Release: v0.35.0

* add alpha

* load into 2nd transformer

* Update src/diffusers/loaders/lora_conversion_utils.py

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* Update src/diffusers/loaders/lora_conversion_utils.py

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* pr comments

* pr comments

* pr comments

* fix

* fix

* Apply style fixes

* fix copies

* fix

* fix copies

* Update src/diffusers/loaders/lora_pipeline.py

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* revert change

* revert change

* fix copies

* up

* fix

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: linoy <linoy@hf.co>

.github/workflows/benchmark.yml

@@ -11,20 +11,21 @@ env:
   HF_HOME: /mnt/cache
   OMP_NUM_THREADS: 8
   MKL_NUM_THREADS: 8
+  BASE_PATH: benchmark_outputs
 
 jobs:
-  torch_pipelines_cuda_benchmark_tests:
+  torch_models_cuda_benchmark_tests:
     env:
       SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL_BENCHMARK }}
-    name: Torch Core Pipelines CUDA Benchmarking Tests
+    name: Torch Core Models CUDA Benchmarking Tests
     strategy:
       fail-fast: false
       max-parallel: 1
     runs-on:
-      group: aws-g6-4xlarge-plus
+      group: aws-g6e-4xlarge
     container:
-      image: diffusers/diffusers-pytorch-compile-cuda
-      options: --shm-size "16gb" --ipc host --gpus 0
+      image: diffusers/diffusers-pytorch-cuda
+      options: --shm-size "16gb" --ipc host --gpus all
     steps:
       - name: Checkout diffusers
         uses: actions/checkout@v3
@@ -35,27 +36,47 @@ jobs:
           nvidia-smi
       - name: Install dependencies
         run: |
+          apt update
+          apt install -y libpq-dev postgresql-client
           python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
           python -m uv pip install -e [quality,test]
-          python -m uv pip install pandas peft
-          python -m uv pip uninstall transformers && python -m uv pip install transformers==4.48.0
+          python -m uv pip install -r benchmarks/requirements.txt
       - name: Environment
         run: |
           python utils/print_env.py
       - name: Diffusers Benchmarking
         env:
-            HF_TOKEN: ${{ secrets.DIFFUSERS_BOT_TOKEN }}
-            BASE_PATH: benchmark_outputs
+          HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
         run: |
-          export TOTAL_GPU_MEMORY=$(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
+          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
 
       - name: Test suite reports artifacts
         if: ${{ always() }}
         uses: actions/upload-artifact@v4
         with:
           name: benchmark_test_reports
-          path: benchmarks/benchmark_outputs
+          path: benchmarks/${{ 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() }}

.github/workflows/build_docker_images.yml

@@ -38,9 +38,16 @@ jobs:
           token: ${{ secrets.GITHUB_TOKEN }}
 
       - name: Build Changed Docker Images
+        env: 
+          CHANGED_FILES: ${{ steps.file_changes.outputs.all }}
         run: |
-          CHANGED_FILES="${{ steps.file_changes.outputs.all }}"
-          for FILE in $CHANGED_FILES; do
+          echo "$CHANGED_FILES"
+          for FILE in $CHANGED_FILES; do 
+            # skip anything that isn't still on disk
+            if [[ ! -f "$FILE" ]]; then
+              echo "Skipping removed file $FILE"
+              continue
+            fi           
             if [[ "$FILE" == docker/*Dockerfile ]]; then
               DOCKER_PATH="${FILE%/Dockerfile}"
               DOCKER_TAG=$(basename "$DOCKER_PATH")
@@ -65,13 +72,9 @@ jobs:
         image-name:
           - diffusers-pytorch-cpu
           - diffusers-pytorch-cuda
-          - diffusers-pytorch-compile-cuda
+          - diffusers-pytorch-cuda
           - diffusers-pytorch-xformers-cuda
           - diffusers-pytorch-minimum-cuda
-          - diffusers-flax-cpu
-          - diffusers-flax-tpu
-          - diffusers-onnxruntime-cpu
-          - diffusers-onnxruntime-cuda
           - diffusers-doc-builder
 
     steps:

.github/workflows/mirror_community_pipeline.yml

@@ -79,14 +79,14 @@ jobs:
 
       # Check secret is set
       - name: whoami
-        run: huggingface-cli 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: huggingface-cli upload diffusers/community-pipelines-mirror ./examples/community ${PATH_IN_REPO} --repo-type dataset
+        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 }}

.github/workflows/nightly_tests.yml

@@ -13,8 +13,9 @@ env:
   PYTEST_TIMEOUT: 600
   RUN_SLOW: yes
   RUN_NIGHTLY: yes
-  PIPELINE_USAGE_CUTOFF: 5000
+  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:
@@ -60,7 +61,7 @@ jobs:
       group: aws-g4dn-2xlarge
     container:
       image: diffusers/diffusers-pytorch-cuda
-      options: --shm-size "16gb" --ipc host --gpus 0
+      options: --shm-size "16gb" --ipc host --gpus all
     steps:
       - name: Checkout diffusers
         uses: actions/checkout@v3
@@ -99,11 +100,6 @@ jobs:
         with:
           name: pipeline_${{ matrix.module }}_test_reports
           path: reports
-      - name: Generate Report and Notify Channel
-        if: always()
-        run: |
-          pip install slack_sdk tabulate
-          python utils/log_reports.py >> $GITHUB_STEP_SUMMARY
 
   run_nightly_tests_for_other_torch_modules:
     name: Nightly Torch CUDA Tests
@@ -111,7 +107,7 @@ jobs:
       group: aws-g4dn-2xlarge
     container:
       image: diffusers/diffusers-pytorch-cuda
-      options: --shm-size "16gb" --ipc host --gpus 0
+      options: --shm-size "16gb" --ipc host --gpus all
     defaults:
       run:
         shell: bash
@@ -174,12 +170,6 @@ jobs:
         name: torch_${{ matrix.module }}_cuda_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_torch_compile_tests:
     name: PyTorch Compile CUDA tests
 
@@ -187,8 +177,8 @@ jobs:
       group: aws-g4dn-2xlarge
 
     container:
-      image: diffusers/diffusers-pytorch-compile-cuda
-      options: --gpus 0 --shm-size "16gb" --ipc host
+      image: diffusers/diffusers-pytorch-cuda
+      options: --gpus all --shm-size "16gb" --ipc host
 
     steps:
     - name: Checkout diffusers
@@ -223,12 +213,6 @@ jobs:
         name: torch_compile_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_big_gpu_torch_tests:
     name: Torch tests on big GPU
     strategy:
@@ -238,7 +222,7 @@ jobs:
       group: aws-g6e-xlarge-plus
     container:
       image: diffusers/diffusers-pytorch-cuda
-      options: --shm-size "16gb" --ipc host --gpus 0
+      options: --shm-size "16gb" --ipc host --gpus all
     steps:
       - name: Checkout diffusers
         uses: actions/checkout@v3
@@ -264,7 +248,7 @@ jobs:
           BIG_GPU_MEMORY: 40
         run: |
           python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-            -m "big_gpu_with_torch_cuda" \
+            -m "big_accelerator" \
             --make-reports=tests_big_gpu_torch_cuda \
             --report-log=tests_big_gpu_torch_cuda.log \
             tests/
@@ -279,19 +263,14 @@ jobs:
         with:
           name: torch_cuda_big_gpu_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
-          
+
   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 0
+      options: --shm-size "16gb" --ipc host --gpus all
     defaults:
       run:
         shell: bash
@@ -341,132 +320,20 @@ jobs:
         with:
           name: torch_minimum_version_cuda_test_reports
           path: reports
- 
-  run_flax_tpu_tests:
-    name: Nightly Flax TPU Tests
-    runs-on:
-      group: gcp-ct5lp-hightpu-8t
-    if: github.event_name == 'schedule'
-
-    container:
-      image: diffusers/diffusers-flax-tpu
-      options: --shm-size "16gb" --ipc host --privileged ${{ vars.V5_LITEPOD_8_ENV}} -v /mnt/hf_cache:/mnt/hf_cache
-    defaults:
-      run:
-        shell: bash
-    steps:
-    - name: Checkout diffusers
-      uses: actions/checkout@v3
-      with:
-        fetch-depth: 2
-
-    - name: Install dependencies
-      run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m uv pip install -e [quality,test]
-        pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
-        python -m uv pip install pytest-reportlog
-
-    - name: Environment
-      run: python utils/print_env.py
-
-    - name: Run nightly Flax TPU tests
-      env:
-        HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
-      run: |
-        python -m pytest -n 0 \
-          -s -v -k "Flax" \
-          --make-reports=tests_flax_tpu \
-          --report-log=tests_flax_tpu.log \
-          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@v4
-      with:
-        name: flax_tpu_test_reports
-        path: reports
-
-    - name: Generate Report and Notify Channel
-      if: always()
-      run: |
-        pip install slack_sdk tabulate
-        python utils/log_reports.py >> $GITHUB_STEP_SUMMARY
-
-  run_nightly_onnx_tests:
-    name: Nightly ONNXRuntime CUDA tests on Ubuntu
-    runs-on:
-      group: aws-g4dn-2xlarge
-    container:
-      image: diffusers/diffusers-onnxruntime-cuda
-      options: --gpus 0 --shm-size "16gb" --ipc host
-
-    steps:
-    - name: Checkout diffusers
-      uses: actions/checkout@v3
-      with:
-        fetch-depth: 2
-
-    - name: NVIDIA-SMI
-      run: nvidia-smi
-
-    - name: Install dependencies
-      run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m uv pip install -e [quality,test]
-        pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
-        python -m uv pip install pytest-reportlog
-    - name: Environment
-      run: python utils/print_env.py
-
-    - name: Run Nightly ONNXRuntime CUDA tests
-      env:
-        HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
-      run: |
-        python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-          -s -v -k "Onnx" \
-          --make-reports=tests_onnx_cuda \
-          --report-log=tests_onnx_cuda.log \
-          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@v4
-      with:
-        name: tests_onnx_cuda_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_quantization_tests:
     name: Torch quantization nightly tests
     strategy:
       fail-fast: false
       max-parallel: 2
-      matrix: 
+      matrix:
         config:
           - backend: "bitsandbytes"
             test_location: "bnb"
             additional_deps: ["peft"]
           - backend: "gguf"
             test_location: "gguf"
-            additional_deps: ["peft"]
+            additional_deps: ["peft", "kernels"]
           - backend: "torchao"
             test_location: "torchao"
             additional_deps: []
@@ -477,7 +344,7 @@ jobs:
       group: aws-g6e-xlarge-plus
     container:
       image: diffusers/diffusers-pytorch-cuda
-      options: --shm-size "20gb" --ipc host --gpus 0
+      options: --shm-size "20gb" --ipc host --gpus all
     steps:
       - name: Checkout diffusers
         uses: actions/checkout@v3
@@ -519,11 +386,114 @@ jobs:
         with:
           name: torch_cuda_${{ matrix.config.backend }}_reports
           path: reports
-      - name: Generate Report and Notify Channel
-        if: always()
+          
+  run_nightly_pipeline_level_quantization_tests:
+    name: Torch quantization nightly tests
+    strategy:
+      fail-fast: false
+      max-parallel: 2
+    runs-on:
+      group: aws-g6e-xlarge-plus
+    container:
+      image: diffusers/diffusers-pytorch-cuda
+      options: --shm-size "20gb" --ipc host --gpus all
+    steps:
+      - name: Checkout diffusers
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 2
+      - name: NVIDIA-SMI
+        run: nvidia-smi
+      - name: Install dependencies
         run: |
+          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+          python -m uv pip install -e [quality,test]
+          python -m uv pip install -U bitsandbytes optimum_quanto
+          python -m 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: |
+          python -m 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 utils/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
+
+      - name: Show consolidated report
+        run: |
+          cat $CONSOLIDATED_REPORT_PATH >> $GITHUB_STEP_SUMMARY
+
+      - name: Upload consolidated report
+        uses: actions/upload-artifact@v4
+        with:
+          name: consolidated_test_report
+          path: ${{ env.CONSOLIDATED_REPORT_PATH }}
 
