update

This reverts commit 3fe4ad67d5.

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

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

.github/workflows/benchmark.yml

@@ -23,7 +23,7 @@ jobs:
     runs-on:
       group: aws-g6-4xlarge-plus
     container:
-      image: diffusers/diffusers-pytorch-compile-cuda
+      image: diffusers/diffusers-pytorch-cuda
       options: --shm-size "16gb" --ipc host --gpus 0
     steps:
       - name: Checkout diffusers
@@ -38,6 +38,7 @@ jobs:
           python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
           python -m uv pip install -e [quality,test]
           python -m uv pip install pandas peft
+          python -m uv pip uninstall transformers && python -m uv pip install transformers==4.48.0
       - name: Environment
         run: |
           python utils/print_env.py

.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")
@@ -65,7 +72,7 @@ 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

.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:
@@ -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
@@ -174,11 +170,48 @@ jobs:
         name: torch_${{ matrix.module }}_cuda_test_reports
         path: reports
 
-    - name: Generate Report and Notify Channel
-      if: always()
+  run_torch_compile_tests:
+    name: PyTorch Compile CUDA tests
+
+    runs-on:
+      group: aws-g4dn-2xlarge
+
+    container:
+      image: diffusers/diffusers-pytorch-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: |
-        pip install slack_sdk tabulate
-        python utils/log_reports.py >> $GITHUB_STEP_SUMMARY
+        nvidia-smi
+    - name: Install dependencies
+      run: |
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+        python -m uv pip install -e [quality,test,training]
+    - name: Environment
+      run: |
+        python utils/print_env.py
+    - name: Run torch compile tests on GPU
+      env:
+        HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
+        RUN_COMPILE: yes
+      run: |
+        python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile -s -v -k "compile" --make-reports=tests_torch_compile_cuda tests/
+    - name: Failure short reports
+      if: ${{ failure() }}
+      run: cat reports/tests_torch_compile_cuda_failures_short.txt
+
+    - name: Test suite reports artifacts
+      if: ${{ always() }}
+      uses: actions/upload-artifact@v4
+      with:
+        name: torch_compile_test_reports
+        path: reports
 
   run_big_gpu_torch_tests:
     name: Torch tests on big GPU
@@ -230,12 +263,7 @@ 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:
@@ -265,7 +293,7 @@ jobs:
 
       - name: Run PyTorch CUDA tests
         env:
-          HF_TOKEN: ${{ secrets.HF_TOKEN }}
+          HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
           # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
           CUBLAS_WORKSPACE_CONFIG: :16:8
         run: |
@@ -292,7 +320,171 @@ jobs:
         with:
           name: torch_minimum_version_cuda_test_reports
           path: reports
- 
+
+  run_nightly_onnx_tests:
+    name: Nightly ONNXRuntime CUDA tests on Ubuntu
+    runs-on:
+      group: aws-g4dn-2xlarge
+    container:
+      image: diffusers/diffusers-onnxruntime-cuda
+      options: --gpus 0 --shm-size "16gb" --ipc host
+
+    steps:
+    - name: Checkout diffusers
+      uses: actions/checkout@v3
+      with:
+        fetch-depth: 2
+
+    - name: NVIDIA-SMI
+      run: nvidia-smi
+
+    - name: Install dependencies
+      run: |
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$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: ${{ always() }}
+      uses: actions/upload-artifact@v4
+      with:
+        name: tests_onnx_cuda_reports
+        path: reports
+
+  run_nightly_quantization_tests:
+    name: Torch quantization nightly tests
+    strategy:
+      fail-fast: false
+      max-parallel: 2
+      matrix:
+        config:
+          - backend: "bitsandbytes"
+            test_location: "bnb"
+            additional_deps: ["peft"]
+          - backend: "gguf"
+            test_location: "gguf"
+            additional_deps: ["peft"]
+          - backend: "torchao"
+            test_location: "torchao"
+            additional_deps: []
+          - backend: "optimum_quanto"
+            test_location: "quanto"
+            additional_deps: []
+    runs-on:
+      group: aws-g6e-xlarge-plus
+    container:
+      image: diffusers/diffusers-pytorch-cuda
+      options: --shm-size "20gb" --ipc host --gpus 0
+    steps:
+      - name: Checkout diffusers
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 2
+      - name: NVIDIA-SMI
+        run: nvidia-smi
+      - name: Install dependencies
+        run: |
+          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+          python -m uv pip install -e [quality,test]
+          python -m uv pip install -U ${{ matrix.config.backend }}
+          if [ "${{ join(matrix.config.additional_deps, ' ') }}" != "" ]; then
+              python -m uv pip install ${{ join(matrix.config.additional_deps, ' ') }}
+          fi
+          python -m uv pip install pytest-reportlog
+      - name: Environment
+        run: |
+          python utils/print_env.py
+      - name: ${{ matrix.config.backend }} quantization tests on GPU
+        env:
+          HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
+          # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
+          CUBLAS_WORKSPACE_CONFIG: :16:8
+          BIG_GPU_MEMORY: 40
+        run: |
+          python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
+            --make-reports=tests_${{ matrix.config.backend }}_torch_cuda \
+            --report-log=tests_${{ matrix.config.backend }}_torch_cuda.log \
+            tests/quantization/${{ matrix.config.test_location }}
+      - name: Failure short reports
+        if: ${{ failure() }}
+        run: |
+          cat reports/tests_${{ matrix.config.backend }}_torch_cuda_stats.txt
+          cat reports/tests_${{ matrix.config.backend }}_torch_cuda_failures_short.txt
+      - name: Test suite reports artifacts
+        if: ${{ always() }}
+        uses: actions/upload-artifact@v4
+        with:
+          name: torch_cuda_${{ matrix.config.backend }}_reports
+          path: reports
+          
+  run_nightly_pipeline_level_quantization_tests:
+    name: Torch quantization nightly tests
+    strategy:
+      fail-fast: false
+      max-parallel: 2
+    runs-on:
+      group: aws-g6e-xlarge-plus
+    container:
+      image: diffusers/diffusers-pytorch-cuda
+      options: --shm-size "20gb" --ipc host --gpus 0
+    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
+
   run_flax_tpu_tests:
     name: Nightly Flax TPU Tests
     runs-on:
@@ -344,128 +536,64 @@ jobs:
         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 >> $GITHUB_STEP_SUMMARY
-
-  run_nightly_onnx_tests:
-    name: Nightly ONNXRuntime CUDA tests on Ubuntu
+  generate_consolidated_report:
+    name: Generate Consolidated Test Report
+    needs: [
+      run_nightly_tests_for_torch_pipelines,
+      run_nightly_tests_for_other_torch_modules,
+      run_torch_compile_tests,
+      run_big_gpu_torch_tests,
+      run_nightly_quantization_tests,
+      run_nightly_pipeline_level_quantization_tests,
+      run_nightly_onnx_tests,
+      torch_minimum_version_cuda_tests,
+      run_flax_tpu_tests
+    ]
+    if: always()
     runs-on:
-      group: aws-g4dn-2xlarge
+      group: aws-general-8-plus
     container:
-      image: diffusers/diffusers-onnxruntime-cuda
-      options: --gpus 0 --shm-size "16gb" --ipc host
-
-    steps:
-    - name: Checkout diffusers
-      uses: actions/checkout@v3
-      with:
-        fetch-depth: 2
-
-    - name: NVIDIA-SMI
-      run: nvidia-smi
-
-    - name: Install dependencies
-      run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$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 >> $GITHUB_STEP_SUMMARY
-
-  run_nightly_quantization_tests:
-    name: Torch quantization nightly tests
-    strategy:
-      fail-fast: false
-      max-parallel: 2
-      matrix: 
-        config:
-          - backend: "bitsandbytes"
-            test_location: "bnb"
-          - backend: "gguf"
-            test_location: "gguf"
-          - backend: "torchao"
-            test_location: "torchao"
-    runs-on:
-      group: aws-g6e-xlarge-plus
-    container:
-      image: diffusers/diffusers-pytorch-cuda
-      options: --shm-size "20gb" --ipc host --gpus 0
+      image: diffusers/diffusers-pytorch-cpu
     steps:
       - name: Checkout diffusers
         uses: actions/checkout@v3
         with:
           fetch-depth: 2
-      - name: NVIDIA-SMI
-        run: nvidia-smi
+
+      - name: Create reports directory
+        run: mkdir -p combined_reports
+
+      - name: Download all test reports
+        uses: actions/download-artifact@v4
+        with:
+          path: artifacts
+
+      - name: Prepare reports
+        run: |
+          # Move all report files to a single directory for processing
+          find artifacts -name "*.txt" -exec cp {} combined_reports/ \;
+
       - name: Install dependencies
         run: |
-          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-          python -m uv pip install -e [quality,test]
-          python -m uv pip install -U ${{ matrix.config.backend }}
-          python -m uv pip install pytest-reportlog
-      - name: Environment
+          pip install -e .[test]
+          pip install slack_sdk tabulate
+
+      - name: Generate consolidated report
         run: |
-          python utils/print_env.py
-      - name: ${{ matrix.config.backend }} 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
+          python utils/consolidated_test_report.py \
+            --reports_dir combined_reports \
+            --output_file $CONSOLIDATED_REPORT_PATH \
+            --slack_channel_name diffusers-ci-nightly
+
+      - name: Show consolidated report
         run: |
-          python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-            --make-reports=tests_${{ matrix.config.backend }}_torch_cuda \
-            --report-log=tests_${{ matrix.config.backend }}_torch_cuda.log \
-            tests/quantization/${{ matrix.config.test_location }}
-      - name: Failure short reports
-        if: ${{ failure() }}
-        run: |
-          cat reports/tests_${{ matrix.config.backend }}_torch_cuda_stats.txt
-          cat reports/tests_${{ matrix.config.backend }}_torch_cuda_failures_short.txt
-      - name: Test suite reports artifacts
-        if: ${{ always() }}
+          cat $CONSOLIDATED_REPORT_PATH >> $GITHUB_STEP_SUMMARY
+
+      - name: Upload consolidated report
         uses: actions/upload-artifact@v4
         with:
-          name: torch_cuda_${{ matrix.config.backend }}_reports
-          path: reports
-      - name: Generate Report and Notify Channel
-        if: always()
-        run: |
-          pip install slack_sdk tabulate
-          python utils/log_reports.py >> $GITHUB_STEP_SUMMARY
+          name: 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
@@ -505,7 +633,7 @@ jobs:
 #        shell: arch -arch arm64 bash {0}
 #        env:
 #          HF_HOME: /System/Volumes/Data/mnt/cache
-#          HF_TOKEN: ${{ secrets.HF_TOKEN }}
+#          HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
 #        run: |
 #          ${CONDA_RUN} python -m pytest -n 1 -s -v --make-reports=tests_torch_mps \
 #            --report-log=tests_torch_mps.log \
@@ -561,7 +689,7 @@ jobs:
 #        shell: arch -arch arm64 bash {0}
 #        env:
 #          HF_HOME: /System/Volumes/Data/mnt/cache
-#          HF_TOKEN: ${{ secrets.HF_TOKEN }}
+#          HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
 #        run: |
 #          ${CONDA_RUN} python -m pytest -n 1 -s -v --make-reports=tests_torch_mps \
 #            --report-log=tests_torch_mps.log \

.github/workflows/pr_style_bot.yml

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

.github/workflows/pr_tests.yml

@@ -2,8 +2,7 @@ name: Fast tests for PRs
 
 on:
   pull_request:
-    branches:
-      - main
+    branches: [main]
     paths:
       - "src/diffusers/**.py"
       - "benchmarks/**.py"
@@ -12,6 +11,7 @@ on:
       - "tests/**.py"
       - ".github/**.yml"
       - "utils/**.py"
+      - "setup.py"
   push:
     branches:
       - ci-*
@@ -64,6 +64,7 @@ jobs:
         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: ${{ failure() }}
@@ -120,7 +121,8 @@ jobs:
       run: |
         python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
         python -m uv pip install -e [quality,test]
-        python -m uv pip install accelerate
+        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: |
@@ -289,8 +291,8 @@ 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

@@ -0,0 +1,296 @@
+name: Fast GPU Tests on PR 
+
+on:
+  pull_request:
+    branches: main
+    paths:
+      - "src/diffusers/models/modeling_utils.py"
+      - "src/diffusers/models/model_loading_utils.py"
+      - "src/diffusers/pipelines/pipeline_utils.py"
+      - "src/diffusers/pipeline_loading_utils.py"
+      - "src/diffusers/loaders/lora_base.py"
+      - "src/diffusers/loaders/lora_pipeline.py"
+      - "src/diffusers/loaders/peft.py"
+      - "tests/pipelines/test_pipelines_common.py"
+      - "tests/models/test_modeling_common.py"
+  workflow_dispatch:
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}
+  cancel-in-progress: true
+
+env:
+  DIFFUSERS_IS_CI: yes
+  OMP_NUM_THREADS: 8
+  MKL_NUM_THREADS: 8
+  HF_HUB_ENABLE_HF_TRANSFER: 1
+  PYTEST_TIMEOUT: 600
+  PIPELINE_USAGE_CUTOFF: 1000000000 # set high cutoff so that only always-test pipelines run
+
+jobs:
+  check_code_quality:
+    runs-on: ubuntu-22.04
+    steps:
+      - uses: actions/checkout@v3
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.8"
+      - name: Install dependencies
+        run: |
+          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: "3.8"
+      - 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
+  
+  setup_torch_cuda_pipeline_matrix:
+    needs: [check_code_quality, check_repository_consistency]
+    name: Setup Torch Pipelines CUDA Slow Tests Matrix
+    runs-on:
+      group: aws-general-8-plus
+    container:
+      image: diffusers/diffusers-pytorch-cpu
+    outputs:
+      pipeline_test_matrix: ${{ steps.fetch_pipeline_matrix.outputs.pipeline_test_matrix }}
+    steps:
+      - name: Checkout diffusers
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 2
+      - name: Install dependencies
+        run: |
+          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+          python -m uv pip install -e [quality,test]
+      - name: Environment
+        run: |
+          python utils/print_env.py
+      - name: Fetch Pipeline Matrix
+        id: fetch_pipeline_matrix
+        run: |
+          matrix=$(python utils/fetch_torch_cuda_pipeline_test_matrix.py)
+          echo $matrix
+          echo "pipeline_test_matrix=$matrix" >> $GITHUB_OUTPUT
+      - name: Pipeline Tests Artifacts
+        if: ${{ always() }}
+        uses: actions/upload-artifact@v4
+        with:
+          name: test-pipelines.json
+          path: reports
+
+  torch_pipelines_cuda_tests:
+    name: Torch Pipelines CUDA Tests
+    needs: setup_torch_cuda_pipeline_matrix
+    strategy:
+      fail-fast: false
+      max-parallel: 8
+      matrix:
+        module: ${{ fromJson(needs.setup_torch_cuda_pipeline_matrix.outputs.pipeline_test_matrix) }}
+    runs-on:
+      group: aws-g4dn-2xlarge
+    container:
+      image: diffusers/diffusers-pytorch-cuda
+      options: --shm-size "16gb" --ipc host --gpus 0
+    steps:
+      - name: Checkout diffusers
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 2
+
+      - name: NVIDIA-SMI
+        run: |
+          nvidia-smi
+      - name: Install dependencies
+        run: |
+          python -m venv /opt/venv && export PATH="/opt/venv/bin:$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
+          pip uninstall transformers -y && python -m uv pip install -U transformers@git+https://github.com/huggingface/transformers.git --no-deps
+
+      - name: Environment
+        run: |
+          python utils/print_env.py
+      - name: Extract tests
+        id: extract_tests
+        run: |
+          pattern=$(python utils/extract_tests_from_mixin.py --type pipeline)
+          echo "$pattern" > /tmp/test_pattern.txt
+          echo "pattern_file=/tmp/test_pattern.txt" >> $GITHUB_OUTPUT
+
+      - name: PyTorch CUDA checkpoint tests on Ubuntu
+        env:
+          HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
+          # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
+          CUBLAS_WORKSPACE_CONFIG: :16:8
+        run: |
+          if [ "${{ matrix.module }}" = "ip_adapters" ]; then 
+              python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
+              -s -v -k "not Flax and not Onnx" \
+              --make-reports=tests_pipeline_${{ matrix.module }}_cuda \
+              tests/pipelines/${{ matrix.module }}
+          else 
+              pattern=$(cat ${{ steps.extract_tests.outputs.pattern_file }})
+              python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
+              -s -v -k "not Flax and not Onnx and $pattern" \
+              --make-reports=tests_pipeline_${{ matrix.module }}_cuda \
+              tests/pipelines/${{ matrix.module }}
+          fi 
+
+      - name: Failure short reports
+        if: ${{ failure() }}
+        run: |
+          cat reports/tests_pipeline_${{ matrix.module }}_cuda_stats.txt
+          cat reports/tests_pipeline_${{ matrix.module }}_cuda_failures_short.txt
+      - name: Test suite reports artifacts
+        if: ${{ always() }}
+        uses: actions/upload-artifact@v4
+        with:
+          name: pipeline_${{ matrix.module }}_test_reports
+          path: reports
+
+  torch_cuda_tests:
+    name: Torch CUDA Tests
+    needs: [check_code_quality, check_repository_consistency]
+    runs-on:
+      group: aws-g4dn-2xlarge
+    container:
+      image: diffusers/diffusers-pytorch-cuda
+      options: --shm-size "16gb" --ipc host --gpus 0
+    defaults:
+      run:
+        shell: bash
+    strategy:
+      fail-fast: false
+      max-parallel: 2
+      matrix:
+        module: [models, schedulers, lora, others]
+    steps:
+    - name: Checkout diffusers
+      uses: actions/checkout@v3
+      with:
+        fetch-depth: 2
+
+    - name: Install dependencies
+      run: |
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+        python -m uv pip install -e [quality,test]
+        python -m uv pip install peft@git+https://github.com/huggingface/peft.git
+        pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
+        pip uninstall transformers -y && python -m uv pip install -U transformers@git+https://github.com/huggingface/transformers.git --no-deps
+
+    - name: Environment
+      run: |
+        python utils/print_env.py
+
+    - name: Extract tests
+      id: extract_tests
+      run: |
+        pattern=$(python utils/extract_tests_from_mixin.py --type ${{ matrix.module }})
+        echo "$pattern" > /tmp/test_pattern.txt
+        echo "pattern_file=/tmp/test_pattern.txt" >> $GITHUB_OUTPUT
+
+    - name: Run PyTorch CUDA tests
+      env:
+        HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
+        # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
+        CUBLAS_WORKSPACE_CONFIG: :16:8
+      run: |
+        pattern=$(cat ${{ steps.extract_tests.outputs.pattern_file }})
+        if [ -z "$pattern" ]; then
+          python -m pytest -n 1 -sv --max-worker-restart=0 --dist=loadfile -k "not Flax and not Onnx" tests/${{ matrix.module }} \
+          --make-reports=tests_torch_cuda_${{ matrix.module }}  
+        else
+          python -m pytest -n 1 -sv --max-worker-restart=0 --dist=loadfile -k "not Flax and not Onnx and $pattern" tests/${{ matrix.module }} \
+          --make-reports=tests_torch_cuda_${{ matrix.module }}  
+        fi
+
+    - name: Failure short reports
+      if: ${{ failure() }}
+      run: |
+        cat reports/tests_torch_cuda_${{ matrix.module }}_stats.txt
+        cat reports/tests_torch_cuda_${{ matrix.module }}_failures_short.txt
+
+    - name: Test suite reports artifacts
+      if: ${{ always() }}
+      uses: actions/upload-artifact@v4
+      with:
+        name: torch_cuda_test_reports_${{ matrix.module }}
+        path: reports
+
+  run_examples_tests:
+    name: Examples PyTorch CUDA tests on Ubuntu
+    needs: [check_code_quality, check_repository_consistency]
+    runs-on:
+      group: aws-g4dn-2xlarge
+
+    container:
+      image: diffusers/diffusers-pytorch-cuda
+      options: --gpus 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:$PATH"
+        pip uninstall transformers -y && python -m uv pip install -U transformers@git+https://github.com/huggingface/transformers.git --no-deps
+        python -m uv pip install -e [quality,test,training]
+
+    - name: Environment
+      run: |
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+        python utils/print_env.py
+
+    - name: Run example tests on GPU
+      env:
+        HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
+      run: |
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+        python -m uv pip install timm
+        python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile -s -v --make-reports=examples_torch_cuda examples/
+
+    - name: Failure short reports
+      if: ${{ failure() }}
+      run: |
+        cat reports/examples_torch_cuda_stats.txt
+        cat reports/examples_torch_cuda_failures_short.txt
+
+    - name: Test suite reports artifacts
+      if: ${{ always() }}
+      uses: actions/upload-artifact@v4
+      with:
+        name: examples_test_reports
+        path: reports
+

.github/workflows/push_tests.yml

@@ -187,7 +187,7 @@ jobs:
 
     - name: Run Flax TPU tests
       env:
-        HF_TOKEN: ${{ secrets.HF_TOKEN }}
+        HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
       run: |
         python -m pytest -n 0 \
           -s -v -k "Flax" \
@@ -235,7 +235,7 @@ jobs:
 
     - name: Run ONNXRuntime CUDA tests
       env:
-        HF_TOKEN: ${{ secrets.HF_TOKEN }}
+        HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
       run: |
         python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
           -s -v -k "Onnx" \
@@ -262,7 +262,7 @@ jobs:
       group: aws-g4dn-2xlarge
 
     container:
-      image: diffusers/diffusers-pytorch-compile-cuda
+      image: diffusers/diffusers-pytorch-cuda
       options: --gpus 0 --shm-size "16gb" --ipc host
 
     steps:
@@ -283,7 +283,7 @@ jobs:
         python utils/print_env.py
     - name: Run example tests on GPU
       env:
-        HF_TOKEN: ${{ secrets.HF_TOKEN }}
+        HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
         RUN_COMPILE: yes
       run: |
         python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile -s -v -k "compile" --make-reports=tests_torch_compile_cuda tests/
@@ -326,7 +326,7 @@ jobs:
         python utils/print_env.py
     - name: Run example tests on GPU
       env:
-        HF_TOKEN: ${{ secrets.HF_TOKEN }}
+        HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
       run: |
         python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile -s -v -k "xformers" --make-reports=tests_torch_xformers_cuda tests/
     - name: Failure short reports
@@ -349,7 +349,6 @@ jobs:
     container:
       image: diffusers/diffusers-pytorch-cuda
       options: --gpus 0 --shm-size "16gb" --ipc host
-
     steps:
     - name: Checkout diffusers
       uses: actions/checkout@v3
@@ -359,7 +358,6 @@ jobs:
     - name: NVIDIA-SMI
       run: |
         nvidia-smi
-
     - name: Install dependencies
       run: |
         python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
@@ -372,7 +370,7 @@ jobs:
 
     - name: Run example tests on GPU
       env:
-        HF_TOKEN: ${{ secrets.HF_TOKEN }}
+        HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
       run: |
         python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
         python -m uv pip install timm

.github/workflows/release_tests_fast.yml

@@ -81,7 +81,7 @@ jobs:
           python utils/print_env.py
       - name: Slow PyTorch CUDA checkpoint tests on Ubuntu
         env:
-          HF_TOKEN: ${{ secrets.HF_TOKEN }}
+          HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
           # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
           CUBLAS_WORKSPACE_CONFIG: :16:8
         run: |
@@ -135,7 +135,7 @@ jobs:
 
     - name: Run PyTorch CUDA tests
       env:
-        HF_TOKEN: ${{ secrets.HF_TOKEN }}
+        HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
         # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
         CUBLAS_WORKSPACE_CONFIG: :16:8
       run: |
@@ -186,7 +186,7 @@ jobs:
 
       - name: Run PyTorch CUDA tests
         env:
-          HF_TOKEN: ${{ secrets.HF_TOKEN }}
+          HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
           # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
           CUBLAS_WORKSPACE_CONFIG: :16:8
         run: |
@@ -241,7 +241,7 @@ jobs:
 
     - name: Run slow Flax TPU tests
       env:
-        HF_TOKEN: ${{ secrets.HF_TOKEN }}
+        HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
       run: |
         python -m pytest -n 0 \
           -s -v -k "Flax" \
@@ -289,7 +289,7 @@ jobs:
 
     - name: Run slow ONNXRuntime CUDA tests
       env:
-        HF_TOKEN: ${{ secrets.HF_TOKEN }}
+        HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
       run: |
         python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
           -s -v -k "Onnx" \
@@ -316,7 +316,7 @@ jobs:
       group: aws-g4dn-2xlarge
 
     container:
-      image: diffusers/diffusers-pytorch-compile-cuda
+      image: diffusers/diffusers-pytorch-cuda
       options: --gpus 0 --shm-size "16gb" --ipc host
 
     steps:
@@ -335,9 +335,9 @@ jobs:
     - name: Environment
       run: |
         python utils/print_env.py
-    - name: Run example tests on GPU
+    - name: Run torch compile tests on GPU
       env:
-        HF_TOKEN: ${{ secrets.HF_TOKEN }}
+        HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
         RUN_COMPILE: yes
       run: |
         python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile -s -v -k "compile" --make-reports=tests_torch_compile_cuda tests/
@@ -380,7 +380,7 @@ jobs:
         python utils/print_env.py
     - name: Run example tests on GPU
       env:
-        HF_TOKEN: ${{ secrets.HF_TOKEN }}
+        HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
       run: |
         python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile -s -v -k "xformers" --make-reports=tests_torch_xformers_cuda tests/
     - name: Failure short reports
@@ -426,7 +426,7 @@ jobs:
 
     - name: Run example tests on GPU
       env:
-        HF_TOKEN: ${{ secrets.HF_TOKEN }}
+        HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
       run: |
         python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
         python -m uv pip install timm

.github/workflows/run_tests_from_a_pr.yml

@@ -7,8 +7,8 @@ on:
         default: 'diffusers/diffusers-pytorch-cuda'
         description: 'Name of the Docker image'
         required: true
-      branch:
-        description: 'PR Branch to test on'
+      pr_number:
+        description: 'PR number to test on'
         required: true
       test:
         description: 'Tests to run (e.g.: `tests/models`).'
@@ -43,8 +43,8 @@ jobs:
             exit 1
           fi
 
-          if [[ ! "$PY_TEST" =~ ^tests/(models|pipelines) ]]; then
-            echo "Error: The input string must contain either 'models' or 'pipelines' after 'tests/'."
+          if [[ ! "$PY_TEST" =~ ^tests/(models|pipelines|lora) ]]; then
+            echo "Error: The input string must contain either 'models', 'pipelines', or 'lora' after 'tests/'."
             exit 1
           fi
 
@@ -53,13 +53,13 @@ jobs:
             exit 1
           fi
           echo "$PY_TEST"
+        
+        shell: bash -e {0}
 
       - name: Checkout PR branch
         uses: actions/checkout@v4
         with:
-          ref: ${{ github.event.inputs.branch }}
-          repository: ${{ github.event.pull_request.head.repo.full_name }}
-
+          ref: refs/pull/${{ inputs.pr_number }}/head
 
       - name: Install pytest
         run: |

.github/workflows/trufflehog.yml

@@ -13,3 +13,6 @@ jobs:
         fetch-depth: 0
     - name: Secret Scanning
       uses: trufflesecurity/trufflehog@main
+      with:
+        extra_args: --results=verified,unknown
+

docker/diffusers-onnxruntime-cpu/Dockerfile

@@ -28,9 +28,9 @@ ENV PATH="/opt/venv/bin:$PATH"
 # pre-install the heavy dependencies (these can later be overridden by the deps from setup.py)
 RUN python3 -m pip install --no-cache-dir --upgrade pip uv==0.1.11 && \
     python3 -m uv pip install --no-cache-dir \
-        torch==2.1.2 \
-        torchvision==0.16.2 \
-        torchaudio==2.1.2 \
+        torch \
+        torchvision \
+        torchaudio\
         onnxruntime \
         --extra-index-url https://download.pytorch.org/whl/cpu && \
     python3 -m uv pip install --no-cache-dir \

