenses/LICENSE-2.0
-
-Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
-an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
-specific language governing permissions and limitations under the License.
--->
-
-# AuraFlowTransformer2DModel
-
-A Transformer model for image-like data from [AuraFlow](https://blog.fal.ai/auraflow/).
-
-## AuraFlowTransformer2DModel
-
-[[autodoc]] AuraFlowTransformer2DModel

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

@@ -1,21 +0,0 @@
-<!--Copyright 2025 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.
--->
-
-# AutoModel
-
-[`AutoModel`] automatically retrieves the correct model class from the checkpoint `config.json` file.
-
-## AutoModel
-
-[[autodoc]] AutoModel
-	- all
-	- from_pretrained

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

@@ -1,72 +0,0 @@
-<!-- Copyright 2025 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. -->
-
-# AutoencoderDC
-
-The 2D Autoencoder model used in [SANA](https://huggingface.co/papers/2410.10629) and introduced in [DCAE](https://huggingface.co/papers/2410.10733) by authors Junyu Chen\*, Han Cai\*, Junsong Chen, Enze Xie, Shang Yang, Haotian Tang, Muyang Li, Yao Lu, Song Han from MIT HAN Lab.
-
-The abstract from the paper is:
-
-*We present Deep Compression Autoencoder (DC-AE), a new family of autoencoder models for accelerating high-resolution diffusion models. Existing autoencoder models have demonstrated impressive results at a moderate spatial compression ratio (e.g., 8x), but fail to maintain satisfactory reconstruction accuracy for high spatial compression ratios (e.g., 64x). We address this challenge by introducing two key techniques: (1) Residual Autoencoding, where we design our models to learn residuals based on the space-to-channel transformed features to alleviate the optimization difficulty of high spatial-compression autoencoders; (2) Decoupled High-Resolution Adaptation, an efficient decoupled three-phases training strategy for mitigating the generalization penalty of high spatial-compression autoencoders. With these designs, we improve the autoencoder's spatial compression ratio up to 128 while maintaining the reconstruction quality. Applying our DC-AE to latent diffusion models, we achieve significant speedup without accuracy drop. For example, on ImageNet 512x512, our DC-AE provides 19.1x inference speedup and 17.9x training speedup on H100 GPU for UViT-H while achieving a better FID, compared with the widely used SD-VAE-f8 autoencoder. Our code is available at [this https URL](https://github.com/mit-han-lab/efficientvit).*
-
-The following DCAE models are released and supported in Diffusers.
-
-| Diffusers format | Original format |
-|:----------------:|:---------------:|
-| [`mit-han-lab/dc-ae-f32c32-sana-1.0-diffusers`](https://huggingface.co/mit-han-lab/dc-ae-f32c32-sana-1.0-diffusers) | [`mit-han-lab/dc-ae-f32c32-sana-1.0`](https://huggingface.co/mit-han-lab/dc-ae-f32c32-sana-1.0)