 # M1 runner currently not well supported
 # TODO: (Dhruv) add these back when we setup better testing for Apple Silicon

.github/workflows/pr_modular_tests.yml

@@ -0,0 +1,141 @@
+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_HUB_ENABLE_HF_TRANSFER: 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: |
+          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
+
+  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: |
+          python -m 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: ${{ matrix.config.image }}
+      options: --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/
+
+    defaults:
+      run:
+        shell: bash
+
+    steps:
+    - name: Checkout diffusers
+      uses: actions/checkout@v3
+      with:
+        fetch-depth: 2
+
+    - name: Install dependencies
+      run: |
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+        python -m uv pip install -e [quality,test]
+        pip uninstall transformers -y && python -m uv pip install -U transformers@git+https://github.com/huggingface/transformers.git --no-deps
+        pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git --no-deps
+
+    - 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: ${{ matrix.config.framework == 'pytorch_pipelines' }}
+      run: |
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+        python -m pytest -n 8 --max-worker-restart=0 --dist=loadfile \
+          -s -v -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

@@ -14,4 +14,4 @@ jobs:
     with:
       python_quality_dependencies: "[quality]"
     secrets:
-      bot_token: ${{ secrets.GITHUB_TOKEN }}
+      bot_token: ${{ secrets.HF_STYLE_BOT_ACTION }}

.github/workflows/pr_tests.yml

@@ -11,6 +11,7 @@ on:
       - "tests/**.py"
       - ".github/**.yml"
       - "utils/**.py"
+      - "setup.py"
   push:
     branches:
       - ci-*
@@ -86,11 +87,6 @@ jobs:
             runner: aws-general-8-plus
             image: diffusers/diffusers-pytorch-cpu
             report: torch_cpu_models_schedulers
-          - name: Fast Flax CPU tests
-            framework: flax
-            runner: aws-general-8-plus
-            image: diffusers/diffusers-flax-cpu
-            report: flax_cpu
           - name: PyTorch Example CPU tests
             framework: pytorch_examples
             runner: aws-general-8-plus
@@ -146,15 +142,6 @@ jobs:
           --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 4 --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: |
@@ -290,8 +277,8 @@ jobs:
     - name: Failure short reports
       if: ${{ failure() }}
       run: |
-        cat reports/tests_lora_failures_short.txt
-        cat reports/tests_models_lora_failures_short.txt
+        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() }}

.github/workflows/pr_tests_gpu.yml

@@ -13,6 +13,7 @@ on:
       - "src/diffusers/loaders/peft.py"
       - "tests/pipelines/test_pipelines_common.py"
       - "tests/models/test_modeling_common.py"
+      - "examples/**/*.py"
   workflow_dispatch:
 
 concurrency:
@@ -117,7 +118,7 @@ jobs:
       group: aws-g4dn-2xlarge
     container:
       image: diffusers/diffusers-pytorch-cuda
-      options: --shm-size "16gb" --ipc host --gpus 0
+      options: --shm-size "16gb" --ipc host --gpus all
     steps:
       - name: Checkout diffusers
         uses: actions/checkout@v3
@@ -182,13 +183,13 @@ jobs:
       group: aws-g4dn-2xlarge
     container:
       image: diffusers/diffusers-pytorch-cuda
-      options: --shm-size "16gb" --ipc host --gpus 0
+      options: --shm-size "16gb" --ipc host --gpus all
     defaults:
       run:
         shell: bash
     strategy:
       fail-fast: false
-      max-parallel: 2
+      max-parallel: 4
       matrix:
         module: [models, schedulers, lora, others]
     steps:
@@ -252,7 +253,7 @@ jobs:
 
     container:
       image: diffusers/diffusers-pytorch-cuda
-      options: --gpus 0 --shm-size "16gb" --ipc host
+      options: --gpus all --shm-size "16gb" --ipc host
     steps:
     - name: Checkout diffusers
       uses: actions/checkout@v3

.github/workflows/push_tests.yml

@@ -64,7 +64,7 @@ jobs:
       group: aws-g4dn-2xlarge
     container:
       image: diffusers/diffusers-pytorch-cuda
-      options: --shm-size "16gb" --ipc host --gpus 0
+      options: --shm-size "16gb" --ipc host --gpus all
     steps:
       - name: Checkout diffusers
         uses: actions/checkout@v3
@@ -109,7 +109,7 @@ jobs:
       group: aws-g4dn-2xlarge
     container:
       image: diffusers/diffusers-pytorch-cuda
-      options: --shm-size "16gb" --ipc host --gpus 0
+      options: --shm-size "16gb" --ipc host --gpus all
     defaults:
       run:
         shell: bash
@@ -159,102 +159,6 @@ jobs:
         name: torch_cuda_test_reports_${{ matrix.module }}
         path: reports
 
-  flax_tpu_tests:
-    name: Flax TPU Tests
-    runs-on:
-      group: gcp-ct5lp-hightpu-8t
-    container:
-      image: diffusers/diffusers-flax-tpu
-      options: --shm-size "16gb" --ipc host --privileged ${{ vars.V5_LITEPOD_8_ENV}} -v /mnt/hf_cache:/mnt/hf_cache 
-    defaults:
-      run:
-        shell: bash
-    steps:
-    - name: Checkout diffusers
-      uses: actions/checkout@v3
-      with:
-        fetch-depth: 2
-
-    - name: Install dependencies
-      run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m uv pip install -e [quality,test]
-        pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
-
-    - name: Environment
-      run: |
-        python utils/print_env.py
-
-    - name: Run Flax TPU tests
-      env:
-        HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_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: ${{ always() }}
-      uses: actions/upload-artifact@v4
-      with:
-        name: flax_tpu_test_reports
-        path: reports
-
-  onnx_cuda_tests:
-    name: ONNX CUDA Tests
-    runs-on:
-      group: aws-g4dn-2xlarge
-    container:
-      image: diffusers/diffusers-onnxruntime-cuda
-      options: --shm-size "16gb" --ipc host -v /mnt/cache/.cache/huggingface:/mnt/cache/ --gpus 0
-    defaults:
-      run:
-        shell: bash
-    steps:
-    - name: Checkout diffusers
-      uses: actions/checkout@v3
-      with:
-        fetch-depth: 2
-
-    - name: Install dependencies
-      run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m uv pip install -e [quality,test]
-        pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
-
-    - name: Environment
-      run: |
-        python utils/print_env.py
-
-    - name: Run ONNXRuntime CUDA tests
-      env:
-        HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_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@v4
-      with:
-        name: onnx_cuda_test_reports
-        path: reports
-
   run_torch_compile_tests:
     name: PyTorch Compile CUDA tests
 