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/source/en/_toctree.yml

@@ -17,12 +17,6 @@
     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: using-diffusers/loading
@@ -33,11 +27,24 @@
     title: Load schedulers and models
   - 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: 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: Adapters
+  isExpanded: false
 - sections:
   - local: using-diffusers/unconditional_image_generation
     title: Unconditional image generation
@@ -59,8 +66,6 @@
     title: Create a server
   - 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
@@ -77,8 +82,16 @@
     title: Outpainting
   title: Advanced inference
 - sections:
-  - local: using-diffusers/cogvideox
-    title: CogVideoX
+  - local: hybrid_inference/overview
+    title: Overview
+  - local: hybrid_inference/vae_decode
+    title: VAE Decode
+  - local: hybrid_inference/vae_encode
+    title: VAE Encode
+  - local: hybrid_inference/api_reference
+    title: API Reference
+  title: Hybrid Inference
+- sections:
   - local: using-diffusers/consisid
     title: ConsisID
   - local: using-diffusers/sdxl
@@ -87,18 +100,12 @@
     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
@@ -163,14 +170,16 @@
     title: gguf
   - local: quantization/torchao
     title: torchao
+  - local: quantization/quanto
+    title: quanto
   title: Quantization Methods
 - sections:
   - local: optimization/fp16
-    title: Speed up inference
+    title: Accelerate inference
+  - local: optimization/cache
+    title: Caching
   - local: optimization/memory
     title: Reduce memory usage
-  - local: optimization/torch2.0
-    title: PyTorch 2.0
   - local: optimization/xformers
     title: xFormers
   - local: optimization/tome
@@ -197,7 +206,7 @@
     - local: optimization/mps
       title: Metal Performance Shaders (MPS)
     - local: optimization/habana
-      title: Habana Gaudi
+      title: Intel Gaudi
     - local: optimization/neuron
       title: AWS Neuron
     title: Optimized hardware
@@ -251,71 +260,91 @@
     sections:
     - local: api/models/overview
       title: Overview
+    - local: api/models/auto_model
+      title: AutoModel
     - sections:
       - local: api/models/controlnet
         title: ControlNetModel
+      - local: api/models/controlnet_union
+        title: ControlNetUnionModel
       - local: api/models/controlnet_flux
         title: FluxControlNetModel
       - local: api/models/controlnet_hunyuandit
         title: HunyuanDiT2DControlNetModel
+      - local: api/models/controlnet_sana
+        title: SanaControlNetModel
       - local: api/models/controlnet_sd3
         title: SD3ControlNetModel
       - local: api/models/controlnet_sparsectrl
         title: SparseControlNetModel
-      - local: api/models/controlnet_union
-        title: ControlNetUnionModel
       title: ControlNets
     - 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/consisid_transformer3d
-        title: ConsisIDTransformer3DModel
       - local: api/models/cogview3plus_transformer2d
         title: CogView3PlusTransformer2DModel
+      - local: api/models/cogview4_transformer2d
+        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
+        title: EasyAnimateTransformer3DModel
       - local: api/models/flux_transformer
         title: FluxTransformer2DModel
+      - local: api/models/hidream_image_transformer
+        title: HiDreamImageTransformer2DModel
       - local: api/models/hunyuan_transformer2d
         title: HunyuanDiT2DModel
       - local: api/models/hunyuan_video_transformer_3d
         title: HunyuanVideoTransformer3DModel
       - local: api/models/latte_transformer3d
         title: LatteTransformer3DModel
-      - local: api/models/lumina_nextdit2d
-        title: LuminaNextDiT2DModel
       - local: api/models/ltx_video_transformer3d
         title: LTXVideoTransformer3DModel
+      - local: api/models/lumina2_transformer2d
+        title: Lumina2Transformer2DModel
+      - local: api/models/lumina_nextdit2d
+        title: LuminaNextDiT2DModel
       - local: api/models/mochi_transformer3d
         title: MochiTransformer3DModel
+      - local: api/models/omnigen_transformer
+        title: OmniGenTransformer2DModel
       - local: api/models/pixart_transformer2d
         title: PixArtTransformer2DModel
       - local: api/models/prior_transformer
         title: PriorTransformer
-      - local: api/models/sd3_transformer2d
-        title: SD3Transformer2DModel
       - local: api/models/sana_transformer2d
         title: SanaTransformer2DModel
+      - local: api/models/sd3_transformer2d
+        title: SD3Transformer2DModel
       - local: api/models/stable_audio_transformer
         title: StableAudioDiTModel
       - local: api/models/transformer2d
         title: Transformer2DModel
       - local: api/models/transformer_temporal
         title: TransformerTemporalModel
+      - local: api/models/wan_transformer_3d
+        title: WanTransformer3DModel
       title: Transformers
     - sections:
       - local: api/models/stable_cascade_unet
         title: StableCascadeUNet
       - local: api/models/unet
         title: UNet1DModel
-      - local: api/models/unet2d
-        title: UNet2DModel
       - local: api/models/unet2d-cond
         title: UNet2DConditionModel
+      - local: api/models/unet2d
+        title: UNet2DModel
       - local: api/models/unet3d-cond
         title: UNet3DConditionModel
       - local: api/models/unet-motion
@@ -324,22 +353,28 @@
         title: UViT2DModel
       title: UNets
     - sections:
+      - local: api/models/asymmetricautoencoderkl
+        title: AsymmetricAutoencoderKL
+      - local: api/models/autoencoder_dc
+        title: AutoencoderDC
       - local: api/models/autoencoderkl
         title: AutoencoderKL
       - local: api/models/autoencoderkl_allegro
         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
         title: AutoencoderKLLTXVideo
+      - local: api/models/autoencoderkl_magvit
+        title: AutoencoderKLMagvit
       - local: api/models/autoencoderkl_mochi
         title: AutoencoderKLMochi
-      - local: api/models/asymmetricautoencoderkl
-        title: AsymmetricAutoencoderKL
-      - local: api/models/autoencoder_dc
-        title: AutoencoderDC
+      - local: api/models/autoencoder_kl_wan
+        title: AutoencoderKLWan
       - local: api/models/consistency_decoder_vae
         title: ConsistencyDecoderVAE
       - local: api/models/autoencoder_oobleck
@@ -372,10 +407,14 @@
       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
       title: CogView3
+    - local: api/pipelines/cogview4
+      title: CogView4
     - local: api/pipelines/consisid
       title: ConsisID
     - local: api/pipelines/consistency_models
@@ -390,12 +429,16 @@
       title: ControlNet with Stable Diffusion 3
     - local: api/pipelines/controlnet_sdxl
       title: ControlNet with Stable Diffusion XL
+    - local: api/pipelines/controlnet_sana
+      title: ControlNet-Sana
     - local: api/pipelines/controlnetxs
       title: ControlNet-XS
     - local: api/pipelines/controlnetxs_sdxl
       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
@@ -408,10 +451,16 @@
       title: DiffEdit
     - local: api/pipelines/dit
       title: DiT
+    - local: api/pipelines/easyanimate
+      title: EasyAnimate
     - local: api/pipelines/flux
       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
       title: Hunyuan-DiT
     - local: api/pipelines/hunyuan_video
@@ -438,6 +487,8 @@
       title: LEDITS++
     - local: api/pipelines/ltx_video
       title: LTXVideo
+    - local: api/pipelines/lumina2
+      title: Lumina 2.0
     - local: api/pipelines/lumina
       title: Lumina-T2X
     - local: api/pipelines/marigold
@@ -448,6 +499,8 @@
       title: MultiDiffusion
     - local: api/pipelines/musicldm
       title: MusicLDM
+    - local: api/pipelines/omnigen
+      title: OmniGen
     - local: api/pipelines/pag
       title: PAG
     - local: api/pipelines/paint_by_example
@@ -460,6 +513,8 @@
       title: PixArt-Σ
     - local: api/pipelines/sana
       title: Sana
+    - local: api/pipelines/sana_sprint
+      title: Sana Sprint
     - local: api/pipelines/self_attention_guidance
       title: Self-Attention Guidance
     - local: api/pipelines/semantic_stable_diffusion
@@ -473,40 +528,40 @@
     - sections:
       - local: api/pipelines/stable_diffusion/overview
         title: Overview
-      - local: api/pipelines/stable_diffusion/text2img
-        title: Text-to-image
+      - local: api/pipelines/stable_diffusion/depth2img
+        title: Depth-to-image
+      - local: api/pipelines/stable_diffusion/gligen
+        title: GLIGEN (Grounded Language-to-Image Generation)
+      - local: api/pipelines/stable_diffusion/image_variation
+        title: Image variation
       - local: api/pipelines/stable_diffusion/img2img
         title: Image-to-image
       - local: api/pipelines/stable_diffusion/svd
         title: Image-to-video
       - local: api/pipelines/stable_diffusion/inpaint
         title: Inpainting
-      - local: api/pipelines/stable_diffusion/depth2img
-        title: Depth-to-image
-      - local: api/pipelines/stable_diffusion/image_variation
-        title: Image variation
+      - local: api/pipelines/stable_diffusion/k_diffusion
+        title: K-Diffusion
+      - local: api/pipelines/stable_diffusion/latent_upscale
+        title: Latent upscaler
+      - local: api/pipelines/stable_diffusion/ldm3d_diffusion
+        title: LDM3D Text-to-(RGB, Depth), Text-to-(RGB-pano, Depth-pano), LDM3D Upscaler
       - local: api/pipelines/stable_diffusion/stable_diffusion_safe
         title: Safe Stable Diffusion
+      - local: api/pipelines/stable_diffusion/sdxl_turbo
+        title: SDXL Turbo
       - local: api/pipelines/stable_diffusion/stable_diffusion_2
         title: Stable Diffusion 2
       - local: api/pipelines/stable_diffusion/stable_diffusion_3
         title: Stable Diffusion 3
       - local: api/pipelines/stable_diffusion/stable_diffusion_xl
         title: Stable Diffusion XL
-      - local: api/pipelines/stable_diffusion/sdxl_turbo
-        title: SDXL Turbo
-      - local: api/pipelines/stable_diffusion/latent_upscale
-        title: Latent upscaler
       - local: api/pipelines/stable_diffusion/upscale
         title: Super-resolution
-      - local: api/pipelines/stable_diffusion/k_diffusion
-        title: K-Diffusion
-      - local: api/pipelines/stable_diffusion/ldm3d_diffusion
-        title: LDM3D Text-to-(RGB, Depth), Text-to-(RGB-pano, Depth-pano), LDM3D Upscaler
       - local: api/pipelines/stable_diffusion/adapter
         title: T2I-Adapter
-      - local: api/pipelines/stable_diffusion/gligen
-        title: GLIGEN (Grounded Language-to-Image Generation)
+      - local: api/pipelines/stable_diffusion/text2img
+        title: Text-to-image
       title: Stable Diffusion
     - local: api/pipelines/stable_unclip
       title: Stable unCLIP
@@ -520,6 +575,10 @@
       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
@@ -529,6 +588,10 @@
       title: Overview
     - local: api/schedulers/cm_stochastic_iterative
       title: CMStochasticIterativeScheduler
+    - local: api/schedulers/ddim_cogvideox
+      title: CogVideoXDDIMScheduler
+    - local: api/schedulers/multistep_dpm_solver_cogvideox
+      title: CogVideoXDPMScheduler
     - local: api/schedulers/consistency_decoder
       title: ConsistencyDecoderScheduler
     - local: api/schedulers/cosine_dpm
@@ -598,6 +661,8 @@
       title: Attention Processor
     - local: api/activations
       title: Custom activation functions
+    - local: api/cache
+      title: Caching methods
     - local: api/normalization
       title: Custom normalization layers
     - local: api/utilities

docs/source/en/api/activations.md

@@ -25,3 +25,16 @@ Customized activation functions for supporting various models in 🤗 Diffusers.
 ## ApproximateGELU
 
 [[autodoc]] models.activations.ApproximateGELU
+
+
+## SwiGLU
+
+[[autodoc]] models.activations.SwiGLU
+
+## FP32SiLU
+
+[[autodoc]] models.activations.FP32SiLU
+
+## LinearActivation
+
+[[autodoc]] models.activations.LinearActivation

docs/source/en/api/attnprocessor.md

@@ -147,3 +147,20 @@ An attention processor is a class for applying different types of attention mech
 ## XLAFlashAttnProcessor2_0
 
 [[autodoc]] models.attention_processor.XLAFlashAttnProcessor2_0
+
+## XFormersJointAttnProcessor
+
+[[autodoc]] models.attention_processor.XFormersJointAttnProcessor
+
+## IPAdapterXFormersAttnProcessor
+
+[[autodoc]] models.attention_processor.IPAdapterXFormersAttnProcessor
+
+## FluxIPAdapterJointAttnProcessor2_0
+
+[[autodoc]] models.attention_processor.FluxIPAdapterJointAttnProcessor2_0
+
+
+## XLAFluxFlashAttnProcessor2_0
+
+[[autodoc]] models.attention_processor.XLAFluxFlashAttnProcessor2_0

docs/source/en/api/cache.md

@@ -0,0 +1,30 @@
+<!-- Copyright 2024 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License. -->
+
+# Caching methods
+
+Cache methods speedup diffusion transformers by storing and reusing intermediate outputs of specific layers, such as attention and feedforward layers, instead of recalculating them at each inference step.
+
+## CacheMixin
+
+[[autodoc]] CacheMixin
+
+## PyramidAttentionBroadcastConfig
+
+[[autodoc]] PyramidAttentionBroadcastConfig
+
+[[autodoc]] apply_pyramid_attention_broadcast
+
+## FasterCacheConfig
+
+[[autodoc]] FasterCacheConfig
+
+[[autodoc]] apply_faster_cache

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

@@ -20,7 +20,15 @@ LoRA is a fast and lightweight training method that inserts and trains a signifi
 - [`FluxLoraLoaderMixin`] provides similar functions for [Flux](https://huggingface.co/docs/diffusers/main/en/api/pipelines/flux).
 - [`CogVideoXLoraLoaderMixin`] provides similar functions for [CogVideoX](https://huggingface.co/docs/diffusers/main/en/api/pipelines/cogvideox).
 - [`Mochi1LoraLoaderMixin`] provides similar functions for [Mochi](https://huggingface.co/docs/diffusers/main/en/api/pipelines/mochi).
+- [`AuraFlowLoraLoaderMixin`] provides similar functions for [AuraFlow](https://huggingface.co/fal/AuraFlow).
+- [`LTXVideoLoraLoaderMixin`] provides similar functions for [LTX-Video](https://huggingface.co/docs/diffusers/main/en/api/pipelines/ltx_video).
+- [`SanaLoraLoaderMixin`] provides similar functions for [Sana](https://huggingface.co/docs/diffusers/main/en/api/pipelines/sana).
+- [`HunyuanVideoLoraLoaderMixin`] provides similar functions for [HunyuanVideo](https://huggingface.co/docs/diffusers/main/en/api/pipelines/hunyuan_video).
+- [`Lumina2LoraLoaderMixin`] provides similar functions for [Lumina2](https://huggingface.co/docs/diffusers/main/en/api/pipelines/lumina2).
+- [`WanLoraLoaderMixin`] provides similar functions for [Wan](https://huggingface.co/docs/diffusers/main/en/api/pipelines/wan).
+- [`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)
 - [`LoraBaseMixin`] provides a base class with several utility methods to fuse, unfuse, unload, LoRAs and more.
 
 <Tip>
@@ -52,11 +60,46 @@ To learn more about how to load LoRA weights, see the [LoRA](../../using-diffuse
 ## Mochi1LoraLoaderMixin
 
 [[autodoc]] loaders.lora_pipeline.Mochi1LoraLoaderMixin
+## AuraFlowLoraLoaderMixin
+
+[[autodoc]] loaders.lora_pipeline.AuraFlowLoraLoaderMixin
+
+## LTXVideoLoraLoaderMixin
+
+[[autodoc]] loaders.lora_pipeline.LTXVideoLoraLoaderMixin
+
+## SanaLoraLoaderMixin
+
+[[autodoc]] loaders.lora_pipeline.SanaLoraLoaderMixin
+
+## HunyuanVideoLoraLoaderMixin
+
+[[autodoc]] loaders.lora_pipeline.HunyuanVideoLoraLoaderMixin
+
+## Lumina2LoraLoaderMixin
+
+[[autodoc]] loaders.lora_pipeline.Lumina2LoraLoaderMixin
+
+## CogView4LoraLoaderMixin
+
+[[autodoc]] loaders.lora_pipeline.CogView4LoraLoaderMixin
+
+## WanLoraLoaderMixin
+
+[[autodoc]] loaders.lora_pipeline.WanLoraLoaderMixin
 
 ## AmusedLoraLoaderMixin
 
 [[autodoc]] loaders.lora_pipeline.AmusedLoraLoaderMixin
 
+## HiDreamImageLoraLoaderMixin
+
+[[autodoc]] loaders.lora_pipeline.HiDreamImageLoraLoaderMixin
+
 ## LoraBaseMixin
 
-[[autodoc]] loaders.lora_base.LoraBaseMixin
+[[autodoc]] loaders.lora_base.LoraBaseMixin
+
+## WanLoraLoaderMixin
+
+[[autodoc]] loaders.lora_pipeline.WanLoraLoaderMixin

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

@@ -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/auto_model.md

@@ -0,0 +1,29 @@
+<!--Copyright 2024 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License.
+-->
+
+# AutoModel
+
+The `AutoModel` is designed to make it easy to load a checkpoint without needing to know the specific model class. `AutoModel` automatically retrieves the correct model class from the checkpoint `config.json` file.
+
+```python
+from diffusers import AutoModel, AutoPipelineForText2Image
+
+unet = AutoModel.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5", subfolder="unet")
+pipe = AutoPipelineForText2Image.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5", unet=unet)
+```
+
+
+## AutoModel
+
+[[autodoc]] AutoModel
+	- all
+	- from_pretrained

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

@@ -0,0 +1,32 @@
+<!-- Copyright 2024 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License. -->
+
+# AutoencoderKLWan
+
+The 3D variational autoencoder (VAE) model with KL loss used in [Wan 2.1](https://github.com/Wan-Video/Wan2.1) by the Alibaba Wan Team.
+
+The model can be loaded with the following code snippet.
+
+```python
+from diffusers import AutoencoderKLWan
+
+vae = AutoencoderKLWan.from_pretrained("Wan-AI/Wan2.1-T2V-1.3B-Diffusers", subfolder="vae", torch_dtype=torch.float32)
+```
+
+## AutoencoderKLWan
+
+[[autodoc]] AutoencoderKLWan
+  - decode
+  - all
+
+## DecoderOutput
+
+[[autodoc]] models.autoencoders.vae.DecoderOutput

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

@@ -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

@@ -18,7 +18,7 @@ The model can be loaded with the following code snippet.
 ```python
 from diffusers import AutoencoderKLAllegro
 
-vae = AutoencoderKLCogVideoX.from_pretrained("rhymes-ai/Allegro", subfolder="vae", torch_dtype=torch.float32).to("cuda")
+vae = AutoencoderKLAllegro.from_pretrained("rhymes-ai/Allegro", subfolder="vae", torch_dtype=torch.float32).to("cuda")
 ```
 
 ## AutoencoderKLAllegro

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

@@ -0,0 +1,40 @@
+<!-- Copyright 2024 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License. -->
+
+# 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_magvit.md

@@ -0,0 +1,37 @@
+<!--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. -->
+
+# AutoencoderKLMagvit
+
+The 3D variational autoencoder (VAE) model with KL loss used in [EasyAnimate](https://github.com/aigc-apps/EasyAnimate) was introduced by Alibaba PAI.
+
+The model can be loaded with the following code snippet.
+
+```python
+from diffusers import AutoencoderKLMagvit
+
+vae = AutoencoderKLMagvit.from_pretrained("alibaba-pai/EasyAnimateV5.1-12b-zh", subfolder="vae", torch_dtype=torch.float16).to("cuda")
+```
+
+## AutoencoderKLMagvit
+
+[[autodoc]] AutoencoderKLMagvit
+    - 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/cogview4_transformer2d.md

@@ -0,0 +1,30 @@
+<!--Copyright 2024 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License. -->
+
+# CogView4Transformer2DModel
+
+A Diffusion Transformer model for 2D data from [CogView4]()
+
+The model can be loaded with the following code snippet.
+
+```python
+from diffusers import CogView4Transformer2DModel
+
+transformer = CogView4Transformer2DModel.from_pretrained("THUDM/CogView4-6B", subfolder="transformer", torch_dtype=torch.bfloat16).to("cuda")
+```
+
+## CogView4Transformer2DModel
+
+[[autodoc]] CogView4Transformer2DModel
+
+## Transformer2DModelOutput
+
+[[autodoc]] models.modeling_outputs.Transformer2DModelOutput

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

@@ -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/controlnet_hunyuandit.md

@@ -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

@@ -0,0 +1,29 @@
+<!--Copyright 2024 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License.
+-->
+
+# SanaControlNetModel
+
+The ControlNet model was introduced in [Adding Conditional Control to Text-to-Image Diffusion Models](https://huggingface.co/papers/2302.05543) by Lvmin Zhang, Anyi Rao, Maneesh Agrawala. It provides a greater degree of control over text-to-image generation by conditioning the model on additional inputs such as edge maps, depth maps, segmentation maps, and keypoints for pose detection.
+
+The abstract from the paper is:
+
+*We present ControlNet, a neural network architecture to add spatial conditioning controls to large, pretrained text-to-image diffusion models. ControlNet locks the production-ready large diffusion models, and reuses their deep and robust encoding layers pretrained with billions of images as a strong backbone to learn a diverse set of conditional controls. The neural architecture is connected with "zero convolutions" (zero-initialized convolution layers) that progressively grow the parameters from zero and ensure that no harmful noise could affect the finetuning. We test various conditioning controls, eg, edges, depth, segmentation, human pose, etc, with Stable Diffusion, using single or multiple conditions, with or without prompts. We show that the training of ControlNets is robust with small (<50k) and large (>1m) datasets. Extensive results show that ControlNet may facilitate wider applications to control image diffusion models.*
+
+This model was contributed by [ishan24](https://huggingface.co/ishan24). ❤️
+The original codebase can be found at [NVlabs/Sana](https://github.com/NVlabs/Sana), and you can find official ControlNet checkpoints on [Efficient-Large-Model's](https://huggingface.co/Efficient-Large-Model) Hub profile.
+
+## SanaControlNetModel
+[[autodoc]] SanaControlNetModel
+
+## SanaControlNetOutput
+[[autodoc]] models.controlnets.controlnet_sana.SanaControlNetOutput
+

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

@@ -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/cosmos_transformer3d.md

@@ -0,0 +1,30 @@
+<!-- Copyright 2024 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License. -->
+
+# 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/easyanimate_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. -->
+
+# EasyAnimateTransformer3DModel
+
+A Diffusion Transformer model for 3D data from [EasyAnimate](https://github.com/aigc-apps/EasyAnimate) was introduced by Alibaba PAI.
+
+The model can be loaded with the following code snippet.
+
+```python
+from diffusers import EasyAnimateTransformer3DModel
+
+transformer = EasyAnimateTransformer3DModel.from_pretrained("alibaba-pai/EasyAnimateV5.1-12b-zh", subfolder="transformer", torch_dtype=torch.float16).to("cuda")
+```
+
+## EasyAnimateTransformer3DModel
+
+[[autodoc]] EasyAnimateTransformer3DModel
+
+## Transformer2DModelOutput
+
+[[autodoc]] models.modeling_outputs.Transformer2DModelOutput

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

@@ -0,0 +1,46 @@
+<!-- Copyright 2024 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License. -->
+
+# HiDreamImageTransformer2DModel
+
+A Transformer model for image-like data from [HiDream-I1](https://huggingface.co/HiDream-ai).
+
+The model can be loaded with the following code snippet.
+
+```python
+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
+
+## Transformer2DModelOutput
+
+[[autodoc]] models.modeling_outputs.Transformer2DModelOutput

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

@@ -0,0 +1,30 @@
+<!-- Copyright 2024 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License. -->
+
+# Lumina2Transformer2DModel
+
+A Diffusion Transformer model for 3D video-like data was introduced in [Lumina Image 2.0](https://huggingface.co/Alpha-VLLM/Lumina-Image-2.0) by Alpha-VLLM.
+
+The model can be loaded with the following code snippet.
+
+```python
+from diffusers import Lumina2Transformer2DModel
+
+transformer = Lumina2Transformer2DModel.from_pretrained("Alpha-VLLM/Lumina-Image-2.0", subfolder="transformer", torch_dtype=torch.bfloat16)
+```
+
+## Lumina2Transformer2DModel
+
+[[autodoc]] Lumina2Transformer2DModel
+
+## Transformer2DModelOutput
+
+[[autodoc]] models.modeling_outputs.Transformer2DModelOutput

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

@@ -0,0 +1,30 @@
+<!--Copyright 2024 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License.
+-->
+
+# OmniGenTransformer2DModel
+
+A Transformer model that accepts multimodal instructions to generate images for [OmniGen](https://github.com/VectorSpaceLab/OmniGen/).
+
+The abstract from the paper is:
+
+*The emergence of Large Language Models (LLMs) has unified language  generation tasks and revolutionized human-machine interaction.  However, in the realm of image generation, a unified model capable of handling various tasks within a single framework remains largely unexplored. In this work, we introduce OmniGen, a new diffusion model for unified image generation. OmniGen is characterized by the following features: 1) Unification: OmniGen not only demonstrates text-to-image generation capabilities but also inherently supports various downstream tasks, such as image editing, subject-driven generation, and visual conditional generation. 2) Simplicity: The architecture of OmniGen is highly simplified, eliminating the need for additional plugins. Moreover, compared to existing diffusion models, it is more user-friendly and can complete complex tasks end-to-end through instructions without the need for extra intermediate steps, greatly simplifying the image generation workflow. 3) Knowledge Transfer: Benefit from learning in a unified format, OmniGen effectively transfers knowledge across different tasks, manages unseen tasks and domains, and exhibits novel capabilities. We also explore the model’s reasoning capabilities and potential applications of the chain-of-thought mechanism.  This work represents the first attempt at a general-purpose image generation model,  and we will release our resources at https://github.com/VectorSpaceLab/OmniGen to foster future advancements.*
+
+```python
+import torch
+from diffusers import OmniGenTransformer2DModel
+
+transformer = OmniGenTransformer2DModel.from_pretrained("Shitao/OmniGen-v1-diffusers", subfolder="transformer", torch_dtype=torch.bfloat16)
+```
+
+## OmniGenTransformer2DModel
+
+[[autodoc]] OmniGenTransformer2DModel

docs/source/en/api/models/wan_transformer_3d.md

@@ -0,0 +1,30 @@
+<!-- Copyright 2024 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License. -->
+
+# WanTransformer3DModel
+
+A Diffusion Transformer model for 3D video-like data was introduced in [Wan 2.1](https://github.com/Wan-Video/Wan2.1) by the Alibaba Wan Team.
+
+The model can be loaded with the following code snippet.
+
+```python
+from diffusers import WanTransformer3DModel
+
+transformer = WanTransformer3DModel.from_pretrained("Wan-AI/Wan2.1-T2V-1.3B-Diffusers", subfolder="transformer", torch_dtype=torch.bfloat16)
+```
+
+## WanTransformer3DModel
+
+[[autodoc]] WanTransformer3DModel
+
+## Transformer2DModelOutput
+
+[[autodoc]] models.modeling_outputs.Transformer2DModelOutput

docs/source/en/api/normalization.md

@@ -29,3 +29,43 @@ Customized normalization layers for supporting various models in 🤗 Diffusers.
 ## AdaGroupNorm
 
 [[autodoc]] models.normalization.AdaGroupNorm
+
+## AdaLayerNormContinuous
+
+[[autodoc]] models.normalization.AdaLayerNormContinuous
+
+## RMSNorm
+
+[[autodoc]] models.normalization.RMSNorm
+
+## GlobalResponseNorm
+
+[[autodoc]] models.normalization.GlobalResponseNorm
+
+
+## LuminaLayerNormContinuous
+[[autodoc]] models.normalization.LuminaLayerNormContinuous
+
+## SD35AdaLayerNormZeroX
+[[autodoc]] models.normalization.SD35AdaLayerNormZeroX
+
+## AdaLayerNormZeroSingle
+[[autodoc]] models.normalization.AdaLayerNormZeroSingle
+
+## LuminaRMSNormZero
+[[autodoc]] models.normalization.LuminaRMSNormZero
+
+## LpNorm
+[[autodoc]] models.normalization.LpNorm
+
+## CogView3PlusAdaLayerNormZeroTextImage
+[[autodoc]] models.normalization.CogView3PlusAdaLayerNormZeroTextImage
+
+## CogVideoXLayerNormZero
+[[autodoc]] models.normalization.CogVideoXLayerNormZero
+
+## MochiRMSNormZero
+[[autodoc]] models.transformers.transformer_mochi.MochiRMSNormZero
+
+## MochiRMSNorm
+[[autodoc]] models.normalization.MochiRMSNorm

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

@@ -14,7 +14,7 @@ specific language governing permissions and limitations under the License.
 
 aMUSEd was introduced in [aMUSEd: An Open MUSE Reproduction](https://huggingface.co/papers/2401.01808) by Suraj Patil, William Berman, Robin Rombach, and Patrick von Platen.
 