-| [`mit-han-lab/dc-ae-f32c32-in-1.0-diffusers`](https://huggingface.co/mit-han-lab/dc-ae-f32c32-in-1.0-diffusers) | [`mit-han-lab/dc-ae-f32c32-in-1.0`](https://huggingface.co/mit-han-lab/dc-ae-f32c32-in-1.0)
-| [`mit-han-lab/dc-ae-f32c32-mix-1.0-diffusers`](https://huggingface.co/mit-han-lab/dc-ae-f32c32-mix-1.0-diffusers) | [`mit-han-lab/dc-ae-f32c32-mix-1.0`](https://huggingface.co/mit-han-lab/dc-ae-f32c32-mix-1.0)
-| [`mit-han-lab/dc-ae-f64c128-in-1.0-diffusers`](https://huggingface.co/mit-han-lab/dc-ae-f64c128-in-1.0-diffusers) | [`mit-han-lab/dc-ae-f64c128-in-1.0`](https://huggingface.co/mit-han-lab/dc-ae-f64c128-in-1.0)
-| [`mit-han-lab/dc-ae-f64c128-mix-1.0-diffusers`](https://huggingface.co/mit-han-lab/dc-ae-f64c128-mix-1.0-diffusers) | [`mit-han-lab/dc-ae-f64c128-mix-1.0`](https://huggingface.co/mit-han-lab/dc-ae-f64c128-mix-1.0)
-| [`mit-han-lab/dc-ae-f128c512-in-1.0-diffusers`](https://huggingface.co/mit-han-lab/dc-ae-f128c512-in-1.0-diffusers) | [`mit-han-lab/dc-ae-f128c512-in-1.0`](https://huggingface.co/mit-han-lab/dc-ae-f128c512-in-1.0)
-| [`mit-han-lab/dc-ae-f128c512-mix-1.0-diffusers`](https://huggingface.co/mit-han-lab/dc-ae-f128c512-mix-1.0-diffusers) | [`mit-han-lab/dc-ae-f128c512-mix-1.0`](https://huggingface.co/mit-han-lab/dc-ae-f128c512-mix-1.0)
-
-This model was contributed by [lawrence-cj](https://github.com/lawrence-cj).
-
-Load a model in Diffusers format with [`~ModelMixin.from_pretrained`].
-
-```python
-from diffusers import AutoencoderDC
-
-ae = AutoencoderDC.from_pretrained("mit-han-lab/dc-ae-f32c32-sana-1.0-diffusers", torch_dtype=torch.float32).to("cuda")
-```
-
-## Load a model in Diffusers via `from_single_file`
-
-```python
-from difusers import AutoencoderDC
-
-ckpt_path = "https://huggingface.co/mit-han-lab/dc-ae-f32c32-sana-1.0/blob/main/model.safetensors"
-model = AutoencoderDC.from_single_file(ckpt_path) 
-
-```
-
-The `AutoencoderDC` model has `in` and `mix` single file checkpoint variants that have matching checkpoint keys, but use different scaling factors. It is not possible for Diffusers to automatically infer the correct config file to use with the model based on just the checkpoint and will default to configuring the model using the `mix` variant config file. To override the automatically determined config, please use the `config` argument when using single file loading with `in` variant checkpoints. 
-
-```python
-from diffusers import AutoencoderDC
-
-ckpt_path = "https://huggingface.co/mit-han-lab/dc-ae-f128c512-in-1.0/blob/main/model.safetensors"
-model = AutoencoderDC.from_single_file(ckpt_path, config="mit-han-lab/dc-ae-f128c512-in-1.0-diffusers")
-```
-
-
-## AutoencoderDC
-
-[[autodoc]] AutoencoderDC
-  - encode
-  - decode
-  - all
-
-## DecoderOutput
-
-[[autodoc]] models.autoencoders.vae.DecoderOutput
-