@@ -262,8 +166,8 @@ jobs:
       group: aws-g4dn-2xlarge
 
     container:
-      image: diffusers/diffusers-pytorch-compile-cuda
-      options: --gpus 0 --shm-size "16gb" --ipc host
+      image: diffusers/diffusers-pytorch-cuda
+      options: --gpus all --shm-size "16gb" --ipc host
 
     steps:
     - name: Checkout diffusers
@@ -306,7 +210,7 @@ jobs:
 
     container:
       image: diffusers/diffusers-pytorch-xformers-cuda
-      options: --gpus 0 --shm-size "16gb" --ipc host
+      options: --gpus all --shm-size "16gb" --ipc host
 
     steps:
     - name: Checkout diffusers
@@ -348,7 +252,7 @@ jobs:
 
     container:
       image: diffusers/diffusers-pytorch-cuda
-      options: --gpus 0 --shm-size "16gb" --ipc host
+      options: --gpus all --shm-size "16gb" --ipc host
     steps:
     - name: Checkout diffusers
       uses: actions/checkout@v3

.github/workflows/push_tests_fast.yml

@@ -33,16 +33,6 @@ jobs:
             runner: aws-general-8-plus
             image: diffusers/diffusers-pytorch-cpu
             report: torch_cpu
-          - name: Fast Flax CPU tests on Ubuntu
-            framework: flax
-            runner: aws-general-8-plus
-            image: diffusers/diffusers-flax-cpu
-            report: flax_cpu
-          - name: Fast ONNXRuntime CPU tests on Ubuntu
-            framework: onnxruntime
-            runner: aws-general-8-plus
-            image: diffusers/diffusers-onnxruntime-cpu
-            report: onnx_cpu
           - name: PyTorch Example CPU tests on Ubuntu
             framework: pytorch_examples
             runner: aws-general-8-plus
@@ -87,24 +77,6 @@ jobs:
           --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 4 --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 4 --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: |

.github/workflows/push_tests_mps.yml

@@ -1,12 +1,7 @@
 name: Fast mps tests on main
 
 on:
-  push:
-    branches:
-      - main
-    paths:
-      - "src/diffusers/**.py"
-      - "tests/**.py"
+  workflow_dispatch:
 
 env:
   DIFFUSERS_IS_CI: yes

.github/workflows/release_tests_fast.yml

@@ -62,7 +62,7 @@ jobs:
       group: aws-g4dn-2xlarge
     container:
       image: diffusers/diffusers-pytorch-cuda
-      options: --shm-size "16gb" --ipc host --gpus 0
+      options: --shm-size "16gb" --ipc host --gpus all
     steps:
       - name: Checkout diffusers
         uses: actions/checkout@v3
@@ -107,7 +107,7 @@ jobs:
       group: aws-g4dn-2xlarge
     container:
       image: diffusers/diffusers-pytorch-cuda
-      options: --shm-size "16gb" --ipc host --gpus 0
+      options: --shm-size "16gb" --ipc host --gpus all
     defaults:
       run:
         shell: bash
@@ -163,7 +163,7 @@ jobs:
       group: aws-g4dn-2xlarge
     container:
       image: diffusers/diffusers-pytorch-minimum-cuda
-      options: --shm-size "16gb" --ipc host --gpus 0
+      options: --shm-size "16gb" --ipc host --gpus all
     defaults:
       run:
         shell: bash
@@ -213,101 +213,6 @@ jobs:
         with:
           name: torch_minimum_version_cuda_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/cache/.cache/huggingface:/mnt/cache/ --privileged
-    defaults:
-      run:
-        shell: bash
-    steps:
-    - name: Checkout diffusers
-      uses: actions/checkout@v3
-      with:
-        fetch-depth: 2
-
-    - name: Install dependencies
-      run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m uv pip install -e [quality,test]
-        pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
-
-    - name: Environment
-      run: |
-        python utils/print_env.py
-
-    - name: Run slow Flax TPU tests
-      env:
-        HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_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: ${{ always() }}
-      uses: actions/upload-artifact@v4
-      with:
-        name: flax_tpu_test_reports
-        path: reports
-
-  onnx_cuda_tests:
-    name: ONNX CUDA Tests
-    runs-on:
-      group: aws-g4dn-2xlarge
-    container:
-      image: diffusers/diffusers-onnxruntime-cuda
-      options: --shm-size "16gb" --ipc host -v /mnt/cache/.cache/huggingface:/mnt/cache/ --gpus 0
-    defaults:
-      run:
-        shell: bash
-    steps:
-    - name: Checkout diffusers
-      uses: actions/checkout@v3
-      with:
-        fetch-depth: 2
-
-    - name: Install dependencies
-      run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m uv pip install -e [quality,test]
-        pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
-
-    - name: Environment
-      run: |
-        python utils/print_env.py
-
-    - name: Run slow ONNXRuntime CUDA tests
-      env:
-        HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_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@v4
-      with:
-        name: onnx_cuda_test_reports
-        path: reports
 
   run_torch_compile_tests:
     name: PyTorch Compile CUDA tests
@@ -316,8 +221,8 @@ jobs:
       group: aws-g4dn-2xlarge
 
     container:
-      image: diffusers/diffusers-pytorch-compile-cuda
-      options: --gpus 0 --shm-size "16gb" --ipc host
+      image: diffusers/diffusers-pytorch-cuda
+      options: --gpus all --shm-size "16gb" --ipc host
 
     steps:
     - name: Checkout diffusers
@@ -360,7 +265,7 @@ jobs:
 
     container:
       image: diffusers/diffusers-pytorch-xformers-cuda
-      options: --gpus 0 --shm-size "16gb" --ipc host
+      options: --gpus all --shm-size "16gb" --ipc host
 
     steps:
     - name: Checkout diffusers
@@ -402,7 +307,7 @@ jobs:
 
     container:
       image: diffusers/diffusers-pytorch-cuda
-      options: --gpus 0 --shm-size "16gb" --ipc host
+      options: --gpus all --shm-size "16gb" --ipc host
 
     steps:
     - name: Checkout diffusers

.github/workflows/run_tests_from_a_pr.yml

@@ -30,7 +30,7 @@ jobs:
       group: aws-g4dn-2xlarge
     container:
       image: ${{ github.event.inputs.docker_image }}
-      options: --gpus 0 --privileged --ipc host -v /mnt/cache/.cache/huggingface:/mnt/cache/
+      options: --gpus all --privileged --ipc host -v /mnt/cache/.cache/huggingface:/mnt/cache/
 
     steps:
       - name: Validate test files input

.github/workflows/ssh-runner.yml

@@ -31,7 +31,7 @@ jobs:
       group: "${{ github.event.inputs.runner_type }}"
     container:
       image: ${{ github.event.inputs.docker_image }}
-      options: --shm-size "16gb" --ipc host -v /mnt/cache/.cache/huggingface/diffusers:/mnt/cache/ --gpus 0 --privileged
+      options: --shm-size "16gb" --ipc host -v /mnt/cache/.cache/huggingface/diffusers:/mnt/cache/ --gpus all --privileged
 
     steps:
       - name: Checkout diffusers

CONTRIBUTING.md

@@ -1,4 +1,4 @@
-<!--Copyright 2024 The HuggingFace Team. All rights reserved.
+<!--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

PHILOSOPHY.md

@@ -1,4 +1,4 @@
-<!--Copyright 2024 The HuggingFace Team. All rights reserved.
+<!--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

benchmarks/README.md

@@ -0,0 +1,69 @@
+# 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

@@ -1,346 +0,0 @@
-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 = {
-    "Lykon/DreamShaper": (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 = "Lykon/DreamShaper"
-
-    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 = "Lykon/DreamShaper"
-
-    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

@@ -1,26 +0,0 @@
-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

@@ -1,33 +0,0 @@
-import argparse
-import sys
-
-
-sys.path.append(".")
-from base_classes import IPAdapterTextToImageBenchmark  # noqa: E402
-
-
-IP_ADAPTER_CKPTS = {
-    # because original SD v1.5 has been taken down.
-    "Lykon/DreamShaper": ("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="rstabilityai/stable-diffusion-xl-base-1.0",
-        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

@@ -1,29 +0,0 @@
-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="Lykon/DreamShaper",
-        choices=[
-            "Lykon/DreamShaper",
-            "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

@@ -1,28 +0,0 @@
-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="Lykon/DreamShaper",
-        choices=[
-            "Lykon/DreamShaper",
-            "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

@@ -1,28 +0,0 @@
-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

@@ -1,23 +0,0 @@
-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

@@ -1,40 +0,0 @@
-import argparse
-import sys
-
-
-sys.path.append(".")
-from base_classes import TextToImageBenchmark, TurboTextToImageBenchmark  # noqa: E402
-
-
-ALL_T2I_CKPTS = [
-    "Lykon/DreamShaper",
-    "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="Lykon/DreamShaper",
-        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

@@ -0,0 +1,98 @@
+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

@@ -0,0 +1,80 @@
+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

@@ -0,0 +1,82 @@
+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

@@ -0,0 +1,244 @@
+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

@@ -0,0 +1,74 @@
+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

@@ -0,0 +1,166 @@
+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 glob
-import sys
+import os
 
 import pandas as pd
 from huggingface_hub import hf_hub_download, upload_file
 from huggingface_hub.utils import EntryNotFoundError
 
 
-sys.path.append(".")
-from utils import BASE_PATH, FINAL_CSV_FILE, GITHUB_SHA, REPO_ID, collate_csv  # noqa: E402
+REPO_ID = "diffusers/benchmarks"
 