-Amused is a lightweight text to image model based off of the [MUSE](https://arxiv.org/abs/2301.00704) architecture. Amused is particularly useful in applications that require a lightweight and fast model such as generating many images quickly at once.
+Amused is a lightweight text to image model based off of the [MUSE](https://huggingface.co/papers/2301.00704) architecture. Amused is particularly useful in applications that require a lightweight and fast model such as generating many images quickly at once.
 
 Amused is a vqvae token based transformer that can generate an image in fewer forward passes than many diffusion models. In contrast with muse, it uses the smaller text encoder CLIP-L/14 instead of t5-xxl. Due to its small parameter count and few forward pass generation process, amused can generate many images quickly. This benefit is seen particularly at larger batch sizes.
 

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

@@ -12,9 +12,13 @@ specific language governing permissions and limitations under the License.
 
 # Text-to-Video Generation with AnimateDiff
 
+<div class="flex flex-wrap space-x-1">
+  <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
+</div>
+
 ## Overview
 
-[AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning](https://arxiv.org/abs/2307.04725) by Yuwei Guo, Ceyuan Yang, Anyi Rao, Yaohui Wang, Yu Qiao, Dahua Lin, Bo Dai.
+[AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning](https://huggingface.co/papers/2307.04725) by Yuwei Guo, Ceyuan Yang, Anyi Rao, Yaohui Wang, Yu Qiao, Dahua Lin, Bo Dai.
 
 The abstract of the paper is the following:
 
@@ -183,7 +187,7 @@ Here are some sample outputs:
 
 ### AnimateDiffSparseControlNetPipeline
 
-[SparseCtrl: Adding Sparse Controls to Text-to-Video Diffusion Models](https://arxiv.org/abs/2311.16933) for achieving controlled generation in text-to-video diffusion models by Yuwei Guo, Ceyuan Yang, Anyi Rao, Maneesh Agrawala, Dahua Lin, and Bo Dai.
+[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:
 
@@ -747,7 +751,7 @@ export_to_gif(frames, "animation.gif")
 
 ## Using FreeInit
 
-[FreeInit: Bridging Initialization Gap in Video Diffusion Models](https://arxiv.org/abs/2312.07537) by Tianxing Wu, Chenyang Si, Yuming Jiang, Ziqi Huang, Ziwei Liu.
+[FreeInit: Bridging Initialization Gap in Video Diffusion Models](https://huggingface.co/papers/2312.07537) by Tianxing Wu, Chenyang Si, Yuming Jiang, Ziqi Huang, Ziwei Liu.
 
 FreeInit is an effective method that improves temporal consistency and overall quality of videos generated using video-diffusion-models without any addition training. It can be applied to AnimateDiff, ModelScope, VideoCrafter and various other video generation models seamlessly at inference time, and works by iteratively refining the latent-initialization noise. More details can be found it the paper.
 
@@ -916,7 +920,7 @@ export_to_gif(frames, "animatelcm-motion-lora.gif")
 
 ## Using FreeNoise
 
-[FreeNoise: Tuning-Free Longer Video Diffusion via Noise Rescheduling](https://arxiv.org/abs/2310.15169) by Haonan Qiu, Menghan Xia, Yong Zhang, Yingqing He, Xintao Wang, Ying Shan, Ziwei Liu.
+[FreeNoise: Tuning-Free Longer Video Diffusion via Noise Rescheduling](https://huggingface.co/papers/2310.15169) by Haonan Qiu, Menghan Xia, Yong Zhang, Yingqing He, Xintao Wang, Ying Shan, Ziwei Liu.
 
 FreeNoise is a sampling mechanism that can generate longer videos with short-video generation models by employing noise-rescheduling, temporal attention over sliding windows, and weighted averaging of latent frames. It also can be used with multiple prompts to allow for interpolated video generations. More details are available in the paper.
 
@@ -962,7 +966,7 @@ pipe.to("cuda")
 prompt = {
     0: "A caterpillar on a leaf, high quality, photorealistic",
     40: "A caterpillar transforming into a cocoon, on a leaf, near flowers, photorealistic",
-    80: "A cocoon on a leaf, flowers in the backgrond, photorealistic",
+    80: "A cocoon on a leaf, flowers in the background, photorealistic",
     120: "A cocoon maturing and a butterfly being born, flowers and leaves visible in the background, photorealistic",
     160: "A beautiful butterfly, vibrant colors, sitting on a leaf, flowers in the background, photorealistic",
     200: "A beautiful butterfly, flying away in a forest, photorealistic",

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

@@ -12,7 +12,7 @@ specific language governing permissions and limitations under the License.
 
 # AudioLDM 2
 
-AudioLDM 2 was proposed in [AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretraining](https://arxiv.org/abs/2308.05734) by Haohe Liu et al. AudioLDM 2 takes a text prompt as input and predicts the corresponding audio. It can generate text-conditional sound effects, human speech and music.
+AudioLDM 2 was proposed in [AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretraining](https://huggingface.co/papers/2308.05734) by Haohe Liu et al. AudioLDM 2 takes a text prompt as input and predicts the corresponding audio. It can generate text-conditional sound effects, human speech and music.
 
 Inspired by [Stable Diffusion](https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion/overview), AudioLDM 2 is a text-to-audio _latent diffusion model (LDM)_ that learns continuous audio representations from text embeddings. Two text encoder models are used to compute the text embeddings from a prompt input: the text-branch of [CLAP](https://huggingface.co/docs/transformers/main/en/model_doc/clap) and the encoder of [Flan-T5](https://huggingface.co/docs/transformers/main/en/model_doc/flan-t5). These text embeddings are then projected to a shared embedding space by an [AudioLDM2ProjectionModel](https://huggingface.co/docs/diffusers/main/api/pipelines/audioldm2#diffusers.AudioLDM2ProjectionModel). A [GPT2](https://huggingface.co/docs/transformers/main/en/model_doc/gpt2) _language model (LM)_ is used to auto-regressively predict eight new embedding vectors, conditional on the projected CLAP and Flan-T5 embeddings. The generated embedding vectors and Flan-T5 text embeddings are used as cross-attention conditioning in the LDM. The [UNet](https://huggingface.co/docs/diffusers/main/en/api/pipelines/audioldm2#diffusers.AudioLDM2UNet2DConditionModel) of AudioLDM 2 is unique in the sense that it takes **two** cross-attention embeddings, as opposed to one cross-attention conditioning, as in most other LDMs.
 

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

@@ -89,6 +89,23 @@ image = pipeline(prompt).images[0]
 image.save("auraflow.png")
 ```
 
+## Support for `torch.compile()`
+
+AuraFlow can be compiled with `torch.compile()` to speed up inference latency even for different resolutions. First, install PyTorch nightly following the instructions from [here](https://pytorch.org/). The snippet below shows the changes needed to enable this:
+
+```diff
++ torch.fx.experimental._config.use_duck_shape = False
++ pipeline.transformer = torch.compile(
+    pipeline.transformer, fullgraph=True, dynamic=True
+)
+```
+
+Specifying `use_duck_shape` to be `False` instructs the compiler if it should use the same symbolic variable to represent input sizes that are the same. For more details, check out [this comment](https://github.com/huggingface/diffusers/pull/11327#discussion_r2047659790).
+
+This enables from 100% (on low resolutions) to a 30% (on 1536x1536 resolution) speed improvements.
+
+Thanks to [AstraliteHeart](https://github.com/huggingface/diffusers/pull/11297/) who helped us rewrite the [`AuraFlowTransformer2DModel`] class so that the above works for different resolutions ([PR](https://github.com/huggingface/diffusers/pull/11297/)).
+
 ## AuraFlowPipeline
 
 [[autodoc]] AuraFlowPipeline

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

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

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

@@ -0,0 +1,71 @@
+<!--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.
+-->
+
+# Chroma
+
+<div class="flex flex-wrap space-x-1">
+  <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
+  <img alt="MPS" src="https://img.shields.io/badge/MPS-000000?style=flat&logo=apple&logoColor=white%22">
+</div>
+
+Chroma is a text to image generation model based on Flux.
+
+Original model checkpoints for Chroma can be found [here](https://huggingface.co/lodestones/Chroma).
+
+<Tip>
+
+Chroma can use all the same optimizations as Flux.
+
+</Tip>
+
+## Inference (Single File)
+
+The `ChromaTransformer2DModel` supports loading checkpoints in the original format. This is also useful when trying to load finetunes or quantized versions of the models that have been published by the community.
+
+The following example demonstrates how to run Chroma from a single file.
+
+Then run the following example
+
+```python
+import torch
+from diffusers import ChromaTransformer2DModel, ChromaPipeline
+from transformers import T5EncoderModel
+
+bfl_repo = "black-forest-labs/FLUX.1-dev"
+dtype = torch.bfloat16
+
+transformer = ChromaTransformer2DModel.from_single_file("https://huggingface.co/lodestones/Chroma/blob/main/chroma-unlocked-v35.safetensors", torch_dtype=dtype)
+
+text_encoder = T5EncoderModel.from_pretrained(bfl_repo, subfolder="text_encoder_2", torch_dtype=dtype)
+tokenizer = T5Tokenizer.from_pretrained(bfl_repo, subfolder="tokenizer_2", torch_dtype=dtype)
+
+pipe = ChromaPipeline.from_pretrained(bfl_repo, transformer=transformer, text_encoder=text_encoder, tokenizer=tokenizer, torch_dtype=dtype)
+
+pipe.enable_model_cpu_offload()
+
+prompt = "A cat holding a sign that says hello world"
+image = pipe(
+    prompt,
+    guidance_scale=4.0,
+    output_type="pil",
+    num_inference_steps=26,
+    generator=torch.Generator("cpu").manual_seed(0)
+).images[0]
+
+image.save("image.png")
+```
+
+## ChromaPipeline
+
+[[autodoc]] ChromaPipeline
+	- all
+	- __call__

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

@@ -13,146 +13,181 @@
 # limitations under the License.
 -->
 
+<div style="float: right;">
+  <div class="flex flex-wrap space-x-1">
+    <a href="https://huggingface.co/docs/diffusers/main/en/tutorials/using_peft_for_inference" target="_blank" rel="noopener">
+      <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
+    </a>
+  </div>
+</div>
+
 # CogVideoX
 
-[CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://arxiv.org/abs/2408.06072) from Tsinghua University & ZhipuAI, by Zhuoyi Yang, Jiayan Teng, Wendi Zheng, Ming Ding, Shiyu Huang, Jiazheng Xu, Yuanming Yang, Wenyi Hong, Xiaohan Zhang, Guanyu Feng, Da Yin, Xiaotao Gu, Yuxuan Zhang, Weihan Wang, Yean Cheng, Ting Liu, Bin Xu, Yuxiao Dong, Jie Tang.
+[CogVideoX](https://huggingface.co/papers/2408.06072) is a large diffusion transformer model - available in 2B and 5B parameters - designed to generate longer and more consistent videos from text. This model uses a 3D causal variational autoencoder to more efficiently process video data by reducing sequence length (and associated training compute) and preventing flickering in generated videos. An "expert" transformer with adaptive LayerNorm improves alignment between text and video, and 3D full attention helps accurately capture motion and time in generated videos.
 
-The abstract from the paper is:
+You can find all the original CogVideoX checkpoints under the [CogVideoX](https://huggingface.co/collections/THUDM/cogvideo-66c08e62f1685a3ade464cce) collection.
 
-*We introduce CogVideoX, a large-scale diffusion transformer model designed for generating videos based on text prompts. To efficently model video data, we propose to levearge a 3D Variational Autoencoder (VAE) to compresses videos along both spatial and temporal dimensions. To improve the text-video alignment, we propose an expert transformer with the expert adaptive LayerNorm to facilitate the deep fusion between the two modalities. By employing a progressive training technique, CogVideoX is adept at producing coherent, long-duration videos characterized by significant motion. In addition, we develop an effectively text-video data processing pipeline that includes various data preprocessing strategies and a video captioning method. It significantly helps enhance the performance of CogVideoX, improving both generation quality and semantic alignment. Results show that CogVideoX demonstrates state-of-the-art performance across both multiple machine metrics and human evaluations. The model weight of CogVideoX-2B is publicly available at https://github.com/THUDM/CogVideo.*
+> [!TIP]
+> Click on the CogVideoX models in the right sidebar for more examples of other video generation tasks.
 
-<Tip>
+The example below demonstrates how to generate a video optimized for memory or inference speed.
 
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+<hfoptions id="usage">
+<hfoption id="memory">
 
-</Tip>
+Refer to the [Reduce memory usage](../../optimization/memory) guide for more details about the various memory saving techniques.
 
-This pipeline was contributed by [zRzRzRzRzRzRzR](https://github.com/zRzRzRzRzRzRzR). The original codebase can be found [here](https://huggingface.co/THUDM). The original weights can be found under [hf.co/THUDM](https://huggingface.co/THUDM).
-
-There are three official CogVideoX checkpoints for text-to-video and video-to-video.
-
-| checkpoints | recommended inference dtype |
-|:---:|:---:|
-| [`THUDM/CogVideoX-2b`](https://huggingface.co/THUDM/CogVideoX-2b) | torch.float16 |
-| [`THUDM/CogVideoX-5b`](https://huggingface.co/THUDM/CogVideoX-5b) | torch.bfloat16 |
-| [`THUDM/CogVideoX1.5-5b`](https://huggingface.co/THUDM/CogVideoX1.5-5b) | torch.bfloat16 |
-
-There are two official CogVideoX checkpoints available for image-to-video.
-
-| checkpoints | recommended inference dtype |
-|:---:|:---:|
-| [`THUDM/CogVideoX-5b-I2V`](https://huggingface.co/THUDM/CogVideoX-5b-I2V) | torch.bfloat16 |
-| [`THUDM/CogVideoX-1.5-5b-I2V`](https://huggingface.co/THUDM/CogVideoX-1.5-5b-I2V) | torch.bfloat16 |
-
-For the CogVideoX 1.5 series:
-- Text-to-video (T2V) works best at a resolution of 1360x768 because it was trained with that specific resolution.
-- Image-to-video (I2V) works for multiple resolutions. The width can vary from 768 to 1360, but the height must be 768. The height/width must be divisible by 16.
-- Both T2V and I2V models support generation with 81 and 161 frames and work best at this value. Exporting videos at 16 FPS is recommended.
-
-There are two official CogVideoX checkpoints that support pose controllable generation (by the [Alibaba-PAI](https://huggingface.co/alibaba-pai) team).
-
-| checkpoints | recommended inference dtype |
-|:---:|:---:|
-| [`alibaba-pai/CogVideoX-Fun-V1.1-2b-Pose`](https://huggingface.co/alibaba-pai/CogVideoX-Fun-V1.1-2b-Pose) | torch.bfloat16 |
-| [`alibaba-pai/CogVideoX-Fun-V1.1-5b-Pose`](https://huggingface.co/alibaba-pai/CogVideoX-Fun-V1.1-5b-Pose) | torch.bfloat16 |
-
-## Inference
-
-Use [`torch.compile`](https://huggingface.co/docs/diffusers/main/en/tutorials/fast_diffusion#torchcompile) to reduce the inference latency.
-
-First, load the pipeline:
-
-```python
-import torch
-from diffusers import CogVideoXPipeline, CogVideoXImageToVideoPipeline
-from diffusers.utils import export_to_video,load_image
-pipe = CogVideoXPipeline.from_pretrained("THUDM/CogVideoX-5b").to("cuda") # or "THUDM/CogVideoX-2b" 
-```
-
-If you are using the image-to-video pipeline, load it as follows:
-
-```python
-pipe = CogVideoXImageToVideoPipeline.from_pretrained("THUDM/CogVideoX-5b-I2V").to("cuda")
-```
-
-Then change the memory layout of the pipelines `transformer` component to `torch.channels_last`:
-
-```python
-pipe.transformer.to(memory_format=torch.channels_last)
-```
-
-Compile the components and run inference:
-
-```python
-pipe.transformer = torch.compile(pipeline.transformer, mode="max-autotune", fullgraph=True)
-
-# CogVideoX works well with long and well-described prompts
-prompt = "A panda, dressed in a small, red jacket and a tiny hat, sits on a wooden stool in a serene bamboo forest. The panda's fluffy paws strum a miniature acoustic guitar, producing soft, melodic tunes. Nearby, a few other pandas gather, watching curiously and some clapping in rhythm. Sunlight filters through the tall bamboo, casting a gentle glow on the scene. The panda's face is expressive, showing concentration and joy as it plays. The background includes a small, flowing stream and vibrant green foliage, enhancing the peaceful and magical atmosphere of this unique musical performance."
-video = pipe(prompt=prompt, guidance_scale=6, num_inference_steps=50).frames[0]
-```
-
-The [T2V benchmark](https://gist.github.com/a-r-r-o-w/5183d75e452a368fd17448fcc810bd3f) results on an 80GB A100 machine are:
-
-```
-Without torch.compile(): Average inference time: 96.89 seconds.
-With torch.compile(): Average inference time: 76.27 seconds.
-```
-
-### Memory optimization
-
-CogVideoX-2b requires about 19 GB of GPU memory to decode 49 frames (6 seconds of video at 8 FPS) with output resolution 720x480 (W x H), which makes it not possible to run on consumer GPUs or free-tier T4 Colab. The following memory optimizations could be used to reduce the memory footprint. For replication, you can refer to [this](https://gist.github.com/a-r-r-o-w/3959a03f15be5c9bd1fe545b09dfcc93) script.
-
-- `pipe.enable_model_cpu_offload()`:
-  - Without enabling cpu offloading, memory usage is `33 GB`
-  - With enabling cpu offloading, memory usage is `19 GB`
-- `pipe.enable_sequential_cpu_offload()`:
-  - Similar to `enable_model_cpu_offload` but can significantly reduce memory usage at the cost of slow inference
-  - When enabled, memory usage is under `4 GB`
-- `pipe.vae.enable_tiling()`:
-  - With enabling cpu offloading and tiling, memory usage is `11 GB`
-- `pipe.vae.enable_slicing()`
-
-## Quantization
-
-Quantization helps reduce the memory requirements of very large models by storing model weights in a lower precision data type. However, quantization may have varying impact on video quality depending on the video model.
-
-Refer to the [Quantization](../../quantization/overview) overview to learn more about supported quantization backends and selecting a quantization backend that supports your use case. The example below demonstrates how to load a quantized [`CogVideoXPipeline`] for inference with bitsandbytes.
+The quantized CogVideoX 5B model below requires ~16GB of VRAM.
 
 ```py
 import torch
-from diffusers import BitsAndBytesConfig as DiffusersBitsAndBytesConfig, CogVideoXTransformer3DModel, CogVideoXPipeline
+from diffusers import CogVideoXPipeline, AutoModel
+from diffusers.quantizers import PipelineQuantizationConfig
+from diffusers.hooks import apply_group_offloading
 from diffusers.utils import export_to_video
-from transformers import BitsAndBytesConfig as BitsAndBytesConfig, T5EncoderModel
 
-quant_config = BitsAndBytesConfig(load_in_8bit=True)
-text_encoder_8bit = T5EncoderModel.from_pretrained(
-    "THUDM/CogVideoX-2b",
-    subfolder="text_encoder",
-    quantization_config=quant_config,
-    torch_dtype=torch.float16,
+# quantize weights to int8 with torchao
+pipeline_quant_config = PipelineQuantizationConfig(
+  quant_backend="torchao",
+  quant_kwargs={"quant_type": "int8wo"},
+  components_to_quantize=["transformer"]
 )
 
-quant_config = DiffusersBitsAndBytesConfig(load_in_8bit=True)
-transformer_8bit = CogVideoXTransformer3DModel.from_pretrained(
-    "THUDM/CogVideoX-2b",
+# fp8 layerwise weight-casting
+transformer = AutoModel.from_pretrained(
+    "THUDM/CogVideoX-5b",
     subfolder="transformer",
-    quantization_config=quant_config,
-    torch_dtype=torch.float16,
+    torch_dtype=torch.bfloat16
+)
+transformer.enable_layerwise_casting(
+    storage_dtype=torch.float8_e4m3fn, compute_dtype=torch.bfloat16
 )
 
 pipeline = CogVideoXPipeline.from_pretrained(
-    "THUDM/CogVideoX-2b",
-    text_encoder=text_encoder_8bit,
-    transformer=transformer_8bit,
-    torch_dtype=torch.float16,
-    device_map="balanced",
+    "THUDM/CogVideoX-5b",
+    transformer=transformer,
+    quantization_config=pipeline_quant_config,
+    torch_dtype=torch.bfloat16
 )
+pipeline.to("cuda")
 