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

@@ -1,32 +0,0 @@
-<!-- Copyright 2025 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. -->
-
-# AutoencoderKLHunyuanVideo
-
-The 3D variational autoencoder (VAE) model with KL loss used in [HunyuanVideo](https://github.com/Tencent/HunyuanVideo/), which was introduced in [HunyuanVideo: A Systematic Framework For Large Video Generative Models](https://huggingface.co/papers/2412.03603) by Tencent.
-
-The model can be loaded with the following code snippet.
-
-```python
-from diffusers import AutoencoderKLHunyuanVideo
-
-vae = AutoencoderKLHunyuanVideo.from_pretrained("hunyuanvideo-community/HunyuanVideo", subfolder="vae", torch_dtype=torch.float16)
-```
-
-## AutoencoderKLHunyuanVideo
-
-[[autodoc]] AutoencoderKLHunyuanVideo
-  - decode
-  - all
-
-## DecoderOutput
-
-[[autodoc]] models.autoencoders.vae.DecoderOutput

docs/source/en/api/models/autoencoder_kl_hunyuan_video15.md

@@ -1,36 +0,0 @@
-<!-- Copyright 2025 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. -->
-
-# AutoencoderKLHunyuanVideo15
-
-The 3D variational autoencoder (VAE) model with KL loss used in [HunyuanVideo1.5](https://github.com/Tencent/HunyuanVideo1-1.5) by Tencent.
-
-The model can be loaded with the following code snippet.
-
-```python
-from diffusers import AutoencoderKLHunyuanVideo15
-
-vae = AutoencoderKLHunyuanVideo15.from_pretrained("hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-480p_t2v", subfolder="vae", torch_dtype=torch.float32)
-
-# make sure to enable tiling to avoid OOM
-vae.enable_tiling()
-```
-
-## AutoencoderKLHunyuanVideo15
-
-[[autodoc]] AutoencoderKLHunyuanVideo15
-  - decode
-  - encode
-  - all
-
-## DecoderOutput
-
-[[autodoc]] models.autoencoders.vae.DecoderOutput

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

@@ -1,32 +0,0 @@
-<!-- Copyright 2025 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. -->
-
-# AutoencoderKLHunyuanImage
-
-The 2D variational autoencoder (VAE) model with KL loss used in [HunyuanImage2.1].
-
-The model can be loaded with the following code snippet.
-
-```python
-from diffusers import AutoencoderKLHunyuanImage
-
-vae = AutoencoderKLHunyuanImage.from_pretrained("hunyuanvideo-community/HunyuanImage-2.1-Diffusers", subfolder="vae", torch_dtype=torch.bfloat16)
-```
-
-## AutoencoderKLHunyuanImage
-
-[[autodoc]] AutoencoderKLHunyuanImage
-  - decode
-  - all
-
-## DecoderOutput
-
-[[autodoc]] models.autoencoders.vae.DecoderOutput

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

@@ -1,32 +0,0 @@
-<!-- Copyright 2025 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. -->
-
-# AutoencoderKLHunyuanImageRefiner
-
-The 3D variational autoencoder (VAE) model with KL loss used in [HunyuanImage2.1](https://github.com/Tencent-Hunyuan/HunyuanImage-2.1) for its refiner pipeline.
-
-The model can be loaded with the following code snippet.
-
-```python
-from diffusers import AutoencoderKLHunyuanImageRefiner
-
-vae = AutoencoderKLHunyuanImageRefiner.from_pretrained("hunyuanvideo-community/HunyuanImage-2.1-Refiner-Diffusers", subfolder="vae", torch_dtype=torch.bfloat16)
-```
-
-## AutoencoderKLHunyuanImageRefiner
-
-[[autodoc]] AutoencoderKLHunyuanImageRefiner
-  - decode
-  - all
-
-## DecoderOutput
-
-[[autodoc]] models.autoencoders.vae.DecoderOutput

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

@@ -1,32 +0,0 @@
-<!-- Copyright 2025 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. -->
-
-# AutoencoderKLWan
-
-The 3D variational autoencoder (VAE) model with KL loss used in [Wan 2.1](https://github.com/Wan-Video/Wan2.1) by the Alibaba Wan Team.
-
-The model can be loaded with the following code snippet.
-
-```python
-from diffusers import AutoencoderKLWan
-
-vae = AutoencoderKLWan.from_pretrained("Wan-AI/Wan2.1-T2V-1.3B-Diffusers", subfolder="vae", torch_dtype=torch.float32)
-```
-
-## AutoencoderKLWan
-
-[[autodoc]] AutoencoderKLWan
-  - decode
-  - all
-
-## DecoderOutput
-
-[[autodoc]] models.autoencoders.vae.DecoderOutput