 
 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_FILE)
+        csv_path = hf_hub_download(repo_id=REPO_ID, repo_type="dataset", filename=FINAL_CSV_FILENAME)
     except EntryNotFoundError:
         csv_path = None
     return csv_path
@@ -26,46 +26,50 @@ def filter_float(value):
 
 
 def push_to_hf_dataset():
-    all_csvs = sorted(glob.glob(f"{BASE_PATH}/*.csv"))
-    collate_csv(all_csvs, FINAL_CSV_FILE)
+    from run_all import FINAL_CSV_FILENAME, GITHUB_SHA
 
-    # 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_FILE)
+        current_results = pd.read_csv(FINAL_CSV_FILENAME)
         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:
-            previous_results[column] = previous_results[column].map(lambda x: filter_float(x))
+            # get previous values as floats, aligned to current index
+            prev_vals = previous_results[column].map(filter_float).reindex(current_results.index)
 
-            # 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
+            # get current values as floats
+            curr_vals = current_results[column].astype(float)
 
-            # 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}%)"
+            # 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 ""
             )
-            # There might be newly added rows. So, filter out the NaNs.
-            current_results[column] = current_results[column].map(lambda x: x.replace(" (nan%)", ""))
 
-        # Overwrite the current result file.
-        current_results.to_csv(FINAL_CSV_FILE, index=False)
+            # combine
+            current_results[column] = curr_str + append_str
+        os.remove(FINAL_CSV_FILENAME)
+        current_results.to_csv(FINAL_CSV_FILENAME, 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_FILE,
-        path_or_fileobj=FINAL_CSV_FILE,
+        path_in_repo=FINAL_CSV_FILENAME,
+        path_or_fileobj=FINAL_CSV_FILENAME,
         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

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

benchmarks/run_all.py

@@ -1,101 +1,84 @@
 import glob
+import logging
+import os
 import subprocess
-import sys
-from typing import List
+
+import pandas as pd
 
 
-sys.path.append(".")
-from benchmark_text_to_image import ALL_T2I_CKPTS  # noqa: E402
+logging.basicConfig(level=logging.INFO, format="%(asctime)s %(levelname)s %(name)s: %(message)s")
+logger = logging.getLogger(__name__)
 
-
-PATTERN = "benchmark_*.py"
+PATTERN = "benchmarking_*.py"
+FINAL_CSV_FILENAME = "collated_results.csv"
+GITHUB_SHA = os.getenv("GITHUB_SHA", None)
 
 
 class SubprocessCallException(Exception):
     pass
 
 
-# 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`
-    """
+def run_command(command: list[str], return_stdout=False):
     try:
         output = subprocess.check_output(command, stderr=subprocess.STDOUT)
-        if return_stdout:
-            if hasattr(output, "decode"):
-                output = output.decode("utf-8")
-            return output
+        if return_stdout and hasattr(output, "decode"):
+            return output.decode("utf-8")
     except subprocess.CalledProcessError as e:
-        raise SubprocessCallException(
-            f"Command `{' '.join(command)}` failed with the following error:\n\n{e.output.decode()}"
-        ) from e
+        raise SubprocessCallException(f"Command `{' '.join(command)}` failed with:\n{e.output.decode()}") from e
 
 
-def main():
-    python_files = glob.glob(PATTERN)
+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
 
-    for file in python_files:
-        print(f"****** Running file: {file} ******")
-
-        # Run with canonical settings.
-        if file != "benchmark_text_to_image.py" and file != "benchmark_ip_adapters.py":
-            command = f"python {file}"
-            run_command(command.split())
-
-            command += " --run_compile"
-            run_command(command.split())
-
-    # Run variants.
-    for file in python_files:
-        # See: https://github.com/pytorch/pytorch/issues/129637
-        if file == "benchmark_ip_adapters.py":
+    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 file == "benchmark_text_to_image.py":
-            for ckpt in ALL_T2I_CKPTS:
-                command = f"python {file} --ckpt {ckpt}"
+    if not df_list:
+        logger.info("All result CSVs were empty or invalid; nothing to merge.")
+        return
 
-                if "turbo" in ckpt:
-                    command += " --num_inference_steps 1"
+    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}.")
 
-                run_command(command.split())
 
-                command += " --run_compile"
-                run_command(command.split())
+def run_scripts():
+    python_files = sorted(glob.glob(PATTERN))
+    python_files = [f for f in python_files if f != "benchmarking_utils.py"]
 
-        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}"
+    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} ******")
 
-                if ckpt == "stabilityai/sdxl-turbo":
-                    command += " --num_inference_steps 2"
+        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_command(command.split())
-                command += " --run_compile"
-                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)
 
-        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())
+    logger.info(f"\nAll scripts attempted. Final collated CSV: {FINAL_CSV_FILENAME}")
 
 
 if __name__ == "__main__":
-    main()
+    run_scripts()

benchmarks/utils.py

@@ -1,98 +0,0 @@
-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

@@ -47,6 +47,10 @@ RUN python3.10 -m pip install --no-cache-dir --upgrade pip uv==0.1.11 && \
         tensorboard \
         transformers \
         matplotlib \
-        setuptools==69.5.1
+        setuptools==69.5.1 \
+        bitsandbytes \
+        torchao \
+        gguf \
+        optimum-quanto
 
 CMD ["/bin/bash"]

docker/diffusers-pytorch-compile-cuda/Dockerfile

@@ -1,50 +0,0 @@
-FROM nvidia/cuda:12.1.0-runtime-ubuntu20.04
-LABEL maintainer="Hugging Face"
-LABEL repository="diffusers"
-
-ENV DEBIAN_FRONTEND=noninteractive
-
-RUN apt-get -y update \
-    && apt-get install -y software-properties-common \
-    && add-apt-repository ppa:deadsnakes/ppa
-
-RUN apt install -y bash \
-    build-essential \
-    git \
-    git-lfs \
-    curl \
-    ca-certificates \
-    libsndfile1-dev \
-    libgl1 \
-    python3.10 \
-    python3.10-dev \
-    python3-pip \
-    python3.10-venv && \
-    rm -rf /var/lib/apt/lists
-
-# make sure to use venv
-RUN python3.10 -m venv /opt/venv
-ENV PATH="/opt/venv/bin:$PATH"
-
-# pre-install the heavy dependencies (these can later be overridden by the deps from setup.py)
-RUN python3.10 -m pip install --no-cache-dir --upgrade pip uv==0.1.11 && \
-    python3.10 -m uv pip install --no-cache-dir \
-    torch \
-    torchvision \
-    torchaudio \
-    invisible_watermark && \
-    python3.10 -m pip install --no-cache-dir \
-    accelerate \
-    datasets \
-    hf-doc-builder \
-    huggingface-hub \
-    hf_transfer \
-    Jinja2 \
-    librosa \
-    numpy==1.26.4 \
-    scipy \
-    tensorboard \
-    transformers \
-    hf_transfer
-
-CMD ["/bin/bash"]

docs/TRANSLATING.md

@@ -1,4 +1,4 @@
-<!--Copyright 2024 The HuggingFace Team. All rights reserved.
+<!--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