-prompt = "A detailed wooden toy ship with intricately carved masts and sails is seen gliding smoothly over a plush, blue carpet that mimics the waves of the sea. The ship's hull is painted a rich brown, with tiny windows. The carpet, soft and textured, provides a perfect backdrop, resembling an oceanic expanse. Surrounding the ship are various other toys and children's items, hinting at a playful environment. The scene captures the innocence and imagination of childhood, with the toy ship's journey symbolizing endless adventures in a whimsical, indoor setting."
-video = pipeline(prompt=prompt, guidance_scale=6, num_inference_steps=50).frames[0]
-export_to_video(video, "ship.mp4", fps=8)
+# model-offloading
+pipeline.enable_model_cpu_offload()
+
+prompt = """
+A detailed wooden toy ship with intricately carved masts and sails is seen gliding smoothly over a plush, blue carpet that mimics the waves of the sea. 
+The ship's hull is painted a rich brown, with tiny windows. The carpet, soft and textured, provides a perfect backdrop, resembling an oceanic expanse. 
+Surrounding the ship are various other toys and children's items, hinting at a playful environment. The scene captures the innocence and imagination of childhood, 
+with the toy ship's journey symbolizing endless adventures in a whimsical, indoor setting.
+"""
+
+video = pipeline(
+    prompt=prompt,
+    guidance_scale=6,
+    num_inference_steps=50
+).frames[0]
+export_to_video(video, "output.mp4", fps=8)
 ```
 
+</hfoption>
+<hfoption id="inference speed">
+
+[Compilation](../../optimization/fp16#torchcompile) is slow the first time but subsequent calls to the pipeline are faster.
+
+The average inference time with torch.compile on a 80GB A100 is 76.27 seconds compared to 96.89 seconds for an uncompiled model.
+
+```py
+import torch
+from diffusers import CogVideoXPipeline
+from diffusers.utils import export_to_video
+
+pipeline = CogVideoXPipeline.from_pretrained(
+    "THUDM/CogVideoX-2b",
+    torch_dtype=torch.float16
+).to("cuda")
+
+# torch.compile
+pipeline.transformer.to(memory_format=torch.channels_last)
+pipeline.transformer = torch.compile(
+    pipeline.transformer, mode="max-autotune", fullgraph=True
+)
+
+prompt = """
+A detailed wooden toy ship with intricately carved masts and sails is seen gliding smoothly over a plush, blue carpet that mimics the waves of the sea. 
+The ship's hull is painted a rich brown, with tiny windows. The carpet, soft and textured, provides a perfect backdrop, resembling an oceanic expanse. 
+Surrounding the ship are various other toys and children's items, hinting at a playful environment. The scene captures the innocence and imagination of childhood, 
+with the toy ship's journey symbolizing endless adventures in a whimsical, indoor setting.
+"""
+
+video = pipeline(
+    prompt=prompt,
+    guidance_scale=6,
+    num_inference_steps=50
+).frames[0]
+export_to_video(video, "output.mp4", fps=8)
+```
+
+</hfoption>
+</hfoptions>
+
+## Notes
+
+- CogVideoX supports LoRAs with [`~loaders.CogVideoXLoraLoaderMixin.load_lora_weights`].
+
+  <details>
+  <summary>Show example code</summary>
+
+  ```py
+  import torch
+  from diffusers import CogVideoXPipeline
+  from diffusers.hooks import apply_group_offloading
+  from diffusers.utils import export_to_video
+
+  pipeline = CogVideoXPipeline.from_pretrained(
+      "THUDM/CogVideoX-5b",
+      torch_dtype=torch.bfloat16
+  )
+  pipeline.to("cuda")
+
+  # load LoRA weights
+  pipeline.load_lora_weights("finetrainers/CogVideoX-1.5-crush-smol-v0", adapter_name="crush-lora")
+  pipeline.set_adapters("crush-lora", 0.9)
+
+  # model-offloading
+  pipeline.enable_model_cpu_offload()
+
+  prompt = """
+  PIKA_CRUSH A large metal cylinder is seen pressing down on a pile of Oreo cookies, flattening them as if they were under a hydraulic press.
+  """
+  negative_prompt = "inconsistent motion, blurry motion, worse quality, degenerate outputs, deformed outputs"
+
+  video = pipeline(
+      prompt=prompt, 
+      negative_prompt=negative_prompt, 
+      num_frames=81, 
+      height=480,
+      width=768,
+      num_inference_steps=50
+  ).frames[0]
+  export_to_video(video, "output.mp4", fps=16)
+  ```
+
+  </details>
+
+- The text-to-video (T2V) checkpoints work best with a resolution of 1360x768 because that was the resolution it was pretrained on.
+
+- The image-to-video (I2V) checkpoints work with multiple resolutions. The width can vary from 768 to 1360, but the height must be 758. Both height and width must be divisible by 16.
+
+- Both T2V and I2V checkpoints work best with 81 and 161 frames. It is recommended to export the generated video at 16fps.
+
+- Refer to the table below to view memory usage when various memory-saving techniques are enabled.
+
+  | method | memory usage (enabled) | memory usage (disabled) |
+  |---|---|---|
+  | enable_model_cpu_offload | 19GB | 33GB |
+  | enable_sequential_cpu_offload | <4GB | ~33GB (very slow inference speed) |
+  | enable_tiling | 11GB (with enable_model_cpu_offload) | --- |
+ 
 ## CogVideoXPipeline
 
 [[autodoc]] CogVideoXPipeline

docs/source/en/api/pipelines/cogview4.md

@@ -0,0 +1,34 @@
+<!--Copyright 2024 The HuggingFace Team. All rights reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+-->
+
+# CogView4
+
+<Tip>
+
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+
+</Tip>
+
+This pipeline was contributed by [zRzRzRzRzRzRzR](https://github.com/zRzRzRzRzRzRzR). The original codebase can be found [here](https://huggingface.co/THUDM). The original weights can be found under [hf.co/THUDM](https://huggingface.co/THUDM).
+
+## CogView4Pipeline
+
+[[autodoc]] CogView4Pipeline
+  - all
+  - __call__
+
+## CogView4PipelineOutput
+
+[[autodoc]] pipelines.cogview4.pipeline_output.CogView4PipelineOutput

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

@@ -15,7 +15,11 @@
 
 # ConsisID
 
-[Identity-Preserving Text-to-Video Generation by Frequency Decomposition](https://arxiv.org/abs/2411.17440) from Peking University & University of Rochester & etc, by Shenghai Yuan, Jinfa Huang, Xianyi He, Yunyang Ge, Yujun Shi, Liuhan Chen, Jiebo Luo, Li Yuan.
+<div class="flex flex-wrap space-x-1">
+  <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
+</div>
+
+[Identity-Preserving Text-to-Video Generation by Frequency Decomposition](https://huggingface.co/papers/2411.17440) from Peking University & University of Rochester & etc, by Shenghai Yuan, Jinfa Huang, Xianyi He, Yunyang Ge, Yujun Shi, Liuhan Chen, Jiebo Luo, Li Yuan.
 
 The abstract from the paper is:
 

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

@@ -12,6 +12,10 @@ specific language governing permissions and limitations under the License.
 
 # FluxControlInpaint
 
+<div class="flex flex-wrap space-x-1">
+  <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
+</div>
+
 FluxControlInpaintPipeline is an implementation of Inpainting for Flux.1 Depth/Canny models. It is a pipeline that allows you to inpaint images using the Flux.1 Depth/Canny models. The pipeline takes an image and a mask as input and returns the inpainted image.
 
 FLUX.1 Depth and Canny [dev] is a 12 billion parameter rectified flow transformer capable of generating an image based on a text description while following the structure of a given input image. **This is not a ControlNet model**.

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

@@ -12,6 +12,10 @@ specific language governing permissions and limitations under the License.
 
 # ControlNet
 
+<div class="flex flex-wrap space-x-1">
+  <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
+</div>
+
 ControlNet was introduced in [Adding Conditional Control to Text-to-Image Diffusion Models](https://huggingface.co/papers/2302.05543) by Lvmin Zhang, Anyi Rao, and Maneesh Agrawala.
 
 With a ControlNet model, you can provide an additional control image to condition and control Stable Diffusion generation. For example, if you provide a depth map, the ControlNet model generates an image that'll preserve the spatial information from the depth map. It is a more flexible and accurate way to control the image generation process.

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

@@ -12,6 +12,10 @@ specific language governing permissions and limitations under the License.
 
 # ControlNet with Flux.1
 
+<div class="flex flex-wrap space-x-1">
+  <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
+</div>
+
 FluxControlNetPipeline is an implementation of ControlNet for Flux.1.
 
 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/pipelines/controlnet_hunyuandit.md

@@ -12,7 +12,7 @@ specific language governing permissions and limitations under the License.
 
 # ControlNet with Hunyuan-DiT
 
-HunyuanDiTControlNetPipeline is an implementation of ControlNet for [Hunyuan-DiT](https://arxiv.org/abs/2405.08748).
+HunyuanDiTControlNetPipeline 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/pipelines/controlnet_sana.md

@@ -0,0 +1,36 @@
+<!--Copyright 2024 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License.
+-->
+
+# ControlNet
+
+<div class="flex flex-wrap space-x-1">
+  <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
+</div>
+
+ControlNet was introduced in [Adding Conditional Control to Text-to-Image Diffusion Models](https://huggingface.co/papers/2302.05543) by Lvmin Zhang, Anyi Rao, and Maneesh Agrawala.
+
+With a ControlNet model, you can provide an additional control image to condition and control Stable Diffusion generation. For example, if you provide a depth map, the ControlNet model generates an image that'll preserve the spatial information from the depth map. It is a more flexible and accurate way to control the image generation process.
+
+The abstract from the paper is:
+
+*We present ControlNet, a neural network architecture to add spatial conditioning controls to large, pretrained text-to-image diffusion models. ControlNet locks the production-ready large diffusion models, and reuses their deep and robust encoding layers pretrained with billions of images as a strong backbone to learn a diverse set of conditional controls. The neural architecture is connected with "zero convolutions" (zero-initialized convolution layers) that progressively grow the parameters from zero and ensure that no harmful noise could affect the finetuning. We test various conditioning controls, eg, edges, depth, segmentation, human pose, etc, with Stable Diffusion, using single or multiple conditions, with or without prompts. We show that the training of ControlNets is robust with small (<50k) and large (>1m) datasets. Extensive results show that ControlNet may facilitate wider applications to control image diffusion models.*
+
+This pipeline was contributed by [ishan24](https://huggingface.co/ishan24). ❤️
+The original codebase can be found at [NVlabs/Sana](https://github.com/NVlabs/Sana), and you can find official ControlNet checkpoints on [Efficient-Large-Model's](https://huggingface.co/Efficient-Large-Model) Hub profile.
+
+## SanaControlNetPipeline
+[[autodoc]] SanaControlNetPipeline
+	- all
+	- __call__
+
+## SanaPipelineOutput
+[[autodoc]] pipelines.sana.pipeline_output.SanaPipelineOutput

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

@@ -12,6 +12,10 @@ specific language governing permissions and limitations under the License.
 
 # ControlNet with Stable Diffusion 3
 
+<div class="flex flex-wrap space-x-1">
+  <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
+</div>
+
 StableDiffusion3ControlNetPipeline is an implementation of ControlNet for Stable Diffusion 3.
 
 ControlNet was introduced in [Adding Conditional Control to Text-to-Image Diffusion Models](https://huggingface.co/papers/2302.05543) by Lvmin Zhang, Anyi Rao, and Maneesh Agrawala.

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

@@ -12,6 +12,10 @@ specific language governing permissions and limitations under the License.
 
 # ControlNet with Stable Diffusion XL
 
+<div class="flex flex-wrap space-x-1">
+  <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
+</div>
+
 ControlNet was introduced in [Adding Conditional Control to Text-to-Image Diffusion Models](https://huggingface.co/papers/2302.05543) by Lvmin Zhang, Anyi Rao, and Maneesh Agrawala.
 
 With a ControlNet model, you can provide an additional control image to condition and control Stable Diffusion generation. For example, if you provide a depth map, the ControlNet model generates an image that'll preserve the spatial information from the depth map. It is a more flexible and accurate way to control the image generation process.

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

@@ -12,6 +12,10 @@ specific language governing permissions and limitations under the License.
 
 # ControlNetUnion
 
+<div class="flex flex-wrap space-x-1">
+  <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
+</div>
+
 ControlNetUnionModel is an implementation of ControlNet for Stable Diffusion XL.
 
 The ControlNet model was introduced in [ControlNetPlus](https://github.com/xinsir6/ControlNetPlus) by xinsir6. It supports multiple conditioning inputs without increasing computation.

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

@@ -12,6 +12,10 @@ specific language governing permissions and limitations under the License.
 
 # ControlNet-XS
 
+<div class="flex flex-wrap space-x-1">
+  <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
+</div>
+
 ControlNet-XS was introduced in [ControlNet-XS](https://vislearn.github.io/ControlNet-XS/) by Denis Zavadski and Carsten Rother. It is based on the observation that the control model in the [original ControlNet](https://huggingface.co/papers/2302.05543) can be made much smaller and still produce good results.
 
 Like the original ControlNet model, you can provide an additional control image to condition and control Stable Diffusion generation. For example, if you provide a depth map, the ControlNet model generates an image that'll preserve the spatial information from the depth map. It is a more flexible and accurate way to control the image generation process.

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

@@ -0,0 +1,41 @@
+<!-- Copyright 2024 The HuggingFace Team. All rights reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License. -->
+
+# Cosmos
+
+[Cosmos World Foundation Model Platform for Physical AI](https://huggingface.co/papers/2501.03575) by NVIDIA.
+
+*Physical AI needs to be trained digitally first. It needs a digital twin of itself, the policy model, and a digital twin of the world, the world model. In this paper, we present the Cosmos World Foundation Model Platform to help developers build customized world models for their Physical AI setups. We position a world foundation model as a general-purpose world model that can be fine-tuned into customized world models for downstream applications. Our platform covers a video curation pipeline, pre-trained world foundation models, examples of post-training of pre-trained world foundation models, and video tokenizers. To help Physical AI builders solve the most critical problems of our society, we make our platform open-source and our models open-weight with permissive licenses available via https://github.com/NVIDIA/Cosmos.*
+
+<Tip>
+
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+
+</Tip>
+
+## CosmosTextToWorldPipeline
+
+[[autodoc]] CosmosTextToWorldPipeline
+  - all
+  - __call__
+
+## CosmosVideoToWorldPipeline
+
+[[autodoc]] CosmosVideoToWorldPipeline
+  - all
+  - __call__
+
+## CosmosPipelineOutput
+
+[[autodoc]] pipelines.cosmos.pipeline_output.CosmosPipelineOutput

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

@@ -12,6 +12,11 @@ specific language governing permissions and limitations under the License.
 
 # DeepFloyd IF
 
+<div class="flex flex-wrap space-x-1">
+  <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
+  <img alt="MPS" src="https://img.shields.io/badge/MPS-000000?style=flat&logo=apple&logoColor=white%22">
+</div>
+
 ## Overview
 
 DeepFloyd IF is a novel state-of-the-art open-source text-to-image model with a high degree of photorealism and language understanding.
@@ -342,7 +347,7 @@ pipe.to("cuda")
 image = pipe(image=image, prompt="<prompt>", strength=0.3).images
 ```
 
-You can also use [`torch.compile`](../../optimization/torch2.0). Note that we have not exhaustively tested `torch.compile`
+You can also use [`torch.compile`](../../optimization/fp16#torchcompile). Note that we have not exhaustively tested `torch.compile`
 with IF and it might not give expected results.
 
 ```py

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

@@ -0,0 +1,88 @@
+<!--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.
+-->
+
+# EasyAnimate
+[EasyAnimate](https://github.com/aigc-apps/EasyAnimate) by Alibaba PAI.
+
+The description from it's GitHub page:
+*EasyAnimate is a pipeline based on the transformer architecture, designed for generating AI images and videos, and for training baseline models and Lora models for Diffusion Transformer. We support direct prediction from pre-trained EasyAnimate models, allowing for the generation of videos with various resolutions, approximately 6 seconds in length, at 8fps (EasyAnimateV5.1, 1 to 49 frames). Additionally, users can train their own baseline and Lora models for specific style transformations.*
+
+This pipeline was contributed by [bubbliiiing](https://github.com/bubbliiiing). The original codebase can be found [here](https://huggingface.co/alibaba-pai). The original weights can be found under [hf.co/alibaba-pai](https://huggingface.co/alibaba-pai).
+
+There are two official EasyAnimate checkpoints for text-to-video and video-to-video.
+
+| checkpoints | recommended inference dtype |
+|:---:|:---:|
+| [`alibaba-pai/EasyAnimateV5.1-12b-zh`](https://huggingface.co/alibaba-pai/EasyAnimateV5.1-12b-zh) | torch.float16 |
+| [`alibaba-pai/EasyAnimateV5.1-12b-zh-InP`](https://huggingface.co/alibaba-pai/EasyAnimateV5.1-12b-zh-InP) | torch.float16 |
+
+There is one official EasyAnimate checkpoints available for image-to-video and video-to-video.
+
+| checkpoints | recommended inference dtype |
+|:---:|:---:|
+| [`alibaba-pai/EasyAnimateV5.1-12b-zh-InP`](https://huggingface.co/alibaba-pai/EasyAnimateV5.1-12b-zh-InP) | torch.float16 |
+
+There are two official EasyAnimate checkpoints available for control-to-video.
+
+| checkpoints | recommended inference dtype |
+|:---:|:---:|
+| [`alibaba-pai/EasyAnimateV5.1-12b-zh-Control`](https://huggingface.co/alibaba-pai/EasyAnimateV5.1-12b-zh-Control) | torch.float16 |
+| [`alibaba-pai/EasyAnimateV5.1-12b-zh-Control-Camera`](https://huggingface.co/alibaba-pai/EasyAnimateV5.1-12b-zh-Control-Camera) | torch.float16 |
+
+For the EasyAnimateV5.1 series:
+- Text-to-video (T2V) and Image-to-video (I2V) works for multiple resolutions. The width and height can vary from 256 to 1024.
+- Both T2V and I2V models support generation with 1~49 frames and work best at this value. Exporting videos at 8 FPS is recommended.
+
+## Quantization
+
+Quantization helps reduce the memory requirements of very large models by storing model weights in a lower precision data type. However, quantization may have varying impact on video quality depending on the video model.
+
+Refer to the [Quantization](../../quantization/overview) overview to learn more about supported quantization backends and selecting a quantization backend that supports your use case. The example below demonstrates how to load a quantized [`EasyAnimatePipeline`] for inference with bitsandbytes.
+
+```py
+import torch
+from diffusers import BitsAndBytesConfig as DiffusersBitsAndBytesConfig, EasyAnimateTransformer3DModel, EasyAnimatePipeline
+from diffusers.utils import export_to_video
+
+quant_config = DiffusersBitsAndBytesConfig(load_in_8bit=True)
+transformer_8bit = EasyAnimateTransformer3DModel.from_pretrained(
+    "alibaba-pai/EasyAnimateV5.1-12b-zh",
+    subfolder="transformer",
+    quantization_config=quant_config,
+    torch_dtype=torch.float16,
+)
+
+pipeline = EasyAnimatePipeline.from_pretrained(
+    "alibaba-pai/EasyAnimateV5.1-12b-zh",
+    transformer=transformer_8bit,
+    torch_dtype=torch.float16,
+    device_map="balanced",
+)
+
+prompt = "A cat walks on the grass, realistic style."
+negative_prompt = "bad detailed"
+video = pipeline(prompt=prompt, negative_prompt=negative_prompt, num_frames=49, num_inference_steps=30).frames[0]
+export_to_video(video, "cat.mp4", fps=8)
+```
+
+## EasyAnimatePipeline
+
+[[autodoc]] EasyAnimatePipeline
+  - all
+  - __call__
+
+## EasyAnimatePipelineOutput
+
+[[autodoc]] pipelines.easyanimate.pipeline_output.EasyAnimatePipelineOutput

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

@@ -12,6 +12,11 @@ specific language governing permissions and limitations under the License.
 
 # Flux
 
+<div class="flex flex-wrap space-x-1">
+  <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
+  <img alt="MPS" src="https://img.shields.io/badge/MPS-000000?style=flat&logo=apple&logoColor=white%22">
+</div>
+
 Flux is a series of text-to-image generation models based on diffusion transformers. To know more about Flux, check out the original [blog post](https://blackforestlabs.ai/announcing-black-forest-labs/) by the creators of Flux, Black Forest Labs.
 
 Original model checkpoints for Flux can be found [here](https://huggingface.co/black-forest-labs). Original inference code can be found [here](https://github.com/black-forest-labs/flux).
@@ -309,7 +314,120 @@ image.save("output.png")
 
 When unloading the Control LoRA weights, call `pipe.unload_lora_weights(reset_to_overwritten_params=True)` to reset the `pipe.transformer` completely back to its original form. The resultant pipeline can then be used with methods like [`DiffusionPipeline.from_pipe`]. More details about this argument are available in [this PR](https://github.com/huggingface/diffusers/pull/10397).
 
-## Running FP16 inference
+## IP-Adapter
+
+<Tip>
+
+Check out [IP-Adapter](../../../using-diffusers/ip_adapter) to learn more about how IP-Adapters work.
+
+</Tip>
+
+An IP-Adapter lets you prompt Flux with images, in addition to the text prompt. This is especially useful when describing complex concepts that are difficult to articulate through text alone and you have reference images.
+
+```python
+import torch
+from diffusers import FluxPipeline
+from diffusers.utils import load_image
+
+pipe = FluxPipeline.from_pretrained(
+    "black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16
+).to("cuda")
+
+image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/flux_ip_adapter_input.jpg").resize((1024, 1024))
+
+pipe.load_ip_adapter(
+    "XLabs-AI/flux-ip-adapter",
+    weight_name="ip_adapter.safetensors",
+    image_encoder_pretrained_model_name_or_path="openai/clip-vit-large-patch14"
+)
+pipe.set_ip_adapter_scale(1.0)
+
+image = pipe(
+    width=1024,
+    height=1024,
+    prompt="wearing sunglasses",
+    negative_prompt="",
+    true_cfg_scale=4.0,
+    generator=torch.Generator().manual_seed(4444),
+    ip_adapter_image=image,
+).images[0]
+
+image.save('flux_ip_adapter_output.jpg')
+```
+
+<div class="justify-center">
+    <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/flux_ip_adapter_output.jpg"/>
+    <figcaption class="mt-2 text-sm text-center text-gray-500">IP-Adapter examples with prompt "wearing sunglasses"</figcaption>
+</div>
+
+## Optimize
+
+Flux is a very large model and requires ~50GB of RAM/VRAM to load all the modeling components. Enable some of the optimizations below to lower the memory requirements.
+
+### Group offloading
+
+[Group offloading](../../optimization/memory#group-offloading) lowers VRAM usage by offloading groups of internal layers rather than the whole model or weights. You need to use [`~hooks.apply_group_offloading`] on all the model components of a pipeline. The `offload_type` parameter allows you to toggle between block and leaf-level offloading. Setting it to `leaf_level` offloads the lowest leaf-level parameters to the CPU instead of offloading at the module-level.
+
+On CUDA devices that support asynchronous data streaming, set `use_stream=True` to overlap data transfer and computation to accelerate inference.
+
+> [!TIP]
+> It is possible to mix block and leaf-level offloading for different components in a pipeline.
+
+```py
+import torch
+from diffusers import FluxPipeline
+from diffusers.hooks import apply_group_offloading
+
+model_id = "black-forest-labs/FLUX.1-dev"
+dtype = torch.bfloat16
+pipe = FluxPipeline.from_pretrained(
+	model_id,
+	torch_dtype=dtype,
+)
+
+apply_group_offloading(
+    pipe.transformer,
+    offload_type="leaf_level",
+    offload_device=torch.device("cpu"),
+    onload_device=torch.device("cuda"),
+    use_stream=True,
+)
+apply_group_offloading(
+    pipe.text_encoder, 
+    offload_device=torch.device("cpu"),
+    onload_device=torch.device("cuda"),
+    offload_type="leaf_level",
+    use_stream=True,
+)
+apply_group_offloading(
+    pipe.text_encoder_2, 
+    offload_device=torch.device("cpu"),
+    onload_device=torch.device("cuda"),
+    offload_type="leaf_level",
+    use_stream=True,
+)
+apply_group_offloading(
+    pipe.vae, 
+    offload_device=torch.device("cpu"),
+    onload_device=torch.device("cuda"),
+    offload_type="leaf_level",
+    use_stream=True,
+)
+
+prompt="A cat wearing sunglasses and working as a lifeguard at pool."
+
+generator = torch.Generator().manual_seed(181201)
+image = pipe(
+    prompt,
+    width=576,
+    height=1024,
+    num_inference_steps=30,
+    generator=generator
+).images[0]
+image
+```
+
+### Running FP16 inference
 
 Flux can generate high-quality images with FP16 (i.e. to accelerate inference on Turing/Volta GPUs) but produces different outputs compared to FP32/BF16. The issue is that some activations in the text encoders have to be clipped when running in FP16, which affects the overall image. Forcing text encoders to run with FP32 inference thus removes this output difference. See [here](https://github.com/huggingface/diffusers/pull/9097#issuecomment-2272292516) for details.
 
@@ -338,7 +456,7 @@ out = pipe(
 out.save("image.png")
 ```
 
-## Quantization
+### Quantization
 
 Quantization helps reduce the memory requirements of very large models by storing model weights in a lower precision data type. However, quantization may have varying impact on video quality depending on the video model.
 

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

@@ -0,0 +1,209 @@
+<!-- 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. -->
+
+# Framepack
+
+<div class="flex flex-wrap space-x-1">
+  <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
+</div>
+
+[Packing Input Frame Context in Next-Frame Prediction Models for Video Generation](https://huggingface.co/papers/2504.12626) by Lvmin Zhang and Maneesh Agrawala.
+
+*We present a neural network structure, FramePack, to train next-frame (or next-frame-section) prediction models for video generation. The FramePack compresses input frames to make the transformer context length a fixed number regardless of the video length. As a result, we are able to process a large number of frames using video diffusion with computation bottleneck similar to image diffusion. This also makes the training video batch sizes significantly higher (batch sizes become comparable to image diffusion training). We also propose an anti-drifting sampling method that generates frames in inverted temporal order with early-established endpoints to avoid exposure bias (error accumulation over iterations). Finally, we show that existing video diffusion models can be finetuned with FramePack, and their visual quality may be improved because the next-frame prediction supports more balanced diffusion schedulers with less extreme flow shift timesteps.*
+
+<Tip>
+
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+
+</Tip>
+
+## Available models
+
+| Model name | Description |
+|:---|:---|
+- [`lllyasviel/FramePackI2V_HY`](https://huggingface.co/lllyasviel/FramePackI2V_HY) | Trained with the "inverted anti-drifting" strategy as described in the paper. Inference requires setting `sampling_type="inverted_anti_drifting"` when running the pipeline. |
+- [`lllyasviel/FramePack_F1_I2V_HY_20250503`](https://huggingface.co/lllyasviel/FramePack_F1_I2V_HY_20250503) | Trained with a novel anti-drifting strategy but inference is performed in "vanilla" strategy as described in the paper. Inference requires setting `sampling_type="vanilla"` when running the pipeline. |
+
+## Usage
+
+Refer to the pipeline documentation for basic usage examples. The following section contains examples of offloading, different sampling methods, quantization, and more.
+
+### First and last frame to video
+
+The following example shows how to use Framepack with start and end image controls, using the inverted anti-drifiting sampling model.
+
+```python
+import torch
+from diffusers import HunyuanVideoFramepackPipeline, HunyuanVideoFramepackTransformer3DModel
+from diffusers.utils import export_to_video, load_image
+from transformers import SiglipImageProcessor, SiglipVisionModel
+
+transformer = HunyuanVideoFramepackTransformer3DModel.from_pretrained(
+    "lllyasviel/FramePackI2V_HY", torch_dtype=torch.bfloat16
+)
+feature_extractor = SiglipImageProcessor.from_pretrained(
+    "lllyasviel/flux_redux_bfl", subfolder="feature_extractor"
+)
+image_encoder = SiglipVisionModel.from_pretrained(
+    "lllyasviel/flux_redux_bfl", subfolder="image_encoder", torch_dtype=torch.float16
+)
+pipe = HunyuanVideoFramepackPipeline.from_pretrained(
+    "hunyuanvideo-community/HunyuanVideo",
+    transformer=transformer,
+    feature_extractor=feature_extractor,
+    image_encoder=image_encoder,
+    torch_dtype=torch.float16,
+)
+
+# Enable memory optimizations
+pipe.enable_model_cpu_offload()
+pipe.vae.enable_tiling()
+
+prompt = "CG animation style, a small blue bird takes off from the ground, flapping its wings. The bird's feathers are delicate, with a unique pattern on its chest. The background shows a blue sky with white clouds under bright sunshine. The camera follows the bird upward, capturing its flight and the vastness of the sky from a close-up, low-angle perspective."
+first_image = load_image(
+    "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/flf2v_input_first_frame.png"
+)
+last_image = load_image(
+    "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/flf2v_input_last_frame.png"
+)
+output = pipe(
+    image=first_image,
+    last_image=last_image,
+    prompt=prompt,
+    height=512,
+    width=512,
+    num_frames=91,
+    num_inference_steps=30,
+    guidance_scale=9.0,
+    generator=torch.Generator().manual_seed(0),
+    sampling_type="inverted_anti_drifting",
+).frames[0]
+export_to_video(output, "output.mp4", fps=30)
+```
+
+### Vanilla sampling
+
+The following example shows how to use Framepack with the F1 model trained with vanilla sampling but new regulation approach for anti-drifting.
+
+```python
+import torch
+from diffusers import HunyuanVideoFramepackPipeline, HunyuanVideoFramepackTransformer3DModel
+from diffusers.utils import export_to_video, load_image
+from transformers import SiglipImageProcessor, SiglipVisionModel
+
+transformer = HunyuanVideoFramepackTransformer3DModel.from_pretrained(
+    "lllyasviel/FramePack_F1_I2V_HY_20250503", torch_dtype=torch.bfloat16
+)
+feature_extractor = SiglipImageProcessor.from_pretrained(
+    "lllyasviel/flux_redux_bfl", subfolder="feature_extractor"
+)
+image_encoder = SiglipVisionModel.from_pretrained(
+    "lllyasviel/flux_redux_bfl", subfolder="image_encoder", torch_dtype=torch.float16
+)
+pipe = HunyuanVideoFramepackPipeline.from_pretrained(
+    "hunyuanvideo-community/HunyuanVideo",
+    transformer=transformer,
+    feature_extractor=feature_extractor,
+    image_encoder=image_encoder,
+    torch_dtype=torch.float16,
+)
+
+# Enable memory optimizations
+pipe.enable_model_cpu_offload()
+pipe.vae.enable_tiling()
+
+image = load_image(
+    "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/penguin.png"
+)
+output = pipe(
+    image=image,
+    prompt="A penguin dancing in the snow",
+    height=832,
+    width=480,
+    num_frames=91,
+    num_inference_steps=30,
+    guidance_scale=9.0,
+    generator=torch.Generator().manual_seed(0),
+    sampling_type="vanilla",
+).frames[0]
+export_to_video(output, "output.mp4", fps=30)
+```
+
+### Group offloading
+
+Group offloading ([`~hooks.apply_group_offloading`]) provides aggressive memory optimizations for offloading internal parts of any model to the CPU, with possibly no additional overhead to generation time. If you have very low VRAM available, this approach may be suitable for you depending on the amount of CPU RAM available.
+
+```python
+import torch
+from diffusers import HunyuanVideoFramepackPipeline, HunyuanVideoFramepackTransformer3DModel
+from diffusers.hooks import apply_group_offloading
+from diffusers.utils import export_to_video, load_image
+from transformers import SiglipImageProcessor, SiglipVisionModel
+
+transformer = HunyuanVideoFramepackTransformer3DModel.from_pretrained(
+    "lllyasviel/FramePack_F1_I2V_HY_20250503", torch_dtype=torch.bfloat16
+)
+feature_extractor = SiglipImageProcessor.from_pretrained(
+    "lllyasviel/flux_redux_bfl", subfolder="feature_extractor"
+)
+image_encoder = SiglipVisionModel.from_pretrained(
+    "lllyasviel/flux_redux_bfl", subfolder="image_encoder", torch_dtype=torch.float16
+)
+pipe = HunyuanVideoFramepackPipeline.from_pretrained(
+    "hunyuanvideo-community/HunyuanVideo",
+    transformer=transformer,
+    feature_extractor=feature_extractor,
+    image_encoder=image_encoder,
+    torch_dtype=torch.float16,
+)
+
+# Enable group offloading
+onload_device = torch.device("cuda")
+offload_device = torch.device("cpu")
+list(map(
+    lambda x: apply_group_offloading(x, onload_device, offload_device, offload_type="leaf_level", use_stream=True, low_cpu_mem_usage=True),
+    [pipe.text_encoder, pipe.text_encoder_2, pipe.transformer]
+))
+pipe.image_encoder.to(onload_device)
+pipe.vae.to(onload_device)
+pipe.vae.enable_tiling()
+
+image = load_image(
+    "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/penguin.png"
+)
+output = pipe(
+    image=image,
+    prompt="A penguin dancing in the snow",
+    height=832,
+    width=480,
+    num_frames=91,
+    num_inference_steps=30,
+    guidance_scale=9.0,
+    generator=torch.Generator().manual_seed(0),
+    sampling_type="vanilla",
+).frames[0]
+print(f"Max memory: {torch.cuda.max_memory_allocated() / 1024**3:.3f} GB")
+export_to_video(output, "output.mp4", fps=30)
+```
+
+## HunyuanVideoFramepackPipeline
+
+[[autodoc]] HunyuanVideoFramepackPipeline
+  - all
+  - __call__
+
+## HunyuanVideoPipelineOutput
+
+[[autodoc]] pipelines.hunyuan_video.pipeline_output.HunyuanVideoPipelineOutput
+

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

@@ -0,0 +1,43 @@
+<!-- Copyright 2024 The HuggingFace Team. All rights reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License. -->
+
+# HiDreamImage
+
+[HiDream-I1](https://huggingface.co/HiDream-ai) by HiDream.ai
+
+<Tip>
+
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+
+</Tip>
+
+## Available models
+
+The following models are available for the [`HiDreamImagePipeline`](text-to-image) pipeline:
+
+| Model name | Description |
+|:---|:---|
+| [`HiDream-ai/HiDream-I1-Full`](https://huggingface.co/HiDream-ai/HiDream-I1-Full) | - |
+| [`HiDream-ai/HiDream-I1-Dev`](https://huggingface.co/HiDream-ai/HiDream-I1-Dev) | - |
+| [`HiDream-ai/HiDream-I1-Fast`](https://huggingface.co/HiDream-ai/HiDream-I1-Fast) | - |
+
+## HiDreamImagePipeline
+
+[[autodoc]] HiDreamImagePipeline
+  - all
+  - __call__
+
+## HiDreamImagePipelineOutput
+
+[[autodoc]] pipelines.hidream_image.pipeline_output.HiDreamImagePipelineOutput

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

@@ -12,57 +12,171 @@
 # See the License for the specific language governing permissions and
 # limitations under the License. -->
 
+<div style="float: right;">
+  <div class="flex flex-wrap space-x-1">
+    <a href="https://huggingface.co/docs/diffusers/main/en/tutorials/using_peft_for_inference" target="_blank" rel="noopener">
+      <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
+    </a>
+  </div>
+</div>
+
 # HunyuanVideo
 
-[HunyuanVideo](https://www.arxiv.org/abs/2412.03603) by Tencent.
+[HunyuanVideo](https://huggingface.co/papers/2412.03603) is a 13B parameter diffusion transformer model designed to be competitive with closed-source video foundation models and enable wider community access. This model uses a "dual-stream to single-stream" architecture to separately process the video and text tokens first, before concatenating and feeding them to the transformer to fuse the multimodal information. A pretrained multimodal large language model (MLLM) is used as the encoder because it has better image-text alignment, better image detail description and reasoning, and it can be used as a zero-shot learner if system instructions are added to user prompts. Finally, HunyuanVideo uses a 3D causal variational autoencoder to more efficiently process video data at the original resolution and frame rate.
 