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

@@ -1,38 +0,0 @@
-<!--Copyright 2025 The HuggingFace Team. All rights reserved.
-
-Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
-the License. You may obtain a copy of the License at
-
-http://www.apache.org/licenses/LICENSE-2.0
-
-Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
-an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
-specific language governing permissions and limitations under the License.
--->
-
-# AutoencoderOobleck
-
-The Oobleck variational autoencoder (VAE) model with KL loss was introduced in [Stability-AI/stable-audio-tools](https://github.com/Stability-AI/stable-audio-tools) and [Stable Audio Open](https://huggingface.co/papers/2407.14358) by Stability AI. The model is used in 🤗 Diffusers to encode audio waveforms into latents and to decode latent representations into audio waveforms.
-
-The abstract from the paper is:
-
-*Open generative models are vitally important for the community, allowing for fine-tunes and serving as baselines when presenting new models. However, most current text-to-audio models are private and not accessible for artists and researchers to build upon. Here we describe the architecture and training process of a new open-weights text-to-audio model trained with Creative Commons data. Our evaluation shows that the model's performance is competitive with the state-of-the-art across various metrics. Notably, the reported FDopenl3 results (measuring the realism of the generations) showcase its potential for high-quality stereo sound synthesis at 44.1kHz.*
-
-## AutoencoderOobleck
-
-[[autodoc]] AutoencoderOobleck
-    - decode
-    - encode
-    - all
-
-## OobleckDecoderOutput
-
-[[autodoc]] models.autoencoders.autoencoder_oobleck.OobleckDecoderOutput
-
-## OobleckDecoderOutput
-
-[[autodoc]] models.autoencoders.autoencoder_oobleck.OobleckDecoderOutput
-
-## AutoencoderOobleckOutput
-
-[[autodoc]] models.autoencoders.autoencoder_oobleck.AutoencoderOobleckOutput

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

@@ -1,4 +1,4 @@
-<!--Copyright 2025 The HuggingFace Team. All rights reserved.
+<!--Copyright 2024 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at

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

@@ -1,4 +1,4 @@
-<!--Copyright 2025 The HuggingFace Team. All rights reserved.
+<!--Copyright 2024 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at
@@ -12,7 +12,7 @@ specific language governing permissions and limitations under the License.
 
 # AutoencoderKL
 
-The variational autoencoder (VAE) model with KL loss was introduced in [Auto-Encoding Variational Bayes](https://huggingface.co/papers/1312.6114v11) by Diederik P. Kingma and Max Welling. The model is used in 🤗 Diffusers to encode images into latents and to decode latent representations into images.
+The variational autoencoder (VAE) model with KL loss was introduced in [Auto-Encoding Variational Bayes](https://arxiv.org/abs/1312.6114v11) by Diederik P. Kingma and Max Welling. The model is used in 🤗 Diffusers to encode images into latents and to decode latent representations into images.
 
 The abstract from the paper is:
 
@@ -21,7 +21,7 @@ The abstract from the paper is:
 ## Loading from the original format
 