docs/source/en/_toctree.yml

@@ -1,66 +1,63 @@
-- sections:
+- title: Get started
+  sections:
   - local: index
-    title: 🧨 Diffusers
-  - local: quicktour
-    title: Quicktour
-  - local: stable_diffusion
-    title: Effective and efficient diffusion
+    title: Diffusers
   - local: installation
     title: Installation
-  title: Get started
-- sections:
-  - local: tutorials/tutorial_overview
-    title: Overview
-  - local: using-diffusers/write_own_pipeline
-    title: Understanding pipelines, models and schedulers
-  - local: tutorials/autopipeline
-    title: AutoPipeline
-  - local: tutorials/basic_training
-    title: Train a diffusion model
-  - local: tutorials/using_peft_for_inference
-    title: Load LoRAs for inference
-  - local: tutorials/fast_diffusion
-    title: Accelerate inference of text-to-image diffusion models
-  - local: tutorials/inference_with_big_models
-    title: Working with big models
-  title: Tutorials
-- sections:
+  - local: quicktour
+    title: Quickstart
+  - local: stable_diffusion
+    title: Basic performance
+
+- title: DiffusionPipeline
+  isExpanded: false
+  sections:
   - local: using-diffusers/loading
     title: Load pipelines
+  - local: tutorials/autopipeline
+    title: AutoPipeline
   - local: using-diffusers/custom_pipeline_overview
     title: Load community pipelines and components
+  - local: using-diffusers/callback
+    title: Pipeline callbacks
+  - local: using-diffusers/reusing_seeds
+    title: Reproducible pipelines
   - local: using-diffusers/schedulers
     title: Load schedulers and models
+  - local: using-diffusers/scheduler_features
+    title: Scheduler features
   - local: using-diffusers/other-formats
     title: Model files and layouts
-  - local: using-diffusers/loading_adapters
-    title: Load adapters
   - local: using-diffusers/push_to_hub
     title: Push files to the Hub
-  title: Load pipelines and adapters
-- sections:
-  - local: using-diffusers/unconditional_image_generation
-    title: Unconditional image generation
-  - local: using-diffusers/conditional_image_generation
-    title: Text-to-image
-  - local: using-diffusers/img2img
-    title: Image-to-image
-  - local: using-diffusers/inpaint
-    title: Inpainting
-  - local: using-diffusers/text-img2vid
-    title: Video generation
-  - local: using-diffusers/depth2img
-    title: Depth-to-image
-  title: Generative tasks
-- sections:
-  - local: using-diffusers/overview_techniques
-    title: Overview
+
+- title: Adapters
+  isExpanded: false
+  sections:
+  - local: tutorials/using_peft_for_inference
+    title: LoRA
+  - local: using-diffusers/ip_adapter
+    title: IP-Adapter
+  - local: using-diffusers/controlnet
+    title: ControlNet
+  - local: using-diffusers/t2i_adapter
+    title: T2I-Adapter
+  - local: using-diffusers/dreambooth
+    title: DreamBooth
+  - local: using-diffusers/textual_inversion_inference
+    title: Textual inversion
+
+- title: Inference
+  isExpanded: false
+  sections:
+  - local: using-diffusers/weighted_prompts
+    title: Prompt techniques
   - local: using-diffusers/create_a_server
     title: Create a server
+  - local: using-diffusers/batched_inference
+    title: Batch inference
   - local: training/distributed_inference
     title: Distributed inference
-  - local: using-diffusers/merge_loras
-    title: Merge LoRAs
   - local: using-diffusers/scheduler_features
     title: Scheduler features
   - local: using-diffusers/callback
@@ -69,14 +66,38 @@
     title: Reproducible pipelines
   - local: using-diffusers/image_quality
     title: Controlling image quality
-  - local: using-diffusers/weighted_prompts
-    title: Prompt techniques
-  title: Inference techniques
-- sections:
-  - local: advanced_inference/outpaint
-    title: Outpainting
-  title: Advanced inference
-- sections:
+
+- title: Inference optimization
+  isExpanded: false
+  sections:
+  - local: optimization/fp16
+    title: Accelerate inference
+  - local: optimization/cache
+    title: Caching
+  - local: optimization/memory
+    title: Reduce memory usage
+  - local: optimization/speed-memory-optims
+    title: Compile and offloading quantized models
+  - title: Community optimizations
+    sections:
+    - local: optimization/pruna
+      title: Pruna
+    - local: optimization/xformers
+      title: xFormers
+    - local: optimization/tome
+      title: Token merging
+    - local: optimization/deepcache
+      title: DeepCache
+    - local: optimization/tgate
+      title: TGATE
+    - local: optimization/xdit
+      title: xDiT
+    - local: optimization/para_attn
+      title: ParaAttention
+
+- title: Hybrid Inference
+  isExpanded: false
+  sections:
   - local: hybrid_inference/overview
     title: Overview
   - local: hybrid_inference/vae_decode
@@ -85,51 +106,43 @@
     title: VAE Encode
   - local: hybrid_inference/api_reference
     title: API Reference
-  title: Hybrid Inference
-- sections:
-  - local: using-diffusers/cogvideox
-    title: CogVideoX
-  - local: using-diffusers/consisid
-    title: ConsisID
-  - local: using-diffusers/sdxl
-    title: Stable Diffusion XL
-  - local: using-diffusers/sdxl_turbo
-    title: SDXL Turbo
-  - local: using-diffusers/kandinsky
-    title: Kandinsky
-  - local: using-diffusers/ip_adapter
-    title: IP-Adapter
-  - local: using-diffusers/omnigen
-    title: OmniGen
-  - local: using-diffusers/pag
-    title: PAG
-  - local: using-diffusers/controlnet
-    title: ControlNet
-  - local: using-diffusers/t2i_adapter
-    title: T2I-Adapter
-  - local: using-diffusers/inference_with_lcm
-    title: Latent Consistency Model
-  - local: using-diffusers/textual_inversion_inference
-    title: Textual inversion
-  - local: using-diffusers/shap-e
-    title: Shap-E
-  - local: using-diffusers/diffedit
-    title: DiffEdit
-  - local: using-diffusers/inference_with_tcd_lora
-    title: Trajectory Consistency Distillation-LoRA
-  - local: using-diffusers/svd
-    title: Stable Video Diffusion
-  - local: using-diffusers/marigold_usage
-    title: Marigold Computer Vision
-  title: Specific pipeline examples
-- sections:
+
+- title: Modular Diffusers
+  isExpanded: false
+  sections:
+  - local: modular_diffusers/overview
+    title: Overview
+  - local: modular_diffusers/quickstart
+    title: Quickstart
+  - local: modular_diffusers/modular_diffusers_states
+    title: States
+  - local: modular_diffusers/pipeline_block
+    title: ModularPipelineBlocks
+  - local: modular_diffusers/sequential_pipeline_blocks
+    title: SequentialPipelineBlocks
+  - local: modular_diffusers/loop_sequential_pipeline_blocks
+    title: LoopSequentialPipelineBlocks
+  - local: modular_diffusers/auto_pipeline_blocks
+    title: AutoPipelineBlocks
+  - local: modular_diffusers/modular_pipeline
+    title: ModularPipeline
+  - local: modular_diffusers/components_manager
+    title: ComponentsManager
+  - local: modular_diffusers/guiders
+    title: Guiders
+
+- title: Training
+  isExpanded: false
+  sections:
   - local: training/overview
     title: Overview
   - local: training/create_dataset
     title: Create a dataset for training
   - local: training/adapt_a_model
     title: Adapt a model to a new task
-  - isExpanded: false
+  - local: tutorials/basic_training
+    title: Train a diffusion model
+  - title: Models
     sections:
     - local: training/unconditional_training
       title: Unconditional image generation
@@ -149,8 +162,7 @@
       title: InstructPix2Pix
     - local: training/cogvideox
       title: CogVideoX
-    title: Models
-  - isExpanded: false
+  - title: Methods
     sections:
     - local: training/text_inversion
       title: Textual Inversion
@@ -164,11 +176,12 @@
       title: Latent Consistency Distillation
     - local: training/ddpo
       title: Reinforcement learning training with DDPO
-    title: Methods
-  title: Training
-- sections:
+
+- title: Quantization
+  isExpanded: false
+  sections:
   - local: quantization/overview
-    title: Getting Started
+    title: Getting started
   - local: quantization/bitsandbytes
     title: bitsandbytes
   - local: quantization/gguf
@@ -177,46 +190,76 @@
     title: torchao
   - local: quantization/quanto
     title: quanto
-  title: Quantization Methods
-- sections:
-  - local: optimization/fp16
-    title: Speed up inference
-  - local: optimization/memory
-    title: Reduce memory usage
-  - local: optimization/torch2.0
-    title: PyTorch 2.0
-  - local: optimization/xformers
-    title: xFormers
-  - local: optimization/tome
-    title: Token merging
-  - local: optimization/deepcache
-    title: DeepCache
-  - local: optimization/tgate
-    title: TGATE
-  - local: optimization/xdit
-    title: xDiT
-  - local: optimization/para_attn
-    title: ParaAttention
-  - sections:
-    - local: using-diffusers/stable_diffusion_jax_how_to
-      title: JAX/Flax
-    - local: optimization/onnx
-      title: ONNX
-    - local: optimization/open_vino
-      title: OpenVINO
-    - local: optimization/coreml
-      title: Core ML
-    title: Optimized model formats
-  - sections:
-    - local: optimization/mps
-      title: Metal Performance Shaders (MPS)
-    - local: optimization/habana
-      title: Habana Gaudi
-    - local: optimization/neuron
-      title: AWS Neuron
-    title: Optimized hardware
-  title: Accelerate inference and reduce memory
-- sections:
+
+- title: Model accelerators and hardware
+  isExpanded: false
+  sections:
+  - local: using-diffusers/stable_diffusion_jax_how_to
+    title: JAX/Flax
+  - local: optimization/onnx
+    title: ONNX
+  - local: optimization/open_vino
+    title: OpenVINO
+  - local: optimization/coreml
+    title: Core ML