-*Recent advancements in video generation have significantly impacted daily life for both individuals and industries. However, the leading video generation models remain closed-source, resulting in a notable performance gap between industry capabilities and those available to the public. In this report, we introduce HunyuanVideo, an innovative open-source video foundation model that demonstrates performance in video generation comparable to, or even surpassing, that of leading closed-source models. HunyuanVideo encompasses a comprehensive framework that integrates several key elements, including data curation, advanced architectural design, progressive model scaling and training, and an efficient infrastructure tailored for large-scale model training and inference. As a result, we successfully trained a video generative model with over 13 billion parameters, making it the largest among all open-source models. We conducted extensive experiments and implemented a series of targeted designs to ensure high visual quality, motion dynamics, text-video alignment, and advanced filming techniques. According to evaluations by professionals, HunyuanVideo outperforms previous state-of-the-art models, including Runway Gen-3, Luma 1.6, and three top-performing Chinese video generative models. By releasing the code for the foundation model and its applications, we aim to bridge the gap between closed-source and open-source communities. This initiative will empower individuals within the community to experiment with their ideas, fostering a more dynamic and vibrant video generation ecosystem. The code is publicly available at [this https URL](https://github.com/tencent/HunyuanVideo).*
+You can find all the original HunyuanVideo checkpoints under the [Tencent](https://huggingface.co/tencent) organization.
 
-<Tip>
+> [!TIP]
+> Click on the HunyuanVideo models in the right sidebar for more examples of video generation tasks.
+>
+> The examples below use a checkpoint from [hunyuanvideo-community](https://huggingface.co/hunyuanvideo-community) because the weights are stored in a layout compatible with Diffusers.
 
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+The example below demonstrates how to generate a video optimized for memory or inference speed.
 
-</Tip>
+<hfoptions id="usage">
+<hfoption id="memory">
 
-Recommendations for inference:
-- Both text encoders should be in `torch.float16`.
-- Transformer should be in `torch.bfloat16`.
-- VAE should be in `torch.float16`.
-- `num_frames` should be of the form `4 * k + 1`, for example `49` or `129`.
-- For smaller resolution videos, try lower values of `shift` (between `2.0` to `5.0`) in the [Scheduler](https://huggingface.co/docs/diffusers/main/en/api/schedulers/flow_match_euler_discrete#diffusers.FlowMatchEulerDiscreteScheduler.shift). For larger resolution images, try higher values (between `7.0` and `12.0`). The default value is `7.0` for HunyuanVideo.
-- For more information about supported resolutions and other details, please refer to the original repository [here](https://github.com/Tencent/HunyuanVideo/).
+Refer to the [Reduce memory usage](../../optimization/memory) guide for more details about the various memory saving techniques.
 
-## Quantization
-
-Quantization helps reduce the memory requirements of very large models by storing model weights in a lower precision data type. However, quantization may have varying impact on video quality depending on the video model.
-
-Refer to the [Quantization](../../quantization/overview) overview to learn more about supported quantization backends and selecting a quantization backend that supports your use case. The example below demonstrates how to load a quantized [`HunyuanVideoPipeline`] for inference with bitsandbytes.
+The quantized HunyuanVideo model below requires ~14GB of VRAM.
 
 ```py
 import torch
-from diffusers import BitsAndBytesConfig as DiffusersBitsAndBytesConfig, HunyuanVideoTransformer3DModel, HunyuanVideoPipeline
+from diffusers import AutoModel, HunyuanVideoPipeline
+from diffusers.quantizers import PipelineQuantizationConfig
 from diffusers.utils import export_to_video
 
-quant_config = DiffusersBitsAndBytesConfig(load_in_8bit=True)
-transformer_8bit = HunyuanVideoTransformer3DModel.from_pretrained(
-    "hunyuanvideo-community/HunyuanVideo",
-    subfolder="transformer",
-    quantization_config=quant_config,
-    torch_dtype=torch.bfloat16,
+# quantize weights to int4 with bitsandbytes
+pipeline_quant_config = PipelineQuantizationConfig(
+    quant_backend="bitsandbytes_4bit",
+    quant_kwargs={
+      "load_in_4bit": True,
+      "bnb_4bit_quant_type": "nf4",
+      "bnb_4bit_compute_dtype": torch.bfloat16
+      },
+    components_to_quantize=["transformer"]
 )
 
 pipeline = HunyuanVideoPipeline.from_pretrained(
     "hunyuanvideo-community/HunyuanVideo",
-    transformer=transformer_8bit,
-    torch_dtype=torch.float16,
-    device_map="balanced",
+    quantization_config=pipeline_quant_config,
+    torch_dtype=torch.bfloat16,
 )
 
-prompt = "A cat walks on the grass, realistic style."
+# model-offloading and tiling
+pipeline.enable_model_cpu_offload()
+pipeline.vae.enable_tiling()
+
+prompt = "A fluffy teddy bear sits on a bed of soft pillows surrounded by children's toys."
 video = pipeline(prompt=prompt, num_frames=61, num_inference_steps=30).frames[0]
-export_to_video(video, "cat.mp4", fps=15)
+export_to_video(video, "output.mp4", fps=15)
 ```
 
+</hfoption>
+<hfoption id="inference speed">
+
+[Compilation](../../optimization/fp16#torchcompile) is slow the first time but subsequent calls to the pipeline are faster.
+
+```py
+import torch
+from diffusers import AutoModel, HunyuanVideoPipeline
+from diffusers.quantizers import PipelineQuantizationConfig
+from diffusers.utils import export_to_video
+
+# quantize weights to int4 with bitsandbytes
+pipeline_quant_config = PipelineQuantizationConfig(
+    quant_backend="bitsandbytes_4bit",
+    quant_kwargs={
+      "load_in_4bit": True,
+      "bnb_4bit_quant_type": "nf4",
+      "bnb_4bit_compute_dtype": torch.bfloat16
+      },
+    components_to_quantize=["transformer"]
+)
+
+pipeline = HunyuanVideoPipeline.from_pretrained(
+    "hunyuanvideo-community/HunyuanVideo",
+    quantization_config=pipeline_quant_config,
+    torch_dtype=torch.bfloat16,
+)
+
+# model-offloading and tiling
+pipeline.enable_model_cpu_offload()
+pipeline.vae.enable_tiling()
+
+# torch.compile
+pipeline.transformer.to(memory_format=torch.channels_last)
+pipeline.transformer = torch.compile(
+    pipeline.transformer, mode="max-autotune", fullgraph=True
+)
+
+prompt = "A fluffy teddy bear sits on a bed of soft pillows surrounded by children's toys."
+video = pipeline(prompt=prompt, num_frames=61, num_inference_steps=30).frames[0]
+export_to_video(video, "output.mp4", fps=15)
+```
+
+</hfoption>
+</hfoptions>
+
+## Notes
+
+- HunyuanVideo supports LoRAs with [`~loaders.HunyuanVideoLoraLoaderMixin.load_lora_weights`].
+
+  <details>
+  <summary>Show example code</summary>
+
+  ```py
+  import torch
+  from diffusers import AutoModel, HunyuanVideoPipeline
+  from diffusers.quantizers import PipelineQuantizationConfig
+  from diffusers.utils import export_to_video
+
+  # quantize weights to int4 with bitsandbytes
+  pipeline_quant_config = PipelineQuantizationConfig(
+      quant_backend="bitsandbytes_4bit",
+      quant_kwargs={
+        "load_in_4bit": True,
+        "bnb_4bit_quant_type": "nf4",
+        "bnb_4bit_compute_dtype": torch.bfloat16
+        },
+      components_to_quantize=["transformer"]
+  )
+
+  pipeline = HunyuanVideoPipeline.from_pretrained(
+      "hunyuanvideo-community/HunyuanVideo",
+      quantization_config=pipeline_quant_config,
+      torch_dtype=torch.bfloat16,
+  )
+
+  # load LoRA weights
+  pipeline.load_lora_weights("https://huggingface.co/lucataco/hunyuan-steamboat-willie-10", adapter_name="steamboat-willie")
+  pipeline.set_adapters("steamboat-willie", 0.9)
+
+  # model-offloading and tiling
+  pipeline.enable_model_cpu_offload()
+  pipeline.vae.enable_tiling()
+
+  # use "In the style of SWR" to trigger the LoRA
+  prompt = """
+  In the style of SWR. A black and white animated scene featuring a fluffy teddy bear sits on a bed of soft pillows surrounded by children's toys.
+  """
+  video = pipeline(prompt=prompt, num_frames=61, num_inference_steps=30).frames[0]
+  export_to_video(video, "output.mp4", fps=15)
+  ```
+
+  </details>
+
+- Refer to the table below for recommended inference values.
+
+  | parameter | recommended value |
+  |---|---|
+  | text encoder dtype | `torch.float16` |
+  | transformer dtype | `torch.bfloat16` |
+  | vae dtype | `torch.float16` |
+  | `num_frames (k)` | 4 * `k` + 1 |
+
+- Try lower `shift` values (`2.0` to `5.0`) for lower resolution videos and higher `shift` values (`7.0` to `12.0`) for higher resolution images.
+
 ## HunyuanVideoPipeline
 
 [[autodoc]] HunyuanVideoPipeline

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

@@ -13,7 +13,7 @@ specific language governing permissions and limitations under the License.
 # Hunyuan-DiT
 ![chinese elements understanding](https://github.com/gnobitab/diffusers-hunyuan/assets/1157982/39b99036-c3cb-4f16-bb1a-40ec25eda573)
 
-[Hunyuan-DiT : A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding](https://arxiv.org/abs/2405.08748) from Tencent Hunyuan.
+[Hunyuan-DiT : A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding](https://huggingface.co/papers/2405.08748) from Tencent Hunyuan.
 
 The abstract from the paper is:
 

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

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

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

@@ -9,6 +9,10 @@ specific language governing permissions and limitations under the License.
 
 # Kandinsky 3
 
+<div class="flex flex-wrap space-x-1">
+  <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
+</div>
+
 Kandinsky 3 is created by [Vladimir Arkhipkin](https://github.com/oriBetelgeuse),[Anastasia Maltseva](https://github.com/NastyaMittseva),[Igor Pavlov](https://github.com/boomb0om),[Andrei Filatov](https://github.com/anvilarth),[Arseniy Shakhmatov](https://github.com/cene555),[Andrey Kuznetsov](https://github.com/kuznetsoffandrey),[Denis Dimitrov](https://github.com/denndimitrov), [Zein Shaheen](https://github.com/zeinsh)
 
 The description from it's GitHub page:

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

@@ -12,6 +12,11 @@ specific language governing permissions and limitations under the License.
 
 # Kolors: Effective Training of Diffusion Model for Photorealistic Text-to-Image Synthesis
 
+<div class="flex flex-wrap space-x-1">
+  <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
+  <img alt="MPS" src="https://img.shields.io/badge/MPS-000000?style=flat&logo=apple&logoColor=white%22">
+</div>
+
 ![](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/kolors/kolors_header_collage.png)
 
 Kolors is a large-scale text-to-image generation model based on latent diffusion, developed by [the Kuaishou Kolors team](https://github.com/Kwai-Kolors/Kolors). Trained on billions of text-image pairs, Kolors exhibits significant advantages over both open-source and closed-source models in visual quality, complex semantic accuracy, and text rendering for both Chinese and English characters. Furthermore, Kolors supports both Chinese and English inputs, demonstrating strong performance in understanding and generating Chinese-specific content. For more details, please refer to this [technical report](https://github.com/Kwai-Kolors/Kolors/blob/master/imgs/Kolors_paper.pdf).

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

@@ -12,6 +12,10 @@ specific language governing permissions and limitations under the License.
 
 # Latent Consistency Models
 
+<div class="flex flex-wrap space-x-1">
+  <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
+</div>
+
 Latent Consistency Models (LCMs) were proposed in [Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference](https://huggingface.co/papers/2310.04378) by Simian Luo, Yiqin Tan, Longbo Huang, Jian Li, and Hang Zhao.
 
 The abstract of the paper is as follows:

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

@@ -16,13 +16,13 @@
 
 ![latte text-to-video](https://github.com/Vchitect/Latte/blob/52bc0029899babbd6e9250384c83d8ed2670ff7a/visuals/latte.gif?raw=true)
 
-[Latte: Latent Diffusion Transformer for Video Generation](https://arxiv.org/abs/2401.03048) from Monash University, Shanghai AI Lab, Nanjing University, and Nanyang Technological University.
+[Latte: Latent Diffusion Transformer for Video Generation](https://huggingface.co/papers/2401.03048) from Monash University, Shanghai AI Lab, Nanjing University, and Nanyang Technological University.
 
 The abstract from the paper is:
 
 *We propose a novel Latent Diffusion Transformer, namely Latte, for video generation. Latte first extracts spatio-temporal tokens from input videos and then adopts a series of Transformer blocks to model video distribution in the latent space. In order to model a substantial number of tokens extracted from videos, four efficient variants are introduced from the perspective of decomposing the spatial and temporal dimensions of input videos. To improve the quality of generated videos, we determine the best practices of Latte through rigorous experimental analysis, including video clip patch embedding, model variants, timestep-class information injection, temporal positional embedding, and learning strategies. Our comprehensive evaluation demonstrates that Latte achieves state-of-the-art performance across four standard video generation datasets, i.e., FaceForensics, SkyTimelapse, UCF101, and Taichi-HD. In addition, we extend Latte to text-to-video generation (T2V) task, where Latte achieves comparable results compared to recent T2V models. We strongly believe that Latte provides valuable insights for future research on incorporating Transformers into diffusion models for video generation.*
 
-**Highlights**: Latte is a latent diffusion transformer proposed as a backbone for modeling different modalities (trained for text-to-video generation here). It achieves state-of-the-art performance across four standard video benchmarks - [FaceForensics](https://arxiv.org/abs/1803.09179), [SkyTimelapse](https://arxiv.org/abs/1709.07592), [UCF101](https://arxiv.org/abs/1212.0402) and [Taichi-HD](https://arxiv.org/abs/2003.00196). To prepare and download the datasets for evaluation, please refer to [this https URL](https://github.com/Vchitect/Latte/blob/main/docs/datasets_evaluation.md).
+**Highlights**: Latte is a latent diffusion transformer proposed as a backbone for modeling different modalities (trained for text-to-video generation here). It achieves state-of-the-art performance across four standard video benchmarks - [FaceForensics](https://huggingface.co/papers/1803.09179), [SkyTimelapse](https://huggingface.co/papers/1709.07592), [UCF101](https://huggingface.co/papers/1212.0402) and [Taichi-HD](https://huggingface.co/papers/2003.00196). To prepare and download the datasets for evaluation, please refer to [this https URL](https://github.com/Vchitect/Latte/blob/main/docs/datasets_evaluation.md).
 
 This pipeline was contributed by [maxin-cn](https://github.com/maxin-cn). The original codebase can be found [here](https://github.com/Vchitect/Latte). The original weights can be found under [hf.co/maxin-cn](https://huggingface.co/maxin-cn).
 

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

@@ -12,6 +12,10 @@ specific language governing permissions and limitations under the License.
 
 # LEDITS++
 
+<div class="flex flex-wrap space-x-1">
+  <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
+</div>
+
 LEDITS++ was proposed in [LEDITS++: Limitless Image Editing using Text-to-Image Models](https://huggingface.co/papers/2311.16711) by Manuel Brack, Felix Friedrich, Katharina Kornmeier, Linoy Tsaban, Patrick Schramowski, Kristian Kersting, Apolinário Passos.
 
 The abstract from the paper is:
@@ -25,7 +29,7 @@ You can find additional information about LEDITS++ on the [project page](https:/
 </Tip>
 
 <Tip warning={true}>
-Due to some backward compatability issues with the current diffusers implementation of [`~schedulers.DPMSolverMultistepScheduler`] this implementation of LEdits++ can no longer guarantee perfect inversion.
+Due to some backward compatibility issues with the current diffusers implementation of [`~schedulers.DPMSolverMultistepScheduler`] this implementation of LEdits++ can no longer guarantee perfect inversion.
 This issue is unlikely to have any noticeable effects on applied use-cases. However, we provide an alternative implementation that guarantees perfect inversion in a dedicated [GitHub repo](https://github.com/ml-research/ledits_pp).
 </Tip>
 

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

@@ -12,119 +12,67 @@
 # See the License for the specific language governing permissions and
 # limitations under the License. -->
 
-# LTX Video
+<div style="float: right;">
+  <div class="flex flex-wrap space-x-1">
+    <a href="https://huggingface.co/docs/diffusers/main/en/tutorials/using_peft_for_inference" target="_blank" rel="noopener">
+      <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
+    </a>
+    <img alt="MPS" src="https://img.shields.io/badge/MPS-000000?style=flat&logo=apple&logoColor=white%22">
+  </div>
+</div>
 
-[LTX Video](https://huggingface.co/Lightricks/LTX-Video) is the first DiT-based video generation model capable of generating high-quality videos in real-time. It produces 24 FPS videos at a 768x512 resolution faster than they can be watched. Trained on a large-scale dataset of diverse videos, the model generates high-resolution videos with realistic and varied content. We provide a model for both text-to-video as well as image + text-to-video usecases.
+# LTX-Video
 
-<Tip>
+[LTX-Video](https://huggingface.co/Lightricks/LTX-Video) is a diffusion transformer designed for fast and real-time generation of high-resolution videos from text and images. The main feature of LTX-Video is the Video-VAE. The Video-VAE has a higher pixel to latent compression ratio (1:192) which enables more efficient video data processing and faster generation speed. To support and prevent finer details from being lost during generation, the Video-VAE decoder performs the latent to pixel conversion *and* the last denoising step.
 
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+You can find all the original LTX-Video checkpoints under the [Lightricks](https://huggingface.co/Lightricks) organization.
 
-</Tip>
+> [!TIP]
+> Click on the LTX-Video models in the right sidebar for more examples of other video generation tasks.
 
-Available models:
+The example below demonstrates how to generate a video optimized for memory or inference speed.
 
-|  Model name   | Recommended dtype |
-|:-------------:|:-----------------:|
-| [`LTX Video 0.9.0`](https://huggingface.co/Lightricks/LTX-Video/blob/main/ltx-video-2b-v0.9.safetensors) | `torch.bfloat16` |
-| [`LTX Video 0.9.1`](https://huggingface.co/Lightricks/LTX-Video/blob/main/ltx-video-2b-v0.9.1.safetensors) | `torch.bfloat16` |
+<hfoptions id="usage">
+<hfoption id="memory">
 
-Note: The recommended dtype is for the transformer component. The VAE and text encoders can be either `torch.float32`, `torch.bfloat16` or `torch.float16` but the recommended dtype is `torch.bfloat16` as used in the original repository.
+Refer to the [Reduce memory usage](../../optimization/memory) guide for more details about the various memory saving techniques.
 
-## Loading Single Files
-
-Loading the original LTX Video checkpoints is also possible with [`~ModelMixin.from_single_file`]. We recommend using `from_single_file` for the Lightricks series of models, as they plan to release multiple models in the future in the single file format.
-
-```python
-import torch
-from diffusers import AutoencoderKLLTXVideo, LTXImageToVideoPipeline, LTXVideoTransformer3DModel
-
-# `single_file_url` could also be https://huggingface.co/Lightricks/LTX-Video/ltx-video-2b-v0.9.1.safetensors
-single_file_url = "https://huggingface.co/Lightricks/LTX-Video/ltx-video-2b-v0.9.safetensors"
-transformer = LTXVideoTransformer3DModel.from_single_file(
-  single_file_url, torch_dtype=torch.bfloat16
-)
-vae = AutoencoderKLLTXVideo.from_single_file(single_file_url, torch_dtype=torch.bfloat16)
-pipe = LTXImageToVideoPipeline.from_pretrained(
-  "Lightricks/LTX-Video", transformer=transformer, vae=vae, torch_dtype=torch.bfloat16
-)
-
-# ... inference code ...
-```
-
-Alternatively, the pipeline can be used to load the weights with [`~FromSingleFileMixin.from_single_file`].
-
-```python
-import torch
-from diffusers import LTXImageToVideoPipeline
-from transformers import T5EncoderModel, T5Tokenizer
-
-single_file_url = "https://huggingface.co/Lightricks/LTX-Video/ltx-video-2b-v0.9.safetensors"
-text_encoder = T5EncoderModel.from_pretrained(
-  "Lightricks/LTX-Video", subfolder="text_encoder", torch_dtype=torch.bfloat16
-)
-tokenizer = T5Tokenizer.from_pretrained(
-  "Lightricks/LTX-Video", subfolder="tokenizer", torch_dtype=torch.bfloat16
-)
-pipe = LTXImageToVideoPipeline.from_single_file(
-  single_file_url, text_encoder=text_encoder, tokenizer=tokenizer, torch_dtype=torch.bfloat16
-)
-```
-
-Loading [LTX GGUF checkpoints](https://huggingface.co/city96/LTX-Video-gguf) are also supported:
+The LTX-Video model below requires ~10GB of VRAM.
 
 ```py
 import torch
+from diffusers import LTXPipeline, AutoModel
+from diffusers.hooks import apply_group_offloading
 from diffusers.utils import export_to_video
-from diffusers import LTXPipeline, LTXVideoTransformer3DModel, GGUFQuantizationConfig
 
-ckpt_path = (
-    "https://huggingface.co/city96/LTX-Video-gguf/blob/main/ltx-video-2b-v0.9-Q3_K_S.gguf"
-)
-transformer = LTXVideoTransformer3DModel.from_single_file(
-    ckpt_path,
-    quantization_config=GGUFQuantizationConfig(compute_dtype=torch.bfloat16),
-    torch_dtype=torch.bfloat16,
-)
-pipe = LTXPipeline.from_pretrained(
+# fp8 layerwise weight-casting
+transformer = AutoModel.from_pretrained(
     "Lightricks/LTX-Video",
-    transformer=transformer,
-    torch_dtype=torch.bfloat16,
+    subfolder="transformer",
+    torch_dtype=torch.bfloat16
+)
+transformer.enable_layerwise_casting(
+    storage_dtype=torch.float8_e4m3fn, compute_dtype=torch.bfloat16
 )
-pipe.enable_model_cpu_offload()
 
-prompt = "A woman with long brown hair and light skin smiles at another woman with long blonde hair. The woman with brown hair wears a black jacket and has a small, barely noticeable mole on her right cheek. The camera angle is a close-up, focused on the woman with brown hair's face. The lighting is warm and natural, likely from the setting sun, casting a soft glow on the scene. The scene appears to be real-life footage"
+pipeline = LTXPipeline.from_pretrained("Lightricks/LTX-Video", transformer=transformer, torch_dtype=torch.bfloat16)
+
+# group-offloading
+onload_device = torch.device("cuda")
+offload_device = torch.device("cpu")
+pipeline.transformer.enable_group_offload(onload_device=onload_device, offload_device=offload_device, offload_type="leaf_level", use_stream=True)
+apply_group_offloading(pipeline.text_encoder, onload_device=onload_device, offload_type="block_level", num_blocks_per_group=2)
+apply_group_offloading(pipeline.vae, onload_device=onload_device, offload_type="leaf_level")
+
+prompt = """
+A woman with long brown hair and light skin smiles at another woman with long blonde hair.
+The woman with brown hair wears a black jacket and has a small, barely noticeable mole on her right cheek.
+The camera angle is a close-up, focused on the woman with brown hair's face. The lighting is warm and 
+natural, likely from the setting sun, casting a soft glow on the scene. The scene appears to be real-life footage
+"""
 negative_prompt = "worst quality, inconsistent motion, blurry, jittery, distorted"
 
-video = pipe(
-    prompt=prompt,
-    negative_prompt=negative_prompt,
-    width=704,
-    height=480,
-    num_frames=161,
-    num_inference_steps=50,
-).frames[0]
-export_to_video(video, "output_gguf_ltx.mp4", fps=24)
-```
-
-Make sure to read the [documentation on GGUF](../../quantization/gguf) to learn more about our GGUF support.
-
-<!-- TODO(aryan): Update this when official weights are supported -->
-
-Loading and running inference with [LTX Video 0.9.1](https://huggingface.co/Lightricks/LTX-Video/blob/main/ltx-video-2b-v0.9.1.safetensors) weights.
-
-```python
-import torch
-from diffusers import LTXPipeline
-from diffusers.utils import export_to_video
-
-pipe = LTXPipeline.from_pretrained("a-r-r-o-w/LTX-Video-0.9.1-diffusers", torch_dtype=torch.bfloat16)
-pipe.to("cuda")
-
-prompt = "A woman with long brown hair and light skin smiles at another woman with long blonde hair. The woman with brown hair wears a black jacket and has a small, barely noticeable mole on her right cheek. The camera angle is a close-up, focused on the woman with brown hair's face. The lighting is warm and natural, likely from the setting sun, casting a soft glow on the scene. The scene appears to be real-life footage"
-negative_prompt = "worst quality, inconsistent motion, blurry, jittery, distorted"
-
-video = pipe(
+video = pipeline(
     prompt=prompt,
     negative_prompt=negative_prompt,
     width=768,
@@ -137,49 +85,306 @@ video = pipe(
 export_to_video(video, "output.mp4", fps=24)
 ```
 
-Refer to [this section](https://huggingface.co/docs/diffusers/main/en/api/pipelines/cogvideox#memory-optimization) to learn more about optimizing memory consumption.
+</hfoption>
+<hfoption id="inference speed">
 