 By default the [`AutoencoderKL`] should be loaded with [`~ModelMixin.from_pretrained`], but it can also be loaded
-from the original format using [`FromOriginalModelMixin.from_single_file`] as follows:
+from the original format using [`FromOriginalVAEMixin.from_single_file`] as follows:
 
 ```py
 from diffusers import AutoencoderKL
@@ -44,3 +44,15 @@ model = AutoencoderKL.from_single_file(url)
 ## DecoderOutput
 
 [[autodoc]] models.autoencoders.vae.DecoderOutput
+
+## FlaxAutoencoderKL
+
+[[autodoc]] FlaxAutoencoderKL
+
+## FlaxAutoencoderKLOutput
+
+[[autodoc]] models.vae_flax.FlaxAutoencoderKLOutput
+
+## FlaxDecoderOutput
+
+[[autodoc]] models.vae_flax.FlaxDecoderOutput

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

@@ -1,37 +0,0 @@
-<!-- Copyright 2025 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. -->
-
-# AutoencoderKLAllegro
-
-The 3D variational autoencoder (VAE) model with KL loss used in [Allegro](https://github.com/rhymes-ai/Allegro) was introduced in [Allegro: Open the Black Box of Commercial-Level Video Generation Model](https://huggingface.co/papers/2410.15458) by RhymesAI.
-
-The model can be loaded with the following code snippet.
-
-```python
-from diffusers import AutoencoderKLAllegro
-
-vae = AutoencoderKLAllegro.from_pretrained("rhymes-ai/Allegro", subfolder="vae", torch_dtype=torch.float32).to("cuda")
-```
-
-## AutoencoderKLAllegro
-
-[[autodoc]] AutoencoderKLAllegro
-    - decode
-    - encode
-    - all
-
-## AutoencoderKLOutput
-
-[[autodoc]] models.autoencoders.autoencoder_kl.AutoencoderKLOutput
-
-## DecoderOutput
-
-[[autodoc]] models.autoencoders.vae.DecoderOutput

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

@@ -1,37 +0,0 @@
-<!--Copyright 2025 The HuggingFace Team. All rights reserved.
-
-Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
-the License. You may obtain a copy of the License at
-
-http://www.apache.org/licenses/LICENSE-2.0
-
-Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
-an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
-specific language governing permissions and limitations under the License. -->
-
-# AutoencoderKLCogVideoX
-
-The 3D variational autoencoder (VAE) model with KL loss used in [CogVideoX](https://github.com/THUDM/CogVideo) was introduced in [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://github.com/THUDM/CogVideo/blob/main/resources/CogVideoX.pdf) by Tsinghua University & ZhipuAI.
-
-The model can be loaded with the following code snippet.
-
-```python
-from diffusers import AutoencoderKLCogVideoX
-
-vae = AutoencoderKLCogVideoX.from_pretrained("THUDM/CogVideoX-2b", subfolder="vae", torch_dtype=torch.float16).to("cuda")
-```
-
-## AutoencoderKLCogVideoX
-
-[[autodoc]] AutoencoderKLCogVideoX
-    - decode
-    - encode
-    - all
-
-## AutoencoderKLOutput
-
-[[autodoc]] models.autoencoders.autoencoder_kl.AutoencoderKLOutput
-
-## DecoderOutput
-
-[[autodoc]] models.autoencoders.vae.DecoderOutput

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

@@ -1,40 +0,0 @@
-<!-- Copyright 2025 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. -->
-
-# AutoencoderKLCosmos
-
-[Cosmos Tokenizers](https://github.com/NVIDIA/Cosmos-Tokenizer).
-
-Supported models:
-- [nvidia/Cosmos-1.0-Tokenizer-CV8x8x8](https://huggingface.co/nvidia/Cosmos-1.0-Tokenizer-CV8x8x8)
-
-The model can be loaded with the following code snippet.
-
-```python
-from diffusers import AutoencoderKLCosmos
-
-vae = AutoencoderKLCosmos.from_pretrained("nvidia/Cosmos-1.0-Tokenizer-CV8x8x8", subfolder="vae")
-```
-
-## AutoencoderKLCosmos
-
-[[autodoc]] AutoencoderKLCosmos
-    - decode
-    - encode
-    - all
-
-## AutoencoderKLOutput
-
-[[autodoc]] models.autoencoders.autoencoder_kl.AutoencoderKLOutput
-
-## DecoderOutput
-
-[[autodoc]] models.autoencoders.vae.DecoderOutput

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

@@ -1,37 +0,0 @@
-<!-- Copyright 2025 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. -->
-
-# AutoencoderKLLTXVideo
-
-The 3D variational autoencoder (VAE) model with KL loss used in [LTX](https://huggingface.co/Lightricks/LTX-Video) was introduced by Lightricks.
-
-The model can be loaded with the following code snippet.
-
-```python
-from diffusers import AutoencoderKLLTXVideo
-
-vae = AutoencoderKLLTXVideo.from_pretrained("Lightricks/LTX-Video", subfolder="vae", torch_dtype=torch.float32).to("cuda")
-```
-
-## AutoencoderKLLTXVideo
-
-[[autodoc]] AutoencoderKLLTXVideo
-    - decode
-    - encode
-    - all
-
-## AutoencoderKLOutput
-
-[[autodoc]] models.autoencoders.autoencoder_kl.AutoencoderKLOutput
-
-## DecoderOutput
-
-[[autodoc]] models.autoencoders.vae.DecoderOutput