+  - local: optimization/mps
+    title: Metal Performance Shaders (MPS)
+  - local: optimization/habana
+    title: Intel Gaudi
+  - local: optimization/neuron
+    title: AWS Neuron
+
+- title: Specific pipeline examples
+  isExpanded: false
+  sections:
+  - local: using-diffusers/consisid
+    title: ConsisID
+  - local: using-diffusers/sdxl
+    title: Stable Diffusion XL
+  - local: using-diffusers/sdxl_turbo
+    title: SDXL Turbo
+  - local: using-diffusers/kandinsky
+    title: Kandinsky
+  - local: using-diffusers/omnigen
+    title: OmniGen
+  - local: using-diffusers/pag
+    title: PAG
+  - local: using-diffusers/inference_with_lcm
+    title: Latent Consistency Model
+  - local: using-diffusers/shap-e
+    title: Shap-E
+  - local: using-diffusers/diffedit
+    title: DiffEdit
+  - local: using-diffusers/inference_with_tcd_lora
+    title: Trajectory Consistency Distillation-LoRA
+  - local: using-diffusers/svd
+    title: Stable Video Diffusion
+  - local: using-diffusers/marigold_usage
+    title: Marigold Computer Vision
+
+- title: Resources
+  isExpanded: false
+  sections:
+  - title: Task recipes
+    sections:
+    - local: using-diffusers/unconditional_image_generation
+      title: Unconditional image generation
+    - local: using-diffusers/conditional_image_generation
+      title: Text-to-image
+    - local: using-diffusers/img2img
+      title: Image-to-image
+    - local: using-diffusers/inpaint
+      title: Inpainting
+    - local: advanced_inference/outpaint
+      title: Outpainting
+    - local: using-diffusers/text-img2vid
+      title: Video generation
+    - local: using-diffusers/depth2img
+      title: Depth-to-image
+  - local: using-diffusers/write_own_pipeline
+    title: Understanding pipelines, models and schedulers
+  - local: community_projects
+    title: Projects built with Diffusers
   - local: conceptual/philosophy
     title: Philosophy
   - local: using-diffusers/controlling_generation
@@ -227,13 +270,11 @@
     title: Diffusers' Ethical Guidelines
   - local: conceptual/evaluation
     title: Evaluating Diffusion Models
-  title: Conceptual Guides
-- sections:
-  - local: community_projects
-    title: Projects built with Diffusers
-  title: Community Projects
-- sections:
-  - isExpanded: false
+
+- title: API
+  isExpanded: false
+  sections:
+  - title: Main Classes
     sections:
     - local: api/configuration
       title: Configuration
@@ -243,8 +284,19 @@
       title: Outputs
     - local: api/quantization
       title: Quantization
-    title: Main Classes
-  - isExpanded: false
+  - title: Modular
+    sections:
+    - local: api/modular_diffusers/pipeline
+      title: Pipeline
+    - local: api/modular_diffusers/pipeline_blocks
+      title: Blocks
+    - local: api/modular_diffusers/pipeline_states
+      title: States
+    - local: api/modular_diffusers/pipeline_components
+      title: Components and configs
+    - local: api/modular_diffusers/guiders
+      title: Guiders
+  - title: Loaders
     sections:
     - local: api/loaders/ip_adapter
       title: IP-Adapter
@@ -260,14 +312,14 @@
       title: SD3Transformer2D
     - local: api/loaders/peft
       title: PEFT
-    title: Loaders
-  - isExpanded: false
+  - title: Models
     sections:
     - local: api/models/overview
       title: Overview
     - local: api/models/auto_model
       title: AutoModel
-    - sections:
+    - title: ControlNets
+      sections:
       - local: api/models/controlnet
         title: ControlNetModel
       - local: api/models/controlnet_union
@@ -282,12 +334,14 @@
         title: SD3ControlNetModel
       - local: api/models/controlnet_sparsectrl
         title: SparseControlNetModel
-      title: ControlNets
-    - sections:
+    - title: Transformers
+      sections:
       - local: api/models/allegro_transformer3d
         title: AllegroTransformer3DModel
       - local: api/models/aura_flow_transformer2d
         title: AuraFlowTransformer2DModel
+      - local: api/models/chroma_transformer
+        title: ChromaTransformer2DModel
       - local: api/models/cogvideox_transformer3d
         title: CogVideoXTransformer3DModel
       - local: api/models/cogview3plus_transformer2d
@@ -296,6 +350,8 @@
         title: CogView4Transformer2DModel
       - local: api/models/consisid_transformer3d
         title: ConsisIDTransformer3DModel
+      - local: api/models/cosmos_transformer3d
+        title: CosmosTransformer3DModel
       - local: api/models/dit_transformer2d
         title: DiTTransformer2DModel
       - local: api/models/easyanimate_transformer3d
@@ -324,10 +380,14 @@
         title: PixArtTransformer2DModel
       - local: api/models/prior_transformer
         title: PriorTransformer
+      - local: api/models/qwenimage_transformer2d
+        title: QwenImageTransformer2DModel
       - local: api/models/sana_transformer2d
         title: SanaTransformer2DModel
       - local: api/models/sd3_transformer2d
         title: SD3Transformer2DModel
+      - local: api/models/skyreels_v2_transformer_3d
+        title: SkyReelsV2Transformer3DModel
       - local: api/models/stable_audio_transformer
         title: StableAudioDiTModel
       - local: api/models/transformer2d
@@ -336,8 +396,8 @@
         title: TransformerTemporalModel
       - local: api/models/wan_transformer_3d
         title: WanTransformer3DModel
-      title: Transformers
-    - sections:
+    - title: UNets
+      sections:
       - local: api/models/stable_cascade_unet
         title: StableCascadeUNet
       - local: api/models/unet
@@ -352,8 +412,8 @@
         title: UNetMotionModel
       - local: api/models/uvit2d
         title: UViT2DModel
-      title: UNets
-    - sections:
+    - title: VAEs
+      sections:
       - local: api/models/asymmetricautoencoderkl
         title: AsymmetricAutoencoderKL
       - local: api/models/autoencoder_dc
@@ -364,6 +424,8 @@
         title: AutoencoderKLAllegro
       - local: api/models/autoencoderkl_cogvideox
         title: AutoencoderKLCogVideoX
+      - local: api/models/autoencoderkl_cosmos
+        title: AutoencoderKLCosmos
       - local: api/models/autoencoder_kl_hunyuan_video
         title: AutoencoderKLHunyuanVideo
       - local: api/models/autoencoderkl_ltx_video
@@ -372,6 +434,8 @@
         title: AutoencoderKLMagvit
       - local: api/models/autoencoderkl_mochi
         title: AutoencoderKLMochi
+      - local: api/models/autoencoderkl_qwenimage
+        title: AutoencoderKLQwenImage
       - local: api/models/autoencoder_kl_wan
         title: AutoencoderKLWan
       - local: api/models/consistency_decoder_vae
@@ -382,9 +446,7 @@
         title: Tiny AutoEncoder
       - local: api/models/vq
         title: VQModel
-      title: VAEs
-    title: Models
-  - isExpanded: false
+  - title: Pipelines
     sections:
     - local: api/pipelines/overview
       title: Overview
@@ -406,6 +468,8 @@
       title: AutoPipeline
     - local: api/pipelines/blip_diffusion
       title: BLIP-Diffusion
+    - local: api/pipelines/chroma
+      title: Chroma
     - local: api/pipelines/cogvideox
       title: CogVideoX
     - local: api/pipelines/cogview3
@@ -434,6 +498,8 @@
       title: ControlNet-XS with Stable Diffusion XL
     - local: api/pipelines/controlnet_union
       title: ControlNetUnion
+    - local: api/pipelines/cosmos
+      title: Cosmos
     - local: api/pipelines/dance_diffusion
       title: Dance Diffusion
     - local: api/pipelines/ddim
@@ -452,6 +518,8 @@
       title: Flux
     - local: api/pipelines/control_flux_inpaint
       title: FluxControlInpaint
+    - local: api/pipelines/framepack
+      title: Framepack
     - local: api/pipelines/hidream
       title: HiDream-I1
     - local: api/pipelines/hunyuandit
@@ -504,6 +572,8 @@
       title: PixArt-α
     - local: api/pipelines/pixart_sigma
       title: PixArt-Σ
+    - local: api/pipelines/qwenimage
+      title: QwenImage
     - local: api/pipelines/sana
       title: Sana
     - local: api/pipelines/sana_sprint
@@ -514,11 +584,14 @@
       title: Semantic Guidance
     - local: api/pipelines/shap_e
       title: Shap-E
+    - local: api/pipelines/skyreels_v2
+      title: SkyReels-V2
     - local: api/pipelines/stable_audio
       title: Stable Audio
     - local: api/pipelines/stable_cascade
       title: Stable Cascade
-    - sections:
+    - title: Stable Diffusion
+      sections:
       - local: api/pipelines/stable_diffusion/overview
         title: Overview
       - local: api/pipelines/stable_diffusion/depth2img
@@ -555,7 +628,6 @@
         title: T2I-Adapter
       - local: api/pipelines/stable_diffusion/text2img
         title: Text-to-image
-      title: Stable Diffusion
     - local: api/pipelines/stable_unclip
       title: Stable unCLIP
     - local: api/pipelines/text_to_video
@@ -568,12 +640,13 @@
       title: UniDiffuser
     - local: api/pipelines/value_guided_sampling
       title: Value-guided sampling
+    - local: api/pipelines/visualcloze
+      title: VisualCloze
     - local: api/pipelines/wan
       title: Wan
     - local: api/pipelines/wuerstchen
       title: Wuerstchen
-    title: Pipelines
-  - isExpanded: false
+  - title: Schedulers
     sections:
     - local: api/schedulers/overview
       title: Overview
@@ -643,8 +716,7 @@
       title: UniPCMultistepScheduler
     - local: api/schedulers/vq_diffusion
       title: VQDiffusionScheduler
-    title: Schedulers
-  - isExpanded: false
+  - title: Internal classes
     sections:
     - local: api/internal_classes_overview
       title: Overview
@@ -662,5 +734,3 @@
       title: VAE Image Processor
     - local: api/video_processor
       title: Video Processor
-    title: Internal classes
-  title: API