-## Quantization
-
-Quantization helps reduce the memory requirements of very large models by storing model weights in a lower precision data type. However, quantization may have varying impact on video quality depending on the video model.
-
-Refer to the [Quantization](../../quantization/overview) overview to learn more about supported quantization backends and selecting a quantization backend that supports your use case. The example below demonstrates how to load a quantized [`LTXPipeline`] for inference with bitsandbytes.
+[Compilation](../../optimization/fp16#torchcompile) is slow the first time but subsequent calls to the pipeline are faster.
 
 ```py
 import torch
-from diffusers import BitsAndBytesConfig as DiffusersBitsAndBytesConfig, LTXVideoTransformer3DModel, LTXPipeline
+from diffusers import LTXPipeline
 from diffusers.utils import export_to_video
-from transformers import BitsAndBytesConfig as BitsAndBytesConfig, T5EncoderModel
-
-quant_config = BitsAndBytesConfig(load_in_8bit=True)
-text_encoder_8bit = T5EncoderModel.from_pretrained(
-    "Lightricks/LTX-Video",
-    subfolder="text_encoder",
-    quantization_config=quant_config,
-    torch_dtype=torch.float16,
-)
-
-quant_config = DiffusersBitsAndBytesConfig(load_in_8bit=True)
-transformer_8bit = LTXVideoTransformer3DModel.from_pretrained(
-    "Lightricks/LTX-Video",
-    subfolder="transformer",
-    quantization_config=quant_config,
-    torch_dtype=torch.float16,
-)
 
 pipeline = LTXPipeline.from_pretrained(
-    "Lightricks/LTX-Video",
-    text_encoder=text_encoder_8bit,
-    transformer=transformer_8bit,
-    torch_dtype=torch.float16,
-    device_map="balanced",
+    "Lightricks/LTX-Video", torch_dtype=torch.bfloat16
 )
 
-prompt = "A detailed wooden toy ship with intricately carved masts and sails is seen gliding smoothly over a plush, blue carpet that mimics the waves of the sea. The ship's hull is painted a rich brown, with tiny windows. The carpet, soft and textured, provides a perfect backdrop, resembling an oceanic expanse. Surrounding the ship are various other toys and children's items, hinting at a playful environment. The scene captures the innocence and imagination of childhood, with the toy ship's journey symbolizing endless adventures in a whimsical, indoor setting."
-video = pipeline(prompt=prompt, num_frames=161, num_inference_steps=50).frames[0]
-export_to_video(video, "ship.mp4", fps=24)
+# torch.compile
+pipeline.transformer.to(memory_format=torch.channels_last)
+pipeline.transformer = torch.compile(
+    pipeline.transformer, mode="max-autotune", fullgraph=True
+)
+
+prompt = """
+A woman with long brown hair and light skin smiles at another woman with long blonde hair.
+The woman with brown hair wears a black jacket and has a small, barely noticeable mole on her right cheek.
+The camera angle is a close-up, focused on the woman with brown hair's face. The lighting is warm and 
+natural, likely from the setting sun, casting a soft glow on the scene. The scene appears to be real-life footage
+"""
+negative_prompt = "worst quality, inconsistent motion, blurry, jittery, distorted"
+
+video = pipeline(
+    prompt=prompt,
+    negative_prompt=negative_prompt,
+    width=768,
+    height=512,
+    num_frames=161,
+    decode_timestep=0.03,
+    decode_noise_scale=0.025,
+    num_inference_steps=50,
+).frames[0]
+export_to_video(video, "output.mp4", fps=24)
 ```
 
+</hfoption>
+</hfoptions>
+
+## Notes
+
+- Refer to the following recommended settings for generation from the [LTX-Video](https://github.com/Lightricks/LTX-Video) repository.
+
+  - The recommended dtype for the transformer, VAE, and text encoder is `torch.bfloat16`. The VAE and text encoder can also be `torch.float32` or `torch.float16`.
+  - For guidance-distilled variants of LTX-Video, set `guidance_scale` to `1.0`. The `guidance_scale` for any other model should be set higher, like `5.0`, for good generation quality.
+  - For timestep-aware VAE variants (LTX-Video 0.9.1 and above), set `decode_timestep` to `0.05` and `image_cond_noise_scale` to `0.025`.
+  - For variants that support interpolation between multiple conditioning images and videos (LTX-Video 0.9.5 and above), use similar images and videos for the best results. Divergence from the conditioning inputs may lead to abrupt transitionts in the generated video.
+
+- LTX-Video 0.9.7 includes a spatial latent upscaler and a 13B parameter transformer. During inference, a low resolution video is quickly generated first and then upscaled and refined.
+
+  <details>
+  <summary>Show example code</summary>
+
+  ```py
+  import torch
+  from diffusers import LTXConditionPipeline, LTXLatentUpsamplePipeline
+  from diffusers.pipelines.ltx.pipeline_ltx_condition import LTXVideoCondition
+  from diffusers.utils import export_to_video, load_video
+
+  pipeline = LTXConditionPipeline.from_pretrained("Lightricks/LTX-Video-0.9.7-dev", torch_dtype=torch.bfloat16)
+  pipeline_upsample = LTXLatentUpsamplePipeline.from_pretrained("Lightricks/ltxv-spatial-upscaler-0.9.7", vae=pipeline.vae, torch_dtype=torch.bfloat16)
+  pipeline.to("cuda")
+  pipe_upsample.to("cuda")
+  pipeline.vae.enable_tiling()
+
+  def round_to_nearest_resolution_acceptable_by_vae(height, width):
+      height = height - (height % pipeline.vae_temporal_compression_ratio)
+      width = width - (width % pipeline.vae_temporal_compression_ratio)
+      return height, width
+
+  video = load_video(
+      "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cosmos/cosmos-video2world-input-vid.mp4"
+  )[:21]  # only use the first 21 frames as conditioning
+  condition1 = LTXVideoCondition(video=video, frame_index=0)
+
+  prompt = """
+  The video depicts a winding mountain road covered in snow, with a single vehicle 
+  traveling along it. The road is flanked by steep, rocky cliffs and sparse vegetation. 
+  The landscape is characterized by rugged terrain and a river visible in the distance. 
+  The scene captures the solitude and beauty of a winter drive through a mountainous region.
+  """
+  negative_prompt = "worst quality, inconsistent motion, blurry, jittery, distorted"
+  expected_height, expected_width = 768, 1152
+  downscale_factor = 2 / 3
+  num_frames = 161
+
+  # 1. Generate video at smaller resolution
+  # Text-only conditioning is also supported without the need to pass `conditions`
+  downscaled_height, downscaled_width = int(expected_height * downscale_factor), int(expected_width * downscale_factor)
+  downscaled_height, downscaled_width = round_to_nearest_resolution_acceptable_by_vae(downscaled_height, downscaled_width)
+  latents = pipeline(
+      conditions=[condition1],
+      prompt=prompt,
+      negative_prompt=negative_prompt,
+      width=downscaled_width,
+      height=downscaled_height,
+      num_frames=num_frames,
+      num_inference_steps=30,
+      decode_timestep=0.05,
+      decode_noise_scale=0.025,
+      image_cond_noise_scale=0.0,
+      guidance_scale=5.0,
+      guidance_rescale=0.7,
+      generator=torch.Generator().manual_seed(0),
+      output_type="latent",
+  ).frames
+
+  # 2. Upscale generated video using latent upsampler with fewer inference steps
+  # The available latent upsampler upscales the height/width by 2x
+  upscaled_height, upscaled_width = downscaled_height * 2, downscaled_width * 2
+  upscaled_latents = pipe_upsample(
+      latents=latents,
+      output_type="latent"
+  ).frames
+
+  # 3. Denoise the upscaled video with few steps to improve texture (optional, but recommended)
+  video = pipeline(
+      conditions=[condition1],
+      prompt=prompt,
+      negative_prompt=negative_prompt,
+      width=upscaled_width,
+      height=upscaled_height,
+      num_frames=num_frames,
+      denoise_strength=0.4,  # Effectively, 4 inference steps out of 10
+      num_inference_steps=10,
+      latents=upscaled_latents,
+      decode_timestep=0.05,
+      decode_noise_scale=0.025,
+      image_cond_noise_scale=0.0,
+      guidance_scale=5.0,
+      guidance_rescale=0.7,
+      generator=torch.Generator().manual_seed(0),
+      output_type="pil",
+  ).frames[0]
+
+  # 4. Downscale the video to the expected resolution
+  video = [frame.resize((expected_width, expected_height)) for frame in video]
+
+  export_to_video(video, "output.mp4", fps=24)
+  ```
+
+  </details>
+
+- LTX-Video 0.9.7 distilled model is guidance and timestep-distilled to speedup generation. It requires `guidance_scale` to be set to `1.0` and `num_inference_steps` should be set between `4` and `10` for good generation quality. You should also use the following custom timesteps for the best results.
+
+  - Base model inference to prepare for upscaling: `[1000, 993, 987, 981, 975, 909, 725, 0.03]`.
+  - Upscaling: `[1000, 909, 725, 421, 0]`.
+
+  <details>
+  <summary>Show example code</summary>
+
+  ```py
+  import torch
+  from diffusers import LTXConditionPipeline, LTXLatentUpsamplePipeline
+  from diffusers.pipelines.ltx.pipeline_ltx_condition import LTXVideoCondition
+  from diffusers.utils import export_to_video, load_video
+
+  pipeline = LTXConditionPipeline.from_pretrained("Lightricks/LTX-Video-0.9.7-distilled", torch_dtype=torch.bfloat16)
+  pipe_upsample = LTXLatentUpsamplePipeline.from_pretrained("Lightricks/ltxv-spatial-upscaler-0.9.7", vae=pipeline.vae, torch_dtype=torch.bfloat16)
+  pipeline.to("cuda")
+  pipe_upsample.to("cuda")
+  pipeline.vae.enable_tiling()
+
+  def round_to_nearest_resolution_acceptable_by_vae(height, width):
+      height = height - (height % pipeline.vae_temporal_compression_ratio)
+      width = width - (width % pipeline.vae_temporal_compression_ratio)
+      return height, width
+
+  prompt = """
+  artistic anatomical 3d render, utlra quality, human half full male body with transparent 
+  skin revealing structure instead of organs, muscular, intricate creative patterns, 
+  monochromatic with backlighting, lightning mesh, scientific concept art, blending biology 
+  with botany, surreal and ethereal quality, unreal engine 5, ray tracing, ultra realistic, 
+  16K UHD, rich details. camera zooms out in a rotating fashion
+  """
+  negative_prompt = "worst quality, inconsistent motion, blurry, jittery, distorted"
+  expected_height, expected_width = 768, 1152
+  downscale_factor = 2 / 3
+  num_frames = 161
+
+  # 1. Generate video at smaller resolution
+  downscaled_height, downscaled_width = int(expected_height * downscale_factor), int(expected_width * downscale_factor)
+  downscaled_height, downscaled_width = round_to_nearest_resolution_acceptable_by_vae(downscaled_height, downscaled_width)
+  latents = pipeline(
+      prompt=prompt,
+      negative_prompt=negative_prompt,
+      width=downscaled_width,
+      height=downscaled_height,
+      num_frames=num_frames,
+      timesteps=[1000, 993, 987, 981, 975, 909, 725, 0.03],
+      decode_timestep=0.05,
+      decode_noise_scale=0.025,
+      image_cond_noise_scale=0.0,
+      guidance_scale=1.0,
+      guidance_rescale=0.7,
+      generator=torch.Generator().manual_seed(0),
+      output_type="latent",
+  ).frames
+
+  # 2. Upscale generated video using latent upsampler with fewer inference steps
+  # The available latent upsampler upscales the height/width by 2x
+  upscaled_height, upscaled_width = downscaled_height * 2, downscaled_width * 2
+  upscaled_latents = pipe_upsample(
+      latents=latents,
+      adain_factor=1.0,
+      output_type="latent"
+  ).frames
+
+  # 3. Denoise the upscaled video with few steps to improve texture (optional, but recommended)
+  video = pipeline(
+      prompt=prompt,
+      negative_prompt=negative_prompt,
+      width=upscaled_width,
+      height=upscaled_height,
+      num_frames=num_frames,
+      denoise_strength=0.999,  # Effectively, 4 inference steps out of 5
+      timesteps=[1000, 909, 725, 421, 0],
+      latents=upscaled_latents,
+      decode_timestep=0.05,
+      decode_noise_scale=0.025,
+      image_cond_noise_scale=0.0,
+      guidance_scale=1.0,
+      guidance_rescale=0.7,
+      generator=torch.Generator().manual_seed(0),
+      output_type="pil",
+  ).frames[0]
+
+  # 4. Downscale the video to the expected resolution
+  video = [frame.resize((expected_width, expected_height)) for frame in video]
+
+  export_to_video(video, "output.mp4", fps=24)
+  ```
+
+  </details>
+
+- LTX-Video supports LoRAs with [`~loaders.LTXVideoLoraLoaderMixin.load_lora_weights`].
+
+  <details>
+  <summary>Show example code</summary>
+
+  ```py
+  import torch
+  from diffusers import LTXConditionPipeline
+  from diffusers.utils import export_to_video, load_image
+
+  pipeline = LTXConditionPipeline.from_pretrained(
+      "Lightricks/LTX-Video-0.9.5", torch_dtype=torch.bfloat16
+  )
+
+  pipeline.load_lora_weights("Lightricks/LTX-Video-Cakeify-LoRA", adapter_name="cakeify")
+  pipeline.set_adapters("cakeify")
+
+  # use "CAKEIFY" to trigger the LoRA
+  prompt = "CAKEIFY a person using a knife to cut a cake shaped like a Pikachu plushie"
+  image = load_image("https://huggingface.co/Lightricks/LTX-Video-Cakeify-LoRA/resolve/main/assets/images/pikachu.png")
+
+  video = pipeline(
+      prompt=prompt,
+      image=image,
+      width=576,
+      height=576,
+      num_frames=161,
+      decode_timestep=0.03,
+      decode_noise_scale=0.025,
+      num_inference_steps=50,
+  ).frames[0]
+  export_to_video(video, "output.mp4", fps=26)
+  ```
+
+  </details>
+
+- LTX-Video supports loading from single files, such as [GGUF checkpoints](../../quantization/gguf), with [`loaders.FromOriginalModelMixin.from_single_file`] or [`loaders.FromSingleFileMixin.from_single_file`].
+
+  <details>
+  <summary>Show example code</summary>
+
+  ```py
+  import torch
+  from diffusers.utils import export_to_video
+  from diffusers import LTXPipeline, AutoModel, GGUFQuantizationConfig
+
+  transformer = AutoModel.from_single_file(
+      "https://huggingface.co/city96/LTX-Video-gguf/blob/main/ltx-video-2b-v0.9-Q3_K_S.gguf"
+      quantization_config=GGUFQuantizationConfig(compute_dtype=torch.bfloat16),
+      torch_dtype=torch.bfloat16
+  )
+  pipeline = LTXPipeline.from_pretrained(
+      "Lightricks/LTX-Video",
+      transformer=transformer,
+      torch_dtype=torch.bfloat16
+  )
+  ```
+
+  </details>
+
 ## LTXPipeline
 
 [[autodoc]] LTXPipeline
@@ -192,6 +397,18 @@ export_to_video(video, "ship.mp4", fps=24)
   - all
   - __call__
 
+## LTXConditionPipeline
+
+[[autodoc]] LTXConditionPipeline
+  - all
+  - __call__
+
+## LTXLatentUpsamplePipeline
+
+[[autodoc]] LTXLatentUpsamplePipeline
+  - all
+  - __call__
+
 ## LTXPipelineOutput
 
 [[autodoc]] pipelines.ltx.pipeline_output.LTXPipelineOutput

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

@@ -28,7 +28,7 @@ Lumina-Next has the following components:
 
 ---
 
-[Lumina-T2X: Transforming Text into Any Modality, Resolution, and Duration via Flow-based Large Diffusion Transformers](https://arxiv.org/abs/2405.05945) from Alpha-VLLM, OpenGVLab, Shanghai AI Laboratory.
+[Lumina-T2X: Transforming Text into Any Modality, Resolution, and Duration via Flow-based Large Diffusion Transformers](https://huggingface.co/papers/2405.05945) from Alpha-VLLM, OpenGVLab, Shanghai AI Laboratory.
 
 The abstract from the paper is:
 
@@ -58,10 +58,10 @@ Use [`torch.compile`](https://huggingface.co/docs/diffusers/main/en/tutorials/fa
 First, load the pipeline:
 
 ```python
-from diffusers import LuminaText2ImgPipeline
+from diffusers import LuminaPipeline
 import torch
 
-pipeline = LuminaText2ImgPipeline.from_pretrained(
+pipeline = LuminaPipeline.from_pretrained(
 	"Alpha-VLLM/Lumina-Next-SFT-diffusers", torch_dtype=torch.bfloat16
 ).to("cuda")
 ```
@@ -86,11 +86,11 @@ image = pipeline(prompt="Upper body of a young woman in a Victorian-era outfit w
 
 Quantization helps reduce the memory requirements of very large models by storing model weights in a lower precision data type. However, quantization may have varying impact on video quality depending on the video model.
 
-Refer to the [Quantization](../../quantization/overview) overview to learn more about supported quantization backends and selecting a quantization backend that supports your use case. The example below demonstrates how to load a quantized [`LuminaText2ImgPipeline`] for inference with bitsandbytes.
+Refer to the [Quantization](../../quantization/overview) overview to learn more about supported quantization backends and selecting a quantization backend that supports your use case. The example below demonstrates how to load a quantized [`LuminaPipeline`] for inference with bitsandbytes.
 
 ```py
 import torch
-from diffusers import BitsAndBytesConfig as DiffusersBitsAndBytesConfig, Transformer2DModel, LuminaText2ImgPipeline
+from diffusers import BitsAndBytesConfig as DiffusersBitsAndBytesConfig, Transformer2DModel, LuminaPipeline
 from transformers import BitsAndBytesConfig as BitsAndBytesConfig, T5EncoderModel
 
 quant_config = BitsAndBytesConfig(load_in_8bit=True)
@@ -109,7 +109,7 @@ transformer_8bit = Transformer2DModel.from_pretrained(
     torch_dtype=torch.float16,
 )
 
-pipeline = LuminaText2ImgPipeline.from_pretrained(
+pipeline = LuminaPipeline.from_pretrained(
     "Alpha-VLLM/Lumina-Next-SFT-diffusers",
     text_encoder=text_encoder_8bit,
     transformer=transformer_8bit,
@@ -122,9 +122,9 @@ image = pipeline(prompt).images[0]
 image.save("lumina.png")
 ```
 
-## LuminaText2ImgPipeline
+## LuminaPipeline
 
-[[autodoc]] LuminaText2ImgPipeline
+[[autodoc]] LuminaPipeline
 	- all
 	- __call__
 

docs/source/en/api/pipelines/lumina2.md

@@ -0,0 +1,87 @@
+<!-- Copyright 2024 The HuggingFace Team. All rights reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License. -->
+
+# Lumina2
+
+<div class="flex flex-wrap space-x-1">
+  <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
+</div>
+
+[Lumina Image 2.0: A Unified and Efficient Image Generative Model](https://huggingface.co/Alpha-VLLM/Lumina-Image-2.0) is a 2 billion parameter flow-based diffusion transformer capable of generating diverse images from text descriptions.
+
+The abstract from the paper is:
+
+*We introduce Lumina-Image 2.0, an advanced text-to-image model that surpasses previous state-of-the-art methods across multiple benchmarks, while also shedding light on its potential to evolve into a generalist vision intelligence model. Lumina-Image 2.0 exhibits three key properties: (1) Unification – it adopts a unified architecture that treats text and image tokens as a joint sequence, enabling natural cross-modal interactions and facilitating task expansion. Besides, since high-quality captioners can provide semantically better-aligned text-image training pairs, we introduce a unified captioning system, UniCaptioner, which generates comprehensive and precise captions for the model. This not only accelerates model convergence but also enhances prompt adherence, variable-length prompt handling, and task generalization via prompt templates. (2) Efficiency – to improve the efficiency of the unified architecture, we develop a set of optimization techniques that improve semantic learning and fine-grained texture generation during training while incorporating inference-time acceleration strategies without compromising image quality. (3) Transparency – we open-source all training details, code, and models to ensure full reproducibility, aiming to bridge the gap between well-resourced closed-source research teams and independent developers.*
+
+<Tip>
+
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+
+</Tip>
+
+## Using Single File loading with Lumina Image 2.0
+
+Single file loading for Lumina Image 2.0 is available for the `Lumina2Transformer2DModel`
+
+```python
+import torch
+from diffusers import Lumina2Transformer2DModel, Lumina2Pipeline
+
+ckpt_path = "https://huggingface.co/Alpha-VLLM/Lumina-Image-2.0/blob/main/consolidated.00-of-01.pth"
+transformer = Lumina2Transformer2DModel.from_single_file(
+    ckpt_path, torch_dtype=torch.bfloat16
+)
+
+pipe = Lumina2Pipeline.from_pretrained(
+    "Alpha-VLLM/Lumina-Image-2.0", transformer=transformer, torch_dtype=torch.bfloat16
+)
+pipe.enable_model_cpu_offload()
+image = pipe(
+    "a cat holding a sign that says hello",
+    generator=torch.Generator("cpu").manual_seed(0),
+).images[0]
+image.save("lumina-single-file.png")
+
+```
+
+## Using GGUF Quantized Checkpoints with Lumina Image 2.0
+
+GGUF Quantized checkpoints for the `Lumina2Transformer2DModel` can be loaded via `from_single_file` with the `GGUFQuantizationConfig` 
+
+```python
+from diffusers import Lumina2Transformer2DModel, Lumina2Pipeline, GGUFQuantizationConfig 
+
+ckpt_path = "https://huggingface.co/calcuis/lumina-gguf/blob/main/lumina2-q4_0.gguf"
+transformer = Lumina2Transformer2DModel.from_single_file(
+    ckpt_path,
+    quantization_config=GGUFQuantizationConfig(compute_dtype=torch.bfloat16),
+    torch_dtype=torch.bfloat16,
+)
+
+pipe = Lumina2Pipeline.from_pretrained(
+    "Alpha-VLLM/Lumina-Image-2.0", transformer=transformer, torch_dtype=torch.bfloat16
+)
+pipe.enable_model_cpu_offload()
+image = pipe(
+    "a cat holding a sign that says hello",
+    generator=torch.Generator("cpu").manual_seed(0),
+).images[0]
+image.save("lumina-gguf.png")
+```
+
+## Lumina2Pipeline
+
+[[autodoc]] Lumina2Pipeline
+  - all
+  - __call__

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

@@ -1,4 +1,6 @@
-<!--Copyright 2024 Marigold authors and The HuggingFace Team. All rights reserved.
+<!--
+Copyright 2023-2025 Marigold Team, ETH Zürich. All rights reserved.
+Copyright 2024-2025 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
@@ -10,67 +12,120 @@ an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express o
 specific language governing permissions and limitations under the License.
 -->
 
-# Marigold Pipelines for Computer Vision Tasks
+# Marigold Computer Vision
 
 ![marigold](https://marigoldmonodepth.github.io/images/teaser_collage_compressed.jpg)
 
-Marigold was proposed in [Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation](https://huggingface.co/papers/2312.02145), a CVPR 2024 Oral paper by [Bingxin Ke](http://www.kebingxin.com/), [Anton Obukhov](https://www.obukhov.ai/), [Shengyu Huang](https://shengyuh.github.io/), [Nando Metzger](https://nandometzger.github.io/), [Rodrigo Caye Daudt](https://rcdaudt.github.io/), and [Konrad Schindler](https://scholar.google.com/citations?user=FZuNgqIAAAAJ&hl=en).
-The idea is to repurpose the rich generative prior of Text-to-Image Latent Diffusion Models (LDMs) for traditional computer vision tasks.
-Initially, this idea was explored to fine-tune Stable Diffusion for Monocular Depth Estimation, as shown in the teaser above.
-Later,
-- [Tianfu Wang](https://tianfwang.github.io/) trained the first Latent Consistency Model (LCM) of Marigold, which unlocked fast single-step inference;
-- [Kevin Qu](https://www.linkedin.com/in/kevin-qu-b3417621b/?locale=en_US) extended the approach to Surface Normals Estimation;
-- [Anton Obukhov](https://www.obukhov.ai/) contributed the pipelines and documentation into diffusers (enabled and supported by [YiYi Xu](https://yiyixuxu.github.io/) and [Sayak Paul](https://sayak.dev/)).
+Marigold was proposed in 
+[Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation](https://huggingface.co/papers/2312.02145), 
+a CVPR 2024 Oral paper by 
+[Bingxin Ke](http://www.kebingxin.com/), 
+[Anton Obukhov](https://www.obukhov.ai/), 
+[Shengyu Huang](https://shengyuh.github.io/), 
+[Nando Metzger](https://nandometzger.github.io/), 
+[Rodrigo Caye Daudt](https://rcdaudt.github.io/), and 
+[Konrad Schindler](https://scholar.google.com/citations?user=FZuNgqIAAAAJ&hl=en).
+The core idea is to **repurpose the generative prior of Text-to-Image Latent Diffusion Models (LDMs) for traditional 
+computer vision tasks**.
+This approach was explored by fine-tuning Stable Diffusion for **Monocular Depth Estimation**, as demonstrated in the 
+teaser above.
 
-The abstract from the paper is:
-
-*Monocular depth estimation is a fundamental computer vision task. Recovering 3D depth from a single image is geometrically ill-posed and requires scene understanding, so it is not surprising that the rise of deep learning has led to a breakthrough. The impressive progress of monocular depth estimators has mirrored the growth in model capacity, from relatively modest CNNs to large Transformer architectures. Still, monocular depth estimators tend to struggle when presented with images with unfamiliar content and layout, since their knowledge of the visual world is restricted by the data seen during training, and challenged by zero-shot generalization to new domains. This motivates us to explore whether the extensive priors captured in recent generative diffusion models can enable better, more generalizable depth estimation. We introduce Marigold, a method for affine-invariant monocular depth estimation that is derived from Stable Diffusion and retains its rich prior knowledge. The estimator can be fine-tuned in a couple of days on a single GPU using only synthetic training data. It delivers state-of-the-art performance across a wide range of datasets, including over 20% performance gains in specific cases. Project page: https://marigoldmonodepth.github.io.*
-
-## Available Pipelines
-
-Each pipeline supports one Computer Vision task, which takes an input RGB image as input and produces a *prediction* of the modality of interest, such as a depth map of the input image.
-Currently, the following tasks are implemented:
-
-| Pipeline                                                                                                                                    | Predicted Modalities                                                                                             |                                                                       Demos                                                                        |
-|---------------------------------------------------------------------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------:|
-| [MarigoldDepthPipeline](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/marigold/pipeline_marigold_depth.py)     | [Depth](https://en.wikipedia.org/wiki/Depth_map), [Disparity](https://en.wikipedia.org/wiki/Binocular_disparity) | [Fast Demo (LCM)](https://huggingface.co/spaces/prs-eth/marigold-lcm), [Slow Original Demo (DDIM)](https://huggingface.co/spaces/prs-eth/marigold) |
-| [MarigoldNormalsPipeline](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/marigold/pipeline_marigold_normals.py) | [Surface normals](https://en.wikipedia.org/wiki/Normal_mapping)                                                  |                                   [Fast Demo (LCM)](https://huggingface.co/spaces/prs-eth/marigold-normals-lcm)                                    |
-
-
-## Available Checkpoints
-
-The original checkpoints can be found under the [PRS-ETH](https://huggingface.co/prs-eth/) Hugging Face organization.
+Marigold was later extended in the follow-up paper, 
+[Marigold: Affordable Adaptation of Diffusion-Based Image Generators for Image Analysis](https://huggingface.co/papers/2312.02145), 
+authored by 
+[Bingxin Ke](http://www.kebingxin.com/), 
+[Kevin Qu](https://www.linkedin.com/in/kevin-qu-b3417621b/?locale=en_US), 
+[Tianfu Wang](https://tianfwang.github.io/), 
+[Nando Metzger](https://nandometzger.github.io/), 
+[Shengyu Huang](https://shengyuh.github.io/), 
+[Bo Li](https://www.linkedin.com/in/bobboli0202/), 
+[Anton Obukhov](https://www.obukhov.ai/), and 
+[Konrad Schindler](https://scholar.google.com/citations?user=FZuNgqIAAAAJ&hl=en).
+This work expanded Marigold to support new modalities such as **Surface Normals** and **Intrinsic Image Decomposition** 
+(IID), introduced a training protocol for **Latent Consistency Models** (LCM), and demonstrated **High-Resolution** (HR) 
+processing capability.
 
 <Tip>
 
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines. Also, to know more about reducing the memory usage of this pipeline, refer to the ["Reduce memory usage"] section [here](../../using-diffusers/svd#reduce-memory-usage).
+The early Marigold models (`v1-0` and earlier) were optimized for best results with at least 10 inference steps.
+LCM models were later developed to enable high-quality inference in just 1 to 4 steps.
+Marigold models `v1-1` and later use the DDIM scheduler to achieve optimal 
+results in as few as 1 to 4 steps.
+
+</Tip>
+
+## Available Pipelines
+
+Each pipeline is tailored for a specific computer vision task, processing an input RGB image and generating a 
+corresponding prediction.
+Currently, the following computer vision tasks are implemented:
+
+| Pipeline                                                                                                                                          | Recommended Model Checkpoints                                                                                                                                                                           |                              Spaces (Interactive Apps)                               | Predicted Modalities                                                                                                                                                               |
+|---------------------------------------------------------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------:|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+| [MarigoldDepthPipeline](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/marigold/pipeline_marigold_depth.py)           | [prs-eth/marigold-depth-v1-1](https://huggingface.co/prs-eth/marigold-depth-v1-1)                                                                                                                       |          [Depth Estimation](https://huggingface.co/spaces/prs-eth/marigold)          | [Depth](https://en.wikipedia.org/wiki/Depth_map), [Disparity](https://en.wikipedia.org/wiki/Binocular_disparity)                                                                   |
+| [MarigoldNormalsPipeline](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/marigold/pipeline_marigold_normals.py)       | [prs-eth/marigold-normals-v1-1](https://huggingface.co/prs-eth/marigold-normals-v1-1)                                                                                                                   | [Surface Normals Estimation](https://huggingface.co/spaces/prs-eth/marigold-normals) | [Surface normals](https://en.wikipedia.org/wiki/Normal_mapping)                                                                                                                    |
+| [MarigoldIntrinsicsPipeline](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/marigold/pipeline_marigold_intrinsics.py) | [prs-eth/marigold-iid-appearance-v1-1](https://huggingface.co/prs-eth/marigold-iid-appearance-v1-1),<br>[prs-eth/marigold-iid-lighting-v1-1](https://huggingface.co/prs-eth/marigold-iid-lighting-v1-1) | [Intrinsic Image Decomposition](https://huggingface.co/spaces/prs-eth/marigold-iid)  | [Albedo](https://en.wikipedia.org/wiki/Albedo), [Materials](https://www.n.aiq3d.com/wiki/roughnessmetalnessao-map), [Lighting](https://en.wikipedia.org/wiki/Diffuse_reflection)   |
+
+## Available Checkpoints
+
+All original checkpoints are available under the [PRS-ETH](https://huggingface.co/prs-eth/) organization on Hugging Face.
+They are designed for use with diffusers pipelines and the [original codebase](https://github.com/prs-eth/marigold), which can also be used to train 
+new model checkpoints.
+The following is a summary of the recommended checkpoints, all of which produce reliable results with 1 to 4 steps. 
+
+| Checkpoint                                                                                          | Modality     | Comment                                                                                                                                                                              |
+|-----------------------------------------------------------------------------------------------------|--------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+| [prs-eth/marigold-depth-v1-1](https://huggingface.co/prs-eth/marigold-depth-v1-1)                   | Depth        | Affine-invariant depth prediction assigns each pixel a value between 0 (near plane) and 1 (far plane), with both planes determined by the model during inference.                    |
+| [prs-eth/marigold-normals-v0-1](https://huggingface.co/prs-eth/marigold-normals-v0-1)               | Normals      | The surface normals predictions are unit-length 3D vectors in the screen space camera, with values in the range from -1 to 1.                                                        |
+| [prs-eth/marigold-iid-appearance-v1-1](https://huggingface.co/prs-eth/marigold-iid-appearance-v1-1) | Intrinsics   | InteriorVerse decomposition is comprised of Albedo and two BRDF material properties: Roughness and Metallicity.                                                                      | 
+| [prs-eth/marigold-iid-lighting-v1-1](https://huggingface.co/prs-eth/marigold-iid-lighting-v1-1)     | Intrinsics   | HyperSim decomposition of an image &nbsp\\(I\\)&nbsp is comprised of Albedo &nbsp\\(A\\), Diffuse shading &nbsp\\(S\\), and Non-diffuse residual &nbsp\\(R\\): &nbsp\\(I = A*S+R\\). |
+
+<Tip>
+
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff 
+between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to 
+efficiently load the same components into multiple pipelines. 
+Also, to know more about reducing the memory usage of this pipeline, refer to the ["Reduce memory usage"] section 
+[here](../../using-diffusers/svd#reduce-memory-usage).
 
 </Tip>
 
 <Tip warning={true}>
 
-Marigold pipelines were designed and tested only with `DDIMScheduler` and `LCMScheduler`.
-Depending on the scheduler, the number of inference steps required to get reliable predictions varies, and there is no universal value that works best across schedulers.
-Because of that, the default value of `num_inference_steps` in the `__call__` method of the pipeline is set to `None` (see the API reference).
-Unless set explicitly, its value will be taken from the checkpoint configuration `model_index.json`.
-This is done to ensure high-quality predictions when calling the pipeline with just the `image` argument.
+Marigold pipelines were designed and tested with the scheduler embedded in the model checkpoint.
+The optimal number of inference steps varies by scheduler, with no universal value that works best across all cases.
+To accommodate this, the `num_inference_steps` parameter in the pipeline's `__call__` method defaults to `None` (see the 
+API reference).
+Unless set explicitly, it inherits the value from the `default_denoising_steps` field in the checkpoint configuration 
+file (`model_index.json`).
+This ensures high-quality predictions when invoking the pipeline with only the `image` argument.
 
 </Tip>
 
-See also Marigold [usage examples](marigold_usage).
+See also Marigold [usage examples](../../using-diffusers/marigold_usage).
+
+## Marigold Depth Prediction API
 
-## MarigoldDepthPipeline
 [[autodoc]] MarigoldDepthPipeline
-	- all
 	- __call__
 
-## MarigoldNormalsPipeline
-[[autodoc]] MarigoldNormalsPipeline
-	- all
-	- __call__
-
-## MarigoldDepthOutput
 [[autodoc]] pipelines.marigold.pipeline_marigold_depth.MarigoldDepthOutput
 
-## MarigoldNormalsOutput
-[[autodoc]] pipelines.marigold.pipeline_marigold_normals.MarigoldNormalsOutput
+[[autodoc]] pipelines.marigold.marigold_image_processing.MarigoldImageProcessor.visualize_depth
+
+## Marigold Normals Estimation API
+[[autodoc]] MarigoldNormalsPipeline
+	- __call__
+
+[[autodoc]] pipelines.marigold.pipeline_marigold_normals.MarigoldNormalsOutput
+
+[[autodoc]] pipelines.marigold.marigold_image_processing.MarigoldImageProcessor.visualize_normals
+
+## Marigold Intrinsic Image Decomposition API
+
+[[autodoc]] MarigoldIntrinsicsPipeline
+	- __call__
+
+[[autodoc]] pipelines.marigold.pipeline_marigold_intrinsics.MarigoldIntrinsicsOutput
+
+[[autodoc]] pipelines.marigold.marigold_image_processing.MarigoldImageProcessor.visualize_intrinsics

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

@@ -15,6 +15,10 @@
 
 # Mochi 1 Preview
 
+<div class="flex flex-wrap space-x-1">
+  <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
+</div>
+
 > [!TIP]
 > Only a research preview of the model weights is available at the moment.
 

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

@@ -0,0 +1,80 @@
+<!--Copyright 2024 The HuggingFace Team. All rights reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+-->
+
+# OmniGen
+
+[OmniGen: Unified Image Generation](https://huggingface.co/papers/2409.11340) from BAAI, by Shitao Xiao, Yueze Wang, Junjie Zhou, Huaying Yuan, Xingrun Xing, Ruiran Yan, Chaofan Li, Shuting Wang, Tiejun Huang, Zheng Liu.
+
+The abstract from the paper is:
+
+*The emergence of Large Language Models (LLMs) has unified language  generation tasks and revolutionized human-machine interaction.  However, in the realm of image generation, a unified model capable of handling various tasks within a single framework remains largely unexplored. In this work, we introduce OmniGen, a new diffusion model for unified image generation. OmniGen is characterized by the following features: 1) Unification: OmniGen not only demonstrates text-to-image generation capabilities but also inherently supports various downstream tasks, such as image editing, subject-driven generation, and visual conditional generation. 2) Simplicity: The architecture of OmniGen is highly simplified, eliminating the need for additional plugins. Moreover, compared to existing diffusion models, it is more user-friendly and can complete complex tasks end-to-end through instructions without the need for extra intermediate steps, greatly simplifying the image generation workflow. 3) Knowledge Transfer: Benefit from learning in a unified format, OmniGen effectively transfers knowledge across different tasks, manages unseen tasks and domains, and exhibits novel capabilities. We also explore the model’s reasoning capabilities and potential applications of the chain-of-thought mechanism.  This work represents the first attempt at a general-purpose image generation model,  and we will release our resources at https://github.com/VectorSpaceLab/OmniGen to foster future advancements.*
+
+<Tip>
+
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers.md) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading.md#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+
+</Tip>
+
+This pipeline was contributed by [staoxiao](https://github.com/staoxiao). The original codebase can be found [here](https://github.com/VectorSpaceLab/OmniGen). The original weights can be found under [hf.co/shitao](https://huggingface.co/Shitao/OmniGen-v1).
+
+## Inference
+
+First, load the pipeline:
+
+```python
+import torch
+from diffusers import OmniGenPipeline
+
+pipe = OmniGenPipeline.from_pretrained("Shitao/OmniGen-v1-diffusers", torch_dtype=torch.bfloat16)
+pipe.to("cuda")
+```
+
+For text-to-image, pass a text prompt. By default, OmniGen generates a 1024x1024 image. 
+You can try setting the `height` and `width` parameters to generate images with different size.
+
+```python
+prompt = "Realistic photo. A young woman sits on a sofa, holding a book and facing the camera. She wears delicate silver hoop earrings adorned with tiny, sparkling diamonds that catch the light, with her long chestnut hair cascading over her shoulders. Her eyes are focused and gentle, framed by long, dark lashes. She is dressed in a cozy cream sweater, which complements her warm, inviting smile. Behind her, there is a table with a cup of water in a sleek, minimalist blue mug. The background is a serene indoor setting with soft natural light filtering through a window, adorned with tasteful art and flowers, creating a cozy and peaceful ambiance. 4K, HD."
+image = pipe(
+    prompt=prompt,
+    height=1024,
+    width=1024,
+    guidance_scale=3,
+    generator=torch.Generator(device="cpu").manual_seed(111),
+).images[0]
+image.save("output.png")
+```
+
+OmniGen supports multimodal inputs. 
+When the input includes an image, you need to add a placeholder `<img><|image_1|></img>` in the text prompt to represent the image. 
+It is recommended to enable `use_input_image_size_as_output` to keep the edited image the same size as the original image.
+
+```python
+prompt="<img><|image_1|></img> Remove the woman's earrings. Replace the mug with a clear glass filled with sparkling iced cola."
+input_images=[load_image("https://raw.githubusercontent.com/VectorSpaceLab/OmniGen/main/imgs/docs_img/t2i_woman_with_book.png")]
+image = pipe(
+    prompt=prompt, 
+    input_images=input_images, 
+    guidance_scale=2, 
+    img_guidance_scale=1.6,
+    use_input_image_size_as_output=True,
+    generator=torch.Generator(device="cpu").manual_seed(222)).images[0]
+image.save("output.png")
+```
+
+## OmniGenPipeline
+
+[[autodoc]] OmniGenPipeline
+  - all
+  - __call__

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

@@ -54,7 +54,7 @@ The table below lists all the pipelines currently available in 🤗 Diffusers an
 | [DiT](dit) | text2image |
 | [Flux](flux) | text2image |
 | [Hunyuan-DiT](hunyuandit) | text2image |
-| [I2VGen-XL](i2vgenxl) | text2video |
+| [I2VGen-XL](i2vgenxl) | image2video |
 | [InstructPix2Pix](pix2pix) | image editing |
 | [Kandinsky 2.1](kandinsky) | text2image, image2image, inpainting, interpolation |
 | [Kandinsky 2.2](kandinsky_v22) | text2image, image2image, inpainting |
@@ -65,7 +65,7 @@ The table below lists all the pipelines currently available in 🤗 Diffusers an
 | [Latte](latte) | text2image |
 | [LEDITS++](ledits_pp) | image editing |
 | [Lumina-T2X](lumina) | text2image |
-| [Marigold](marigold) | depth |
+| [Marigold](marigold) | depth-estimation, normals-estimation, intrinsic-decomposition |
 | [MultiDiffusion](panorama) | text2image |
 | [MusicLDM](musicldm) | text2audio |
 | [PAG](pag) | text2image |
@@ -89,6 +89,7 @@ The table below lists all the pipelines currently available in 🤗 Diffusers an
 | [UniDiffuser](unidiffuser) | text2image, image2text, image variation, text variation, unconditional image generation, unconditional audio generation |
 | [Value-guided planning](value_guided_sampling) | value guided sampling |
 | [Wuerstchen](wuerstchen) | text2image |
+| [VisualCloze](visualcloze) | text2image, image2image, subject driven generation, inpainting, style transfer, image restoration, image editing, [depth,normal,edge,pose]2image, [depth,normal,edge,pose]-estimation, virtual try-on, image relighting |
 
 ## DiffusionPipeline
 

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

@@ -12,6 +12,10 @@ specific language governing permissions and limitations under the License.
 
 # Perturbed-Attention Guidance
 
+<div class="flex flex-wrap space-x-1">
+  <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
+</div>
+
 [Perturbed-Attention Guidance (PAG)](https://ku-cvlab.github.io/Perturbed-Attention-Guidance/) is a new diffusion sampling guidance that improves sample quality across both unconditional and conditional settings, achieving this without requiring further training or the integration of external modules.
 
 PAG was introduced in [Self-Rectifying Diffusion Sampling with Perturbed-Attention Guidance](https://huggingface.co/papers/2403.17377) by Donghoon Ahn, Hyoungwon Cho, Jaewon Min, Wooseok Jang, Jungwoo Kim, SeonHwa Kim, Hyun Hee Park, Kyong Hwan Jin and Seungryong Kim.

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

@@ -12,6 +12,10 @@ specific language governing permissions and limitations under the License.
 
 # MultiDiffusion
 
+<div class="flex flex-wrap space-x-1">
+  <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
+</div>
+
 [MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation](https://huggingface.co/papers/2302.08113) is by Omer Bar-Tal, Lior Yariv, Yaron Lipman, and Tali Dekel.
 
 The abstract from the paper is:

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

@@ -12,9 +12,13 @@ specific language governing permissions and limitations under the License.
 
 # Image-to-Video Generation with PIA (Personalized Image Animator)
 
+<div class="flex flex-wrap space-x-1">
+  <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
+</div>
+
 ## Overview
 
-[PIA: Your Personalized Image Animator via Plug-and-Play Modules in Text-to-Image Models](https://arxiv.org/abs/2312.13964) by Yiming Zhang, Zhening Xing, Yanhong Zeng, Youqing Fang, Kai Chen
+[PIA: Your Personalized Image Animator via Plug-and-Play Modules in Text-to-Image Models](https://huggingface.co/papers/2312.13964) by Yiming Zhang, Zhening Xing, Yanhong Zeng, Youqing Fang, Kai Chen
 
 Recent advancements in personalized text-to-image (T2I) models have revolutionized content creation, empowering non-experts to generate stunning images with unique styles. While promising, adding realistic motions into these personalized images by text poses significant challenges in preserving distinct styles, high-fidelity details, and achieving motion controllability by text. In this paper, we present PIA, a Personalized Image Animator that excels in aligning with condition images, achieving motion controllability by text, and the compatibility with various personalized T2I models without specific tuning. To achieve these goals, PIA builds upon a base T2I model with well-trained temporal alignment layers, allowing for the seamless transformation of any personalized T2I model into an image animation model. A key component of PIA is the introduction of the condition module, which utilizes the condition frame and inter-frame affinity as input to transfer appearance information guided by the affinity hint for individual frame synthesis in the latent space. This design mitigates the challenges of appearance-related image alignment within and allows for a stronger focus on aligning with motion-related guidance.
 
@@ -88,7 +92,7 @@ If you plan on using a scheduler that can clip samples, make sure to disable it
 
 ## Using FreeInit
 
-[FreeInit: Bridging Initialization Gap in Video Diffusion Models](https://arxiv.org/abs/2312.07537) by Tianxing Wu, Chenyang Si, Yuming Jiang, Ziqi Huang, Ziwei Liu.
+[FreeInit: Bridging Initialization Gap in Video Diffusion Models](https://huggingface.co/papers/2312.07537) by Tianxing Wu, Chenyang Si, Yuming Jiang, Ziqi Huang, Ziwei Liu.
 
 FreeInit is an effective method that improves temporal consistency and overall quality of videos generated using video-diffusion-models without any addition training. It can be applied to PIA, AnimateDiff, ModelScope, VideoCrafter and various other video generation models seamlessly at inference time, and works by iteratively refining the latent-initialization noise. More details can be found it the paper.
 

docs/source/en/api/pipelines/pix2pix.md

@@ -12,6 +12,10 @@ specific language governing permissions and limitations under the License.
 
 # InstructPix2Pix
 
+<div class="flex flex-wrap space-x-1">
+  <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
+</div>
+
 [InstructPix2Pix: Learning to Follow Image Editing Instructions](https://huggingface.co/papers/2211.09800) is by Tim Brooks, Aleksander Holynski and Alexei A. Efros.
 
 The abstract from the paper is:

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

@@ -14,6 +14,11 @@
 
 # SanaPipeline
 
+<div class="flex flex-wrap space-x-1">
+  <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
+  <img alt="MPS" src="https://img.shields.io/badge/MPS-000000?style=flat&logo=apple&logoColor=white%22">
+</div>
+
 [SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformers](https://huggingface.co/papers/2410.10629) from NVIDIA and MIT HAN Lab, by Enze Xie, Junsong Chen, Junyu Chen, Han Cai, Haotian Tang, Yujun Lin, Zhekai Zhang, Muyang Li, Ligeng Zhu, Yao Lu, Song Han.
 
 The abstract from the paper is:

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

@@ -0,0 +1,134 @@
+<!-- Copyright 2024 The HuggingFace Team. All rights reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License. -->
+
+# SANA-Sprint
+
+<div class="flex flex-wrap space-x-1">
+  <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
+</div>
+
+[SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillation](https://huggingface.co/papers/2503.09641) from NVIDIA, MIT HAN Lab, and Hugging Face by Junsong Chen, Shuchen Xue, Yuyang Zhao, Jincheng Yu, Sayak Paul, Junyu Chen, Han Cai, Enze Xie, Song Han
+
+The abstract from the paper is:
+
+*This paper presents SANA-Sprint, an efficient diffusion model for ultra-fast text-to-image (T2I) generation. SANA-Sprint is built on a pre-trained foundation model and augmented with hybrid distillation, dramatically reducing inference steps from 20 to 1-4. We introduce three key innovations: (1) We propose a training-free approach that transforms a pre-trained flow-matching model for continuous-time consistency distillation (sCM), eliminating costly training from scratch and achieving high training efficiency. Our hybrid distillation strategy combines sCM with latent adversarial distillation (LADD): sCM ensures alignment with the teacher model, while LADD enhances single-step generation fidelity. (2) SANA-Sprint is a unified step-adaptive model that achieves high-quality generation in 1-4 steps, eliminating step-specific training and improving efficiency. (3) We integrate ControlNet with SANA-Sprint for real-time interactive image generation, enabling instant visual feedback for user interaction. SANA-Sprint establishes a new Pareto frontier in speed-quality tradeoffs, achieving state-of-the-art performance with 7.59 FID and 0.74 GenEval in only 1 step — outperforming FLUX-schnell (7.94 FID / 0.71 GenEval) while being 10× faster (0.1s vs 1.1s on H100). It also achieves 0.1s (T2I) and 0.25s (ControlNet) latency for 1024×1024 images on H100, and 0.31s (T2I) on an RTX 4090, showcasing its exceptional efficiency and potential for AI-powered consumer applications (AIPC). Code and pre-trained models will be open-sourced.*
+
+<Tip>
+
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+
+</Tip>
+
+This pipeline was contributed by [lawrence-cj](https://github.com/lawrence-cj), [shuchen Xue](https://github.com/scxue) and [Enze Xie](https://github.com/xieenze). The original codebase can be found [here](https://github.com/NVlabs/Sana). The original weights can be found under [hf.co/Efficient-Large-Model](https://huggingface.co/Efficient-Large-Model/).
+
+Available models:
+
+|                                                                    Model                                                                    | Recommended dtype |
+|:-------------------------------------------------------------------------------------------------------------------------------------------:|:-----------------:|
+| [`Efficient-Large-Model/Sana_Sprint_1.6B_1024px_diffusers`](https://huggingface.co/Efficient-Large-Model/Sana_Sprint_1.6B_1024px_diffusers) | `torch.bfloat16`  |
+| [`Efficient-Large-Model/Sana_Sprint_0.6B_1024px_diffusers`](https://huggingface.co/Efficient-Large-Model/Sana_Sprint_0.6B_1024px_diffusers) | `torch.bfloat16`  |
+
+Refer to [this](https://huggingface.co/collections/Efficient-Large-Model/sana-sprint-67d6810d65235085b3b17c76) collection for more information.
+
+Note: The recommended dtype mentioned is for the transformer weights. The text encoder must stay in `torch.bfloat16` and VAE weights must stay in `torch.bfloat16` or `torch.float32` for the model to work correctly. Please refer to the inference example below to see how to load the model with the recommended dtype. 
+
+
+## Quantization
+
+Quantization helps reduce the memory requirements of very large models by storing model weights in a lower precision data type. However, quantization may have varying impact on video quality depending on the video model.
+
+Refer to the [Quantization](../../quantization/overview) overview to learn more about supported quantization backends and selecting a quantization backend that supports your use case. The example below demonstrates how to load a quantized [`SanaSprintPipeline`] for inference with bitsandbytes.
+
+```py
+import torch
+from diffusers import BitsAndBytesConfig as DiffusersBitsAndBytesConfig, SanaTransformer2DModel, SanaSprintPipeline
+from transformers import BitsAndBytesConfig as BitsAndBytesConfig, AutoModel
+
+quant_config = BitsAndBytesConfig(load_in_8bit=True)
+text_encoder_8bit = AutoModel.from_pretrained(
+    "Efficient-Large-Model/Sana_Sprint_1.6B_1024px_diffusers",
+    subfolder="text_encoder",
+    quantization_config=quant_config,
+    torch_dtype=torch.bfloat16,
+)
+
+quant_config = DiffusersBitsAndBytesConfig(load_in_8bit=True)
+transformer_8bit = SanaTransformer2DModel.from_pretrained(
+    "Efficient-Large-Model/Sana_Sprint_1.6B_1024px_diffusers",
+    subfolder="transformer",
+    quantization_config=quant_config,
+    torch_dtype=torch.bfloat16,
+)
+
+pipeline = SanaSprintPipeline.from_pretrained(
+    "Efficient-Large-Model/Sana_Sprint_1.6B_1024px_diffusers",
+    text_encoder=text_encoder_8bit,
+    transformer=transformer_8bit,
+    torch_dtype=torch.bfloat16,
+    device_map="balanced",
+)
+
+prompt = "a tiny astronaut hatching from an egg on the moon"
+image = pipeline(prompt).images[0]
+image.save("sana.png")
+```
+
+## Setting `max_timesteps`
+
+Users can tweak the `max_timesteps` value for experimenting with the visual quality of the generated outputs. The default `max_timesteps` value was obtained with an inference-time search process. For more details about it, check out the paper.
+
+## Image to Image 
+
+The [`SanaSprintImg2ImgPipeline`] is a pipeline for image-to-image generation. It takes an input image and a prompt, and generates a new image based on the input image and the prompt.
+
+```py
+import torch
+from diffusers import SanaSprintImg2ImgPipeline
+from diffusers.utils.loading_utils import load_image
+
+image = load_image(
+    "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/penguin.png"
+)
+
+pipe = SanaSprintImg2ImgPipeline.from_pretrained(
+    "Efficient-Large-Model/Sana_Sprint_1.6B_1024px_diffusers", 
+    torch_dtype=torch.bfloat16)
+pipe.to("cuda")
+
+image = pipe(
+    prompt="a cute pink bear", 
+    image=image, 
+    strength=0.5, 
+    height=832, 
+    width=480
+).images[0]
+image.save("output.png")
+```
+
+## SanaSprintPipeline
+
+[[autodoc]] SanaSprintPipeline
+  - all
+  - __call__
+
+## SanaSprintImg2ImgPipeline
+
+[[autodoc]] SanaSprintImg2ImgPipeline
+  - all
+  - __call__
+
+
+## SanaPipelineOutput
+
+[[autodoc]] pipelines.sana.pipeline_output.SanaPipelineOutput

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

@@ -12,7 +12,7 @@ specific language governing permissions and limitations under the License.
 
 # Stable Audio
 
-Stable Audio was proposed in [Stable Audio Open](https://arxiv.org/abs/2407.14358) by Zach Evans et al. . it takes a text prompt as input and predicts the corresponding sound or music sample.
+Stable Audio was proposed in [Stable Audio Open](https://huggingface.co/papers/2407.14358) by Zach Evans et al. . it takes a text prompt as input and predicts the corresponding sound or music sample.
 
 Stable Audio Open generates variable-length (up to 47s) stereo audio at 44.1kHz from text prompts. It comprises three components: an autoencoder that compresses waveforms into a manageable sequence length, a T5-based text embedding for text conditioning, and a transformer-based diffusion (DiT) model that operates in the latent space of the autoencoder.
 

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

@@ -12,7 +12,7 @@ specific language governing permissions and limitations under the License.
 
 # T2I-Adapter
 
-[T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models](https://arxiv.org/abs/2302.08453) by Chong Mou, Xintao Wang, Liangbin Xie, Jian Zhang, Zhongang Qi, Ying Shan, Xiaohu Qie.
+[T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models](https://huggingface.co/papers/2302.08453) by Chong Mou, Xintao Wang, Liangbin Xie, Jian Zhang, Zhongang Qi, Ying Shan, Xiaohu Qie.
 
 Using the pretrained models we can provide control images (for example, a depth map) to control Stable Diffusion text-to-image generation so that it follows the structure of the depth image and fills in the details.
 

docs/source/en/api/pipelines/stable_diffusion/depth2img.md

@@ -12,6 +12,10 @@ specific language governing permissions and limitations under the License.
 
 # Depth-to-image
 
+<div class="flex flex-wrap space-x-1">
+  <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
+</div>
+
 The Stable Diffusion model can also infer depth based on an image using [MiDaS](https://github.com/isl-org/MiDaS). This allows you to pass a text prompt and an initial image to condition the generation of new images as well as a `depth_map` to preserve the image structure.
 
 <Tip>

docs/source/en/api/pipelines/stable_diffusion/img2img.md

@@ -12,6 +12,10 @@ specific language governing permissions and limitations under the License.
 
 # Image-to-image
 
+<div class="flex flex-wrap space-x-1">
+  <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
+</div>
+
 The Stable Diffusion model can also be applied to image-to-image generation by passing a text prompt and an initial image to condition the generation of new images.
 
 The [`StableDiffusionImg2ImgPipeline`] uses the diffusion-denoising mechanism proposed in [SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations](https://huggingface.co/papers/2108.01073) by Chenlin Meng, Yutong He, Yang Song, Jiaming Song, Jiajun Wu, Jun-Yan Zhu, Stefano Ermon.

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

@@ -12,6 +12,10 @@ specific language governing permissions and limitations under the License.
 
 # Inpainting
 
+<div class="flex flex-wrap space-x-1">
+  <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
+</div>
+
 The Stable Diffusion model can also be applied to inpainting which lets you edit specific parts of an image by providing a mask and a text prompt using Stable Diffusion.
 