docs/source/en/advanced_inference/outpaint.md

@@ -1,4 +1,4 @@
-<!--Copyright 2024 The HuggingFace Team. All rights reserved.
+<!--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

docs/source/en/api/activations.md

@@ -1,4 +1,4 @@
-<!--Copyright 2024 The HuggingFace Team. All rights reserved.
+<!--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

docs/source/en/api/attnprocessor.md

@@ -1,4 +1,4 @@
-<!--Copyright 2024 The HuggingFace Team. All rights reserved.
+<!--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

docs/source/en/api/cache.md

@@ -1,4 +1,4 @@
-<!-- Copyright 2024 The HuggingFace Team. All rights reserved.
+<!-- 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
@@ -11,72 +11,26 @@ specific language governing permissions and limitations under the License. -->
 
 # Caching methods
 
-## Pyramid Attention Broadcast
+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.
 
-[Pyramid Attention Broadcast](https://huggingface.co/papers/2408.12588) from Xuanlei Zhao, Xiaolong Jin, Kai Wang, Yang You.
-
-Pyramid Attention Broadcast (PAB) is a method that speeds up inference in diffusion models by systematically skipping attention computations between successive inference steps and reusing cached attention states. The attention states are not very different between successive inference steps. The most prominent difference is in the spatial attention blocks, not as much in the temporal attention blocks, and finally the least in the cross attention blocks. Therefore, many cross attention computation blocks can be skipped, followed by the temporal and spatial attention blocks. By combining other techniques like sequence parallelism and classifier-free guidance parallelism, PAB achieves near real-time video generation.
-
-Enable PAB with [`~PyramidAttentionBroadcastConfig`] on any pipeline. For some benchmarks, refer to [this](https://github.com/huggingface/diffusers/pull/9562) pull request.
-
-```python
-import torch
-from diffusers import CogVideoXPipeline, PyramidAttentionBroadcastConfig
-
-pipe = CogVideoXPipeline.from_pretrained("THUDM/CogVideoX-5b", torch_dtype=torch.bfloat16)
-pipe.to("cuda")
-
-# Increasing the value of `spatial_attention_timestep_skip_range[0]` or decreasing the value of
-# `spatial_attention_timestep_skip_range[1]` will decrease the interval in which pyramid attention
-# broadcast is active, leader to slower inference speeds. However, large intervals can lead to
-# poorer quality of generated videos.
-config = PyramidAttentionBroadcastConfig(
-    spatial_attention_block_skip_range=2,
-    spatial_attention_timestep_skip_range=(100, 800),
-    current_timestep_callback=lambda: pipe.current_timestep,
-)
-pipe.transformer.enable_cache(config)
-```
-
-## Faster Cache
-
-[FasterCache](https://huggingface.co/papers/2410.19355) from Zhengyao Lv, Chenyang Si, Junhao Song, Zhenyu Yang, Yu Qiao, Ziwei Liu, Kwan-Yee K. Wong.
-
-FasterCache is a method that speeds up inference in diffusion transformers by:
-- Reusing attention states between successive inference steps, due to high similarity between them
-- Skipping unconditional branch prediction used in classifier-free guidance by revealing redundancies between unconditional and conditional branch outputs for the same timestep, and therefore approximating the unconditional branch output using the conditional branch output
-
-```python
-import torch
-from diffusers import CogVideoXPipeline, FasterCacheConfig
-
-pipe = CogVideoXPipeline.from_pretrained("THUDM/CogVideoX-5b", torch_dtype=torch.bfloat16)
-pipe.to("cuda")
-
-config = FasterCacheConfig(
-    spatial_attention_block_skip_range=2,
-    spatial_attention_timestep_skip_range=(-1, 681),
-    current_timestep_callback=lambda: pipe.current_timestep,
-    attention_weight_callback=lambda _: 0.3,
-    unconditional_batch_skip_range=5,
-    unconditional_batch_timestep_skip_range=(-1, 781),
-    tensor_format="BFCHW",
-)
-pipe.transformer.enable_cache(config)
-```
-
-### CacheMixin
+## CacheMixin
 
 [[autodoc]] CacheMixin
 
-### PyramidAttentionBroadcastConfig
+## PyramidAttentionBroadcastConfig
 
 [[autodoc]] PyramidAttentionBroadcastConfig
 
 [[autodoc]] apply_pyramid_attention_broadcast
 
-### FasterCacheConfig
+## 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 2024 The HuggingFace Team. All rights reserved.
+<!--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
@@ -16,7 +16,7 @@ Schedulers from [`~schedulers.scheduling_utils.SchedulerMixin`] and models from
 
 <Tip>
 
-To use private or [gated](https://huggingface.co/docs/hub/models-gated#gated-models) models, log-in with `huggingface-cli login`.
+To use private or [gated](https://huggingface.co/docs/hub/models-gated#gated-models) models, log-in with `hf auth login`.
 
 </Tip>
 

docs/source/en/api/image_processor.md

@@ -1,4 +1,4 @@
-<!--Copyright 2024 The HuggingFace Team. All rights reserved.
+<!--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

docs/source/en/api/internal_classes_overview.md

@@ -1,4 +1,4 @@
-<!--Copyright 2024 The HuggingFace Team. All rights reserved.
+<!--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

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

@@ -1,4 +1,4 @@
-<!--Copyright 2024 The HuggingFace Team. All rights reserved.
+<!--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

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

@@ -1,4 +1,4 @@
-<!--Copyright 2024 The HuggingFace Team. All rights reserved.
+<!--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
@@ -26,9 +26,11 @@ LoRA is a fast and lightweight training method that inserts and trains a signifi
 - [`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)
 - [`LoraBaseMixin`] provides a base class with several utility methods to fuse, unfuse, unload, LoRAs and more.
 
 <Tip>
@@ -37,6 +39,10 @@ To learn more about how to load LoRA weights, see the [LoRA](../../using-diffuse
 
 </Tip>
 
+## LoraBaseMixin
+
+[[autodoc]] loaders.lora_base.LoraBaseMixin
+
 ## StableDiffusionLoraLoaderMixin
 
 [[autodoc]] loaders.lora_pipeline.StableDiffusionLoraLoaderMixin
@@ -88,6 +94,10 @@ To learn more about how to load LoRA weights, see the [LoRA](../../using-diffuse
 
 [[autodoc]] loaders.lora_pipeline.WanLoraLoaderMixin
 
+## SkyReelsV2LoraLoaderMixin
+
+[[autodoc]] loaders.lora_pipeline.SkyReelsV2LoraLoaderMixin
+
 ## AmusedLoraLoaderMixin
 
 [[autodoc]] loaders.lora_pipeline.AmusedLoraLoaderMixin
@@ -96,6 +106,10 @@ To learn more about how to load LoRA weights, see the [LoRA](../../using-diffuse
 
 [[autodoc]] loaders.lora_pipeline.HiDreamImageLoraLoaderMixin
 
+## QwenImageLoraLoaderMixin
+
+[[autodoc]] loaders.lora_pipeline.QwenImageLoraLoaderMixin
+
 ## LoraBaseMixin
 
 [[autodoc]] loaders.lora_base.LoraBaseMixin

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

@@ -1,4 +1,4 @@
-<!--Copyright 2024 The HuggingFace Team. All rights reserved.
+<!--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

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

@@ -1,4 +1,4 @@
-<!--Copyright 2024 The HuggingFace Team. All rights reserved.
+<!--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

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

@@ -1,4 +1,4 @@
-<!--Copyright 2024 The HuggingFace Team. All rights reserved.
+<!--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

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

@@ -1,4 +1,4 @@
-<!--Copyright 2024 The HuggingFace Team. All rights reserved.
+<!--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

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

@@ -1,4 +1,4 @@
-<!--Copyright 2024 The HuggingFace Team. All rights reserved.
+<!--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

docs/source/en/api/logging.md

@@ -1,4 +1,4 @@
-<!--Copyright 2024 The HuggingFace Team. All rights reserved.
+<!--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

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

@@ -1,4 +1,4 @@
-<!-- Copyright 2024 The HuggingFace Team. All rights reserved.
+<!-- 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

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

@@ -1,4 +1,4 @@
-<!--Copyright 2024 The HuggingFace Team. All rights reserved.
+<!--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
@@ -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://arxiv.org/abs/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://huggingface.co/papers/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:
 

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

@@ -1,4 +1,4 @@
-<!--Copyright 2024 The HuggingFace Team. All rights reserved.
+<!--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

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

@@ -1,4 +1,4 @@
-<!--Copyright 2024 The HuggingFace Team. All rights reserved.
+<!--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

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

@@ -1,4 +1,4 @@
-<!-- Copyright 2024 The HuggingFace Team. All rights reserved.
+<!-- 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

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

@@ -1,4 +1,4 @@
-<!-- Copyright 2024 The HuggingFace Team. All rights reserved.
+<!-- 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

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

@@ -1,4 +1,4 @@
-<!-- Copyright 2024 The HuggingFace Team. All rights reserved.
+<!-- 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

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

@@ -1,4 +1,4 @@
-<!--Copyright 2024 The HuggingFace Team. All rights reserved.
+<!--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

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

@@ -1,4 +1,4 @@
-<!--Copyright 2024 The HuggingFace Team. All rights reserved.
+<!--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

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

@@ -1,4 +1,4 @@
-<!--Copyright 2024 The HuggingFace Team. All rights reserved.
+<!--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
@@ -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://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 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 abstract from the paper is:
 

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

@@ -1,4 +1,4 @@
-<!-- Copyright 2024 The HuggingFace Team. All rights reserved.
+<!-- 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

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

@@ -1,4 +1,4 @@
-<!--Copyright 2024 The HuggingFace Team. All rights reserved.
+<!--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

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

@@ -0,0 +1,40 @@
+<!-- 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

@@ -1,4 +1,4 @@
-<!-- Copyright 2024 The HuggingFace Team. All rights reserved.
+<!-- 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

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

@@ -1,4 +1,4 @@
-<!-- Copyright 2024 The HuggingFace Team. All rights reserved.
+<!-- 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

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

@@ -0,0 +1,35 @@
+<!-- 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. -->
+
+# AutoencoderKLQwenImage
+
+The model can be loaded with the following code snippet.
+
+```python
+from diffusers import AutoencoderKLQwenImage
+
+vae = AutoencoderKLQwenImage.from_pretrained("Qwen/QwenImage-20B", subfolder="vae")
+```
+
+## AutoencoderKLQwenImage
+
+[[autodoc]] AutoencoderKLQwenImage
+    - decode
+    - encode
+    - all
+
+## AutoencoderKLOutput
+
+[[autodoc]] models.autoencoders.autoencoder_kl.AutoencoderKLOutput
+
+## DecoderOutput
+
+[[autodoc]] models.autoencoders.vae.DecoderOutput

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

@@ -0,0 +1,19 @@
+<!--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.
+-->
+
+# ChromaTransformer2DModel
+
+A modified flux Transformer model from [Chroma](https://huggingface.co/lodestones/Chroma)
+
+## ChromaTransformer2DModel
+
+[[autodoc]] ChromaTransformer2DModel

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

@@ -1,4 +1,4 @@
-<!--Copyright 2024 The HuggingFace Team. All rights reserved.
+<!--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

docs/source/en/api/models/cogview3plus_transformer2d.md

@@ -1,4 +1,4 @@
-<!--Copyright 2024 The HuggingFace Team. All rights reserved.
+<!--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

docs/source/en/api/models/cogview4_transformer2d.md

@@ -1,4 +1,4 @@
-<!--Copyright 2024 The HuggingFace Team. All rights reserved.
+<!--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

docs/source/en/api/models/consisid_transformer3d.md

@@ -1,4 +1,4 @@
-<!--Copyright 2024 The HuggingFace Team. All rights reserved.
+<!--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
@@ -11,7 +11,7 @@ specific language governing permissions and limitations under the License. -->
 
 # ConsisIDTransformer3DModel
 
-A Diffusion Transformer model for 3D data from [ConsisID](https://github.com/PKU-YuanGroup/ConsisID) was introduced in [Identity-Preserving Text-to-Video Generation by Frequency Decomposition](https://arxiv.org/pdf/2411.17440) by Peking University & University of Rochester & etc.
+A Diffusion Transformer model for 3D data from [ConsisID](https://github.com/PKU-YuanGroup/ConsisID) was introduced in [Identity-Preserving Text-to-Video Generation by Frequency Decomposition](https://huggingface.co/papers/2411.17440) by Peking University & University of Rochester & etc.
 
 The model can be loaded with the following code snippet.
 

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

@@ -1,4 +1,4 @@
-<!--Copyright 2024 The HuggingFace Team. All rights reserved.
+<!--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

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

@@ -1,4 +1,4 @@
-<!--Copyright 2024 The HuggingFace Team. All rights reserved.
+<!--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

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

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

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

@@ -1,4 +1,4 @@
-<!--Copyright 2024 The HuggingFace Team and Tencent Hunyuan Team. All rights reserved.
+<!--Copyright 2025 The HuggingFace Team and Tencent Hunyuan Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at
@@ -12,7 +12,7 @@ specific language governing permissions and limitations under the License.
 
 # HunyuanDiT2DControlNetModel
 
-HunyuanDiT2DControlNetModel is an implementation of ControlNet for [Hunyuan-DiT](https://arxiv.org/abs/2405.08748).
+HunyuanDiT2DControlNetModel is an implementation of ControlNet for [Hunyuan-DiT](https://huggingface.co/papers/2405.08748).
 
 ControlNet was introduced in [Adding Conditional Control to Text-to-Image Diffusion Models](https://huggingface.co/papers/2302.05543) by Lvmin Zhang, Anyi Rao, and Maneesh Agrawala.
 

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

@@ -1,4 +1,4 @@
-<!--Copyright 2024 The HuggingFace Team. All rights reserved.
+<!--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

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

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

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

@@ -1,4 +1,4 @@
-<!-- Copyright 2024 The HuggingFace Team. All rights reserved.
+<!-- 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
@@ -11,11 +11,11 @@ specific language governing permissions and limitations under the License. -->
 
 # SparseControlNetModel
 
-SparseControlNetModel is an implementation of ControlNet for [AnimateDiff](https://arxiv.org/abs/2307.04725).
+SparseControlNetModel is an implementation of ControlNet for [AnimateDiff](https://huggingface.co/papers/2307.04725).
 
 ControlNet was introduced in [Adding Conditional Control to Text-to-Image Diffusion Models](https://huggingface.co/papers/2302.05543) by Lvmin Zhang, Anyi Rao, and Maneesh Agrawala.
 
-The SparseCtrl version of ControlNet was introduced in [SparseCtrl: Adding Sparse Controls to Text-to-Video Diffusion Models](https://arxiv.org/abs/2311.16933) for achieving controlled generation in text-to-video diffusion models by Yuwei Guo, Ceyuan Yang, Anyi Rao, Maneesh Agrawala, Dahua Lin, and Bo Dai.
+The SparseCtrl version of ControlNet was introduced in [SparseCtrl: Adding Sparse Controls to Text-to-Video Diffusion Models](https://huggingface.co/papers/2311.16933) for achieving controlled generation in text-to-video diffusion models by Yuwei Guo, Ceyuan Yang, Anyi Rao, Maneesh Agrawala, Dahua Lin, and Bo Dai.
 
 The abstract from the paper is:
 

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

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

docs/source/en/api/models/cosmos_transformer3d.md

@@ -0,0 +1,30 @@
+<!-- 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. -->
+
+# CosmosTransformer3DModel
+
+A Diffusion Transformer model for 3D video-like data was introduced in [Cosmos World Foundation Model Platform for Physical AI](https://huggingface.co/papers/2501.03575) by NVIDIA.
+
+The model can be loaded with the following code snippet.
+
+```python
+from diffusers import CosmosTransformer3DModel
+
+transformer = CosmosTransformer3DModel.from_pretrained("nvidia/Cosmos-1.0-Diffusion-7B-Text2World", subfolder="transformer", torch_dtype=torch.bfloat16)
+```
+
+## CosmosTransformer3DModel
+
+[[autodoc]] CosmosTransformer3DModel
+
+## Transformer2DModelOutput
+
+[[autodoc]] models.modeling_outputs.Transformer2DModelOutput

docs/source/en/api/models/dit_transformer2d.md

@@ -1,4 +1,4 @@
-<!--Copyright 2024 The HuggingFace Team. All rights reserved.
+<!--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

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

@@ -1,4 +1,4 @@
-<!--Copyright 2024 The HuggingFace Team. All rights reserved.
+<!--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

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

@@ -1,4 +1,4 @@
-<!-- Copyright 2024 The HuggingFace Team. All rights reserved.
+<!-- 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
@@ -21,6 +21,22 @@ from diffusers import HiDreamImageTransformer2DModel
 transformer = HiDreamImageTransformer2DModel.from_pretrained("HiDream-ai/HiDream-I1-Full", subfolder="transformer", torch_dtype=torch.bfloat16)
 ```
 
+## Loading GGUF quantized checkpoints for HiDream-I1
+
+GGUF checkpoints for the `HiDreamImageTransformer2DModel` can  be loaded using `~FromOriginalModelMixin.from_single_file`
+
+```python
+import torch
+from diffusers import GGUFQuantizationConfig, HiDreamImageTransformer2DModel
+
+ckpt_path = "https://huggingface.co/city96/HiDream-I1-Dev-gguf/blob/main/hidream-i1-dev-Q2_K.gguf"
+transformer = HiDreamImageTransformer2DModel.from_single_file(
+    ckpt_path,
+    quantization_config=GGUFQuantizationConfig(compute_dtype=torch.bfloat16),
+    torch_dtype=torch.bfloat16
+)
+```
+
 ## HiDreamImageTransformer2DModel
 
 [[autodoc]] HiDreamImageTransformer2DModel

docs/source/en/api/models/hunyuan_transformer2d.md

@@ -1,4 +1,4 @@
-<!--Copyright 2024 The HuggingFace Team. All rights reserved.
+<!--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

docs/source/en/api/models/hunyuan_video_transformer_3d.md

@@ -1,4 +1,4 @@
-<!-- Copyright 2024 The HuggingFace Team. All rights reserved.
+<!-- 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

docs/source/en/api/models/latte_transformer3d.md

@@ -1,4 +1,4 @@
-<!--Copyright 2024 The HuggingFace Team. All rights reserved.
+<!--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

docs/source/en/api/models/ltx_video_transformer3d.md

@@ -1,4 +1,4 @@
-<!-- Copyright 2024 The HuggingFace Team. All rights reserved.
+<!-- 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

docs/source/en/api/models/lumina2_transformer2d.md

@@ -1,4 +1,4 @@
-<!-- Copyright 2024 The HuggingFace Team. All rights reserved.
+<!-- 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

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

@@ -1,4 +1,4 @@
-<!--Copyright 2024 The HuggingFace Team. All rights reserved.
+<!--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

docs/source/en/api/models/mochi_transformer3d.md

@@ -1,4 +1,4 @@
-<!-- Copyright 2024 The HuggingFace Team. All rights reserved.
+<!-- 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

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

@@ -1,4 +1,4 @@
-<!--Copyright 2024 The HuggingFace Team. All rights reserved.
+<!--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

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

@@ -1,4 +1,4 @@
-<!--Copyright 2024 The HuggingFace Team. All rights reserved.
+<!--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

docs/source/en/api/models/pixart_transformer2d.md

@@ -1,4 +1,4 @@
-<!--Copyright 2024 The HuggingFace Team. All rights reserved.
+<!--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

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

@@ -1,4 +1,4 @@
-<!--Copyright 2024 The HuggingFace Team. All rights reserved.
+<!--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

docs/source/en/api/models/qwenimage_transformer2d.md

@@ -0,0 +1,28 @@
+<!-- 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. -->
+
+# QwenImageTransformer2DModel
+
+The model can be loaded with the following code snippet.
+
+```python
+from diffusers import QwenImageTransformer2DModel
+
+transformer = QwenImageTransformer2DModel.from_pretrained("Qwen/QwenImage-20B", subfolder="transformer", torch_dtype=torch.bfloat16)
+```
+
+## QwenImageTransformer2DModel
+
+[[autodoc]] QwenImageTransformer2DModel
+
+## Transformer2DModelOutput
+
+[[autodoc]] models.modeling_outputs.Transformer2DModelOutput