 ## Tips

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

@@ -12,10 +12,14 @@ specific language governing permissions and limitations under the License.
 
 # Text-to-(RGB, depth)
 
+<div class="flex flex-wrap space-x-1">
+  <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
+</div>
+
 LDM3D was proposed in [LDM3D: Latent Diffusion Model for 3D](https://huggingface.co/papers/2305.10853) by Gabriela Ben Melech Stan, Diana Wofk, Scottie Fox, Alex Redden, Will Saxton, Jean Yu, Estelle Aflalo, Shao-Yen Tseng, Fabio Nonato, Matthias Muller, and Vasudev Lal. LDM3D generates an image and a depth map from a given text prompt unlike the existing text-to-image diffusion models such as [Stable Diffusion](./overview) which only generates an image. With almost the same number of parameters, LDM3D achieves to create a latent space that can compress both the RGB images and the depth maps.
 
 Two checkpoints are available for use:
-- [ldm3d-original](https://huggingface.co/Intel/ldm3d). The original checkpoint used in the [paper](https://arxiv.org/pdf/2305.10853.pdf)
+- [ldm3d-original](https://huggingface.co/Intel/ldm3d). The original checkpoint used in the [paper](https://huggingface.co/papers/2305.10853)
 - [ldm3d-4c](https://huggingface.co/Intel/ldm3d-4c). The new version of LDM3D using 4 channels inputs instead of 6-channels inputs and finetuned on higher resolution images.
 
 
@@ -44,7 +48,7 @@ Make sure to check out the Stable Diffusion [Tips](overview#tips) section to lea
 
 # Upscaler
 
-[LDM3D-VR](https://arxiv.org/pdf/2311.03226.pdf) is an extended version of LDM3D.
+[LDM3D-VR](https://huggingface.co/papers/2311.03226) is an extended version of LDM3D.
 
 The abstract from the paper is:
 *Latent diffusion models have proven to be state-of-the-art in the creation and manipulation of visual outputs. However, as far as we know, the generation of depth maps jointly with RGB is still limited. We introduce LDM3D-VR, a suite of diffusion models targeting virtual reality development that includes LDM3D-pano and LDM3D-SR. These models enable the generation of panoramic RGBD based on textual prompts and the upscaling of low-resolution inputs to high-resolution RGBD, respectively. Our models are fine-tuned from existing pretrained models on datasets containing panoramic/high-resolution RGB images, depth maps and captions. Both models are evaluated in comparison to existing related methods*

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

@@ -12,6 +12,10 @@ specific language governing permissions and limitations under the License.
 
 # Stable Diffusion pipelines
 
+<div class="flex flex-wrap space-x-1">
+  <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
+</div>
+
 Stable Diffusion is a text-to-image latent diffusion model created by the researchers and engineers from [CompVis](https://github.com/CompVis), [Stability AI](https://stability.ai/) and [LAION](https://laion.ai/). Latent diffusion applies the diffusion process over a lower dimensional latent space to reduce memory and compute complexity. This specific type of diffusion model was proposed in [High-Resolution Image Synthesis with Latent Diffusion Models](https://huggingface.co/papers/2112.10752) by Robin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser, Björn Ommer.
 
 Stable Diffusion is trained on 512x512 images from a subset of the LAION-5B dataset. This model uses a frozen CLIP ViT-L/14 text encoder to condition the model on text prompts. With its 860M UNet and 123M text encoder, the model is relatively lightweight and can run on consumer GPUs.

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

@@ -12,7 +12,12 @@ specific language governing permissions and limitations under the License.
 
 # Stable Diffusion 3
 
-Stable Diffusion 3 (SD3) was proposed in [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://arxiv.org/pdf/2403.03206.pdf) by Patrick Esser, Sumith Kulal, Andreas Blattmann, Rahim Entezari, Jonas Muller, Harry Saini, Yam Levi, Dominik Lorenz, Axel Sauer, Frederic Boesel, Dustin Podell, Tim Dockhorn, Zion English, Kyle Lacey, Alex Goodwin, Yannik Marek, and Robin Rombach.
+<div class="flex flex-wrap space-x-1">
+  <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
+  <img alt="MPS" src="https://img.shields.io/badge/MPS-000000?style=flat&logo=apple&logoColor=white%22">
+</div>
+
+Stable Diffusion 3 (SD3) was proposed in [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://huggingface.co/papers/2403.03206) by Patrick Esser, Sumith Kulal, Andreas Blattmann, Rahim Entezari, Jonas Muller, Harry Saini, Yam Levi, Dominik Lorenz, Axel Sauer, Frederic Boesel, Dustin Podell, Tim Dockhorn, Zion English, Kyle Lacey, Alex Goodwin, Yannik Marek, and Robin Rombach.
 
 The abstract from the paper is:
 
@@ -77,7 +82,7 @@ from diffusers import StableDiffusion3Pipeline
 from transformers import SiglipVisionModel, SiglipImageProcessor
 
 image_encoder_id = "google/siglip-so400m-patch14-384"
-ip_adapter_id = "guiyrt/InstantX-SD3.5-Large-IP-Adapter-diffusers"
+ip_adapter_id = "InstantX/SD3.5-Large-IP-Adapter"
 
 feature_extractor = SiglipImageProcessor.from_pretrained(
     image_encoder_id,

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

@@ -12,6 +12,11 @@ specific language governing permissions and limitations under the License.
 
 # Stable Diffusion XL
 
+<div class="flex flex-wrap space-x-1">
+  <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
+  <img alt="MPS" src="https://img.shields.io/badge/MPS-000000?style=flat&logo=apple&logoColor=white%22">
+</div>
+
 Stable Diffusion XL (SDXL) was proposed in [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://huggingface.co/papers/2307.01952) by Dustin Podell, Zion English, Kyle Lacey, Andreas Blattmann, Tim Dockhorn, Jonas Müller, Joe Penna, and Robin Rombach.
 
 The abstract from the paper is:

docs/source/en/api/pipelines/stable_diffusion/text2img.md

@@ -12,6 +12,10 @@ specific language governing permissions and limitations under the License.
 
 # Text-to-image
 
+<div class="flex flex-wrap space-x-1">
+  <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
+</div>
+
 The Stable Diffusion model was created by researchers and engineers from [CompVis](https://github.com/CompVis), [Stability AI](https://stability.ai/), [Runway](https://github.com/runwayml), and [LAION](https://laion.ai/). The [`StableDiffusionPipeline`] is capable of generating photorealistic images given any text input. It's trained on 512x512 images from a subset of the LAION-5B dataset. This model uses a frozen CLIP ViT-L/14 text encoder to condition the model on text prompts. With its 860M UNet and 123M text encoder, the model is relatively lightweight and can run on consumer GPUs. Latent diffusion is the research on top of which Stable Diffusion was built. It was proposed in [High-Resolution Image Synthesis with Latent Diffusion Models](https://huggingface.co/papers/2112.10752) by Robin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser, Björn Ommer.
 
 The abstract from the paper is:

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

@@ -12,6 +12,10 @@ specific language governing permissions and limitations under the License.
 
 # Super-resolution
 
+<div class="flex flex-wrap space-x-1">
+  <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
+</div>
+
 The Stable Diffusion upscaler diffusion model was created by the researchers and engineers from [CompVis](https://github.com/CompVis), [Stability AI](https://stability.ai/), and [LAION](https://laion.ai/). It is used to enhance the resolution of input images by a factor of 4.
 
 <Tip>

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

@@ -12,6 +12,10 @@ specific language governing permissions and limitations under the License.
 
 # Stable unCLIP
 
+<div class="flex flex-wrap space-x-1">
+  <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
+</div>
+
 Stable unCLIP checkpoints are finetuned from [Stable Diffusion 2.1](./stable_diffusion/stable_diffusion_2) checkpoints to condition on CLIP image embeddings.
 Stable unCLIP still conditions on text embeddings. Given the two separate conditionings, stable unCLIP can be used
 for text guided image variation. When combined with an unCLIP prior, it can also be used for full text to image generation.

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

@@ -18,7 +18,11 @@ specific language governing permissions and limitations under the License.
 
 # Text-to-video
 
-[ModelScope Text-to-Video Technical Report](https://arxiv.org/abs/2308.06571) is by Jiuniu Wang, Hangjie Yuan, Dayou Chen, Yingya Zhang, Xiang Wang, Shiwei Zhang.
+<div class="flex flex-wrap space-x-1">
+  <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
+</div>
+
+[ModelScope Text-to-Video Technical Report](https://huggingface.co/papers/2308.06571) is by Jiuniu Wang, Hangjie Yuan, Dayou Chen, Yingya Zhang, Xiang Wang, Shiwei Zhang.
 
 The abstract from the paper is:
 

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

@@ -12,6 +12,10 @@ specific language governing permissions and limitations under the License.
 
 # Text2Video-Zero
 
+<div class="flex flex-wrap space-x-1">
+  <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
+</div>
+
 [Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generators](https://huggingface.co/papers/2303.13439) is by Levon Khachatryan, Andranik Movsisyan, Vahram Tadevosyan, Roberto Henschel, [Zhangyang Wang](https://www.ece.utexas.edu/people/faculty/atlas-wang), Shant Navasardyan, [Humphrey Shi](https://www.humphreyshi.com).
 
 Text2Video-Zero enables zero-shot video generation using either:
@@ -30,7 +34,7 @@ Our key modifications include (i) enriching the latent codes of the generated fr
 Experiments show that this leads to low overhead, yet high-quality and remarkably consistent video generation. Moreover, our approach is not limited to text-to-video synthesis but is also applicable to other tasks such as conditional and content-specialized video generation, and Video Instruct-Pix2Pix, i.e., instruction-guided video editing.
 As experiments show, our method performs comparably or sometimes better than recent approaches, despite not being trained on additional video data.*
 
-You can find additional information about Text2Video-Zero on the [project page](https://text2video-zero.github.io/), [paper](https://arxiv.org/abs/2303.13439), and [original codebase](https://github.com/Picsart-AI-Research/Text2Video-Zero).
+You can find additional information about Text2Video-Zero on the [project page](https://text2video-zero.github.io/), [paper](https://huggingface.co/papers/2303.13439), and [original codebase](https://github.com/Picsart-AI-Research/Text2Video-Zero).
 
 ## Usage example
 
@@ -51,9 +55,9 @@ result = [(r * 255).astype("uint8") for r in result]
 imageio.mimsave("video.mp4", result, fps=4)
 ```
 You can change these parameters in the pipeline call:
-* Motion field strength (see the [paper](https://arxiv.org/abs/2303.13439), Sect. 3.3.1):
+* Motion field strength (see the [paper](https://huggingface.co/papers/2303.13439), Sect. 3.3.1):
     * `motion_field_strength_x` and `motion_field_strength_y`. Default: `motion_field_strength_x=12`, `motion_field_strength_y=12`
-* `T` and `T'` (see the [paper](https://arxiv.org/abs/2303.13439), Sect. 3.3.1)
+* `T` and `T'` (see the [paper](https://huggingface.co/papers/2303.13439), Sect. 3.3.1)
     * `t0` and `t1` in the range `{0, ..., num_inference_steps}`. Default: `t0=45`, `t1=48`
 * Video length:
     * `video_length`, the number of frames video_length to be generated. Default: `video_length=8`

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

@@ -12,6 +12,10 @@ specific language governing permissions and limitations under the License.
 
 # UniDiffuser
 
+<div class="flex flex-wrap space-x-1">
+  <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
+</div>
+
 The UniDiffuser model was proposed in [One Transformer Fits All Distributions in Multi-Modal Diffusion at Scale](https://huggingface.co/papers/2303.06555) by Fan Bao, Shen Nie, Kaiwen Xue, Chongxuan Li, Shi Pu, Yaole Wang, Gang Yue, Yue Cao, Hang Su, Jun Zhu.
 
 The abstract from the paper is:

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

@@ -0,0 +1,300 @@
+<!--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.
+-->
+
+# VisualCloze
+
+[VisualCloze: A Universal Image Generation Framework via Visual In-Context Learning](https://huggingface.co/papers/2504.07960) is an innovative in-context learning based universal image generation framework that offers key capabilities:
+1. Support for various in-domain tasks
+2. Generalization to unseen tasks through in-context learning
+3. Unify multiple tasks into one step and generate both target image and intermediate results
+4. Support reverse-engineering conditions from target images
+
+## Overview
+
+The abstract from the paper is:
+
+*Recent progress in diffusion models significantly advances various image generation tasks. However, the current mainstream approach remains focused on building task-specific models, which have limited efficiency when supporting a wide range of different needs. While universal models attempt to address this limitation, they face critical challenges, including generalizable task instruction, appropriate task distributions, and unified architectural design. To tackle these challenges, we propose VisualCloze, a universal image generation framework, which supports a wide range of in-domain tasks, generalization to unseen ones, unseen unification of multiple tasks, and reverse generation. Unlike existing methods that rely on language-based task instruction, leading to task ambiguity and weak generalization, we integrate visual in-context learning, allowing models to identify tasks from visual demonstrations. Meanwhile, the inherent sparsity of visual task distributions hampers the learning of transferable knowledge across tasks. To this end, we introduce Graph200K, a graph-structured dataset that establishes various interrelated tasks, enhancing task density and transferable knowledge. Furthermore, we uncover that our unified image generation formulation shared a consistent objective with image infilling, enabling us to leverage the strong generative priors of pre-trained infilling models without modifying the architectures. The codes, dataset, and models are available at https://visualcloze.github.io.*
+
+## Inference
+
+### Model loading
+
+VisualCloze is a two-stage cascade pipeline, containing `VisualClozeGenerationPipeline` and `VisualClozeUpsamplingPipeline`.
+- In `VisualClozeGenerationPipeline`, each image is downsampled before concatenating images into a grid layout, avoiding excessively high resolutions. VisualCloze releases two models suitable for diffusers, i.e., [VisualClozePipeline-384](https://huggingface.co/VisualCloze/VisualClozePipeline-384) and [VisualClozePipeline-512](https://huggingface.co/VisualCloze/VisualClozePipeline-384), which downsample images to resolutions of 384 and 512, respectively. 
+- `VisualClozeUpsamplingPipeline` uses [SDEdit](https://huggingface.co/papers/2108.01073) to enable high-resolution image synthesis.
+
+The `VisualClozePipeline` integrates both stages to support convenient end-to-end sampling, while also allowing users to utilize each pipeline independently as needed.
+
+### Input Specifications
+
+#### Task and Content Prompts
+- Task prompt: Required to describe the generation task intention
+- Content prompt: Optional description or caption of the target image
+- When content prompt is not needed, pass `None`
+- For batch inference, pass `List[str|None]`
+
+#### Image Input Format
+- Format: `List[List[Image|None]]`
+- Structure:
+  - All rows except the last represent in-context examples
+  - Last row represents the current query (target image set to `None`)
+- For batch inference, pass `List[List[List[Image|None]]]`
+
+#### Resolution Control
+- Default behavior:
+  - Initial generation in the first stage: area of ${pipe.resolution}^2$
+  - Upsampling in the second stage: 3x factor
+- Custom resolution: Adjust using `upsampling_height` and `upsampling_width` parameters
+
+### Examples
+
+For comprehensive examples covering a wide range of tasks, please refer to the [Online Demo](https://huggingface.co/spaces/VisualCloze/VisualCloze) and [GitHub Repository](https://github.com/lzyhha/VisualCloze). Below are simple examples for three cases: mask-to-image conversion, edge detection, and subject-driven generation.
+
+#### Example for mask2image
+
+```python
+import torch
+from diffusers import VisualClozePipeline
+from diffusers.utils import load_image
+
+pipe = VisualClozePipeline.from_pretrained("VisualCloze/VisualClozePipeline-384", resolution=384, torch_dtype=torch.bfloat16)
+pipe.to("cuda")
+
+# Load in-context images (make sure the paths are correct and accessible)
+image_paths = [
+    # in-context examples
+    [
+        load_image('https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/visualcloze/visualcloze_mask2image_incontext-example-1_mask.jpg'),
+        load_image('https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/visualcloze/visualcloze_mask2image_incontext-example-1_image.jpg'),
+    ],
+    # query with the target image
+    [
+        load_image('https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/visualcloze/visualcloze_mask2image_query_mask.jpg'),
+        None, # No image needed for the target image
+    ],
+]
+
+# Task and content prompt
+task_prompt = "In each row, a logical task is demonstrated to achieve [IMAGE2] an aesthetically pleasing photograph based on [IMAGE1] sam 2-generated masks with rich color coding."
+content_prompt = """Majestic photo of a golden eagle perched on a rocky outcrop in a mountainous landscape. 
+The eagle is positioned in the right foreground, facing left, with its sharp beak and keen eyes prominently visible. 
+Its plumage is a mix of dark brown and golden hues, with intricate feather details. 
+The background features a soft-focus view of snow-capped mountains under a cloudy sky, creating a serene and grandiose atmosphere. 
+The foreground includes rugged rocks and patches of green moss. Photorealistic, medium depth of field, 
+soft natural lighting, cool color palette, high contrast, sharp focus on the eagle, blurred background, 
+tranquil, majestic, wildlife photography."""
+
+# Run the pipeline
+image_result = pipe(
+    task_prompt=task_prompt,
+    content_prompt=content_prompt,
+    image=image_paths,
+    upsampling_width=1344,
+    upsampling_height=768,
+    upsampling_strength=0.4,
+    guidance_scale=30,
+    num_inference_steps=30,
+    max_sequence_length=512,
+    generator=torch.Generator("cpu").manual_seed(0)
+).images[0][0]
+
+# Save the resulting image
+image_result.save("visualcloze.png")
+```
+
+#### Example for edge-detection
+
+```python
+import torch
+from diffusers import VisualClozePipeline
+from diffusers.utils import load_image
+
+pipe = VisualClozePipeline.from_pretrained("VisualCloze/VisualClozePipeline-384", resolution=384, torch_dtype=torch.bfloat16)
+pipe.to("cuda")
+
+# Load in-context images (make sure the paths are correct and accessible)
+image_paths = [
+    # in-context examples
+    [
+        load_image('https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/visualcloze/visualcloze_edgedetection_incontext-example-1_image.jpg'),
+        load_image('https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/visualcloze/visualcloze_edgedetection_incontext-example-1_edge.jpg'),
+    ],
+    [
+        load_image('https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/visualcloze/visualcloze_edgedetection_incontext-example-2_image.jpg'),
+        load_image('https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/visualcloze/visualcloze_edgedetection_incontext-example-2_edge.jpg'),
+    ],
+    # query with the target image
+    [
+        load_image('https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/visualcloze/visualcloze_edgedetection_query_image.jpg'),
+        None, # No image needed for the target image
+    ],
+]
+
+# Task and content prompt
+task_prompt = "Each row illustrates a pathway from [IMAGE1] a sharp and beautifully composed photograph to [IMAGE2] edge map with natural well-connected outlines using a clear logical task."
+content_prompt = ""
+
+# Run the pipeline
+image_result = pipe(
+    task_prompt=task_prompt,
+    content_prompt=content_prompt,
+    image=image_paths,
+    upsampling_width=864,
+    upsampling_height=1152,
+    upsampling_strength=0.4,
+    guidance_scale=30,
+    num_inference_steps=30,
+    max_sequence_length=512,
+    generator=torch.Generator("cpu").manual_seed(0)
+).images[0][0]
+
+# Save the resulting image
+image_result.save("visualcloze.png")
+```
+
+#### Example for subject-driven generation
+
+```python
+import torch
+from diffusers import VisualClozePipeline
+from diffusers.utils import load_image
+
+pipe = VisualClozePipeline.from_pretrained("VisualCloze/VisualClozePipeline-384", resolution=384, torch_dtype=torch.bfloat16)
+pipe.to("cuda")
+
+# Load in-context images (make sure the paths are correct and accessible)
+image_paths = [
+    # in-context examples
+    [
+        load_image('https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/visualcloze/visualcloze_subjectdriven_incontext-example-1_reference.jpg'),
+        load_image('https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/visualcloze/visualcloze_subjectdriven_incontext-example-1_depth.jpg'),
+        load_image('https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/visualcloze/visualcloze_subjectdriven_incontext-example-1_image.jpg'),
+    ],
+    [
+        load_image('https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/visualcloze/visualcloze_subjectdriven_incontext-example-2_reference.jpg'),
+        load_image('https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/visualcloze/visualcloze_subjectdriven_incontext-example-2_depth.jpg'),
+        load_image('https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/visualcloze/visualcloze_subjectdriven_incontext-example-2_image.jpg'),
+    ],
+    # query with the target image
+    [
+        load_image('https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/visualcloze/visualcloze_subjectdriven_query_reference.jpg'),
+        load_image('https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/visualcloze/visualcloze_subjectdriven_query_depth.jpg'),
+        None, # No image needed for the target image
+    ],
+]
+
+# Task and content prompt
+task_prompt = """Each row describes a process that begins with [IMAGE1] an image containing the key object, 
+[IMAGE2] depth map revealing gray-toned spatial layers and results in 
+[IMAGE3] an image with artistic qualitya high-quality image with exceptional detail."""
+content_prompt = """A vintage porcelain collector's item. Beneath a blossoming cherry tree in early spring, 
+this treasure is photographed up close, with soft pink petals drifting through the air and vibrant blossoms framing the scene."""
+
+# Run the pipeline
+image_result = pipe(
+    task_prompt=task_prompt,
+    content_prompt=content_prompt,
+    image=image_paths,
+    upsampling_width=1024,
+    upsampling_height=1024,
+    upsampling_strength=0.2,
+    guidance_scale=30,
+    num_inference_steps=30,
+    max_sequence_length=512,
+    generator=torch.Generator("cpu").manual_seed(0)
+).images[0][0]
+
+# Save the resulting image
+image_result.save("visualcloze.png")
+```
+
+#### Utilize each pipeline independently 
+
+```python
+import torch
+from diffusers import VisualClozeGenerationPipeline, FluxFillPipeline as VisualClozeUpsamplingPipeline
+from diffusers.utils import load_image
+from PIL import Image
+
+pipe = VisualClozeGenerationPipeline.from_pretrained(
+    "VisualCloze/VisualClozePipeline-384", resolution=384, torch_dtype=torch.bfloat16
+)
+pipe.to("cuda")
+
+image_paths = [
+    # in-context examples
+    [
+        load_image(
+            "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/visualcloze/visualcloze_mask2image_incontext-example-1_mask.jpg"
+        ),
+        load_image(
+            "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/visualcloze/visualcloze_mask2image_incontext-example-1_image.jpg"
+        ),
+    ],
+    # query with the target image
+    [
+        load_image(
+            "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/visualcloze/visualcloze_mask2image_query_mask.jpg"
+        ),
+        None,  # No image needed for the target image
+    ],
+]
+task_prompt = "In each row, a logical task is demonstrated to achieve [IMAGE2] an aesthetically pleasing photograph based on [IMAGE1] sam 2-generated masks with rich color coding."
+content_prompt = "Majestic photo of a golden eagle perched on a rocky outcrop in a mountainous landscape. The eagle is positioned in the right foreground, facing left, with its sharp beak and keen eyes prominently visible. Its plumage is a mix of dark brown and golden hues, with intricate feather details. The background features a soft-focus view of snow-capped mountains under a cloudy sky, creating a serene and grandiose atmosphere. The foreground includes rugged rocks and patches of green moss. Photorealistic, medium depth of field, soft natural lighting, cool color palette, high contrast, sharp focus on the eagle, blurred background, tranquil, majestic, wildlife photography."
+
+# Stage 1: Generate initial image
+image = pipe(
+    task_prompt=task_prompt,
+    content_prompt=content_prompt,
+    image=image_paths,
+    guidance_scale=30,
+    num_inference_steps=30,
+    max_sequence_length=512,
+    generator=torch.Generator("cpu").manual_seed(0),
+).images[0][0]
+
+# Stage 2 (optional): Upsample the generated image
+pipe_upsample = VisualClozeUpsamplingPipeline.from_pipe(pipe)
+pipe_upsample.to("cuda")
+
+mask_image = Image.new("RGB", image.size, (255, 255, 255))
+
+image = pipe_upsample(
+    image=image,
+    mask_image=mask_image,
+    prompt=content_prompt,
+    width=1344,
+    height=768,
+    strength=0.4,
+    guidance_scale=30,
+    num_inference_steps=30,
+    max_sequence_length=512,
+    generator=torch.Generator("cpu").manual_seed(0),
+).images[0]
+
+image.save("visualcloze.png")
+```
+
+## VisualClozePipeline
+
+[[autodoc]] VisualClozePipeline
+  - all
+  - __call__
+
+## VisualClozeGenerationPipeline
+
+[[autodoc]] VisualClozeGenerationPipeline
+  - all
+  - __call__

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

@@ -0,0 +1,356 @@
+<!-- Copyright 2024 The HuggingFace Team. All rights reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License. -->
+
+<div style="float: right;">
+  <div class="flex flex-wrap space-x-1">
+    <a href="https://huggingface.co/docs/diffusers/main/en/tutorials/using_peft_for_inference" target="_blank" rel="noopener">
+      <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
+    </a>
+  </div>
+</div>
+
+# Wan2.1
+
+[Wan-2.1](https://huggingface.co/papers/2503.20314) by the Wan Team.
+
+*This report presents Wan, a comprehensive and open suite of video foundation models designed to push the boundaries of video generation. Built upon the mainstream diffusion transformer paradigm, Wan achieves significant advancements in generative capabilities through a series of innovations, including our novel VAE, scalable pre-training strategies, large-scale data curation, and automated evaluation metrics. These contributions collectively enhance the model's performance and versatility. Specifically, Wan is characterized by four key features: Leading Performance: The 14B model of Wan, trained on a vast dataset comprising billions of images and videos, demonstrates the scaling laws of video generation with respect to both data and model size. It consistently outperforms the existing open-source models as well as state-of-the-art commercial solutions across multiple internal and external benchmarks, demonstrating a clear and significant performance superiority. Comprehensiveness: Wan offers two capable models, i.e., 1.3B and 14B parameters, for efficiency and effectiveness respectively. It also covers multiple downstream applications, including image-to-video, instruction-guided video editing, and personal video generation, encompassing up to eight tasks. Consumer-Grade Efficiency: The 1.3B model demonstrates exceptional resource efficiency, requiring only 8.19 GB VRAM, making it compatible with a wide range of consumer-grade GPUs. Openness: We open-source the entire series of Wan, including source code and all models, with the goal of fostering the growth of the video generation community. This openness seeks to significantly expand the creative possibilities of video production in the industry and provide academia with high-quality video foundation models. All the code and models are available at [this https URL](https://github.com/Wan-Video/Wan2.1).*
+
+You can find all the original Wan2.1 checkpoints under the [Wan-AI](https://huggingface.co/Wan-AI) organization.
+
+The following Wan models are supported in Diffusers:
+- [Wan 2.1 T2V 1.3B](https://huggingface.co/Wan-AI/Wan2.1-T2V-1.3B-Diffusers)
+- [Wan 2.1 T2V 14B](https://huggingface.co/Wan-AI/Wan2.1-T2V-14B-Diffusers)
+- [Wan 2.1 I2V 14B - 480P](https://huggingface.co/Wan-AI/Wan2.1-I2V-14B-480P-Diffusers)
+- [Wan 2.1 I2V 14B - 720P](https://huggingface.co/Wan-AI/Wan2.1-I2V-14B-720P-Diffusers)
+- [Wan 2.1 FLF2V 14B - 720P](https://huggingface.co/Wan-AI/Wan2.1-FLF2V-14B-720P-diffusers)
+- [Wan 2.1 VACE 1.3B](https://huggingface.co/Wan-AI/Wan2.1-VACE-1.3B-diffusers)
+- [Wan 2.1 VACE 14B](https://huggingface.co/Wan-AI/Wan2.1-VACE-14B-diffusers)
+
+> [!TIP]
+> Click on the Wan2.1 models in the right sidebar for more examples of video generation.
+
+### Text-to-Video Generation
+
+The example below demonstrates how to generate a video from text optimized for memory or inference speed.
+
+<hfoptions id="T2V usage">
+<hfoption id="T2V memory">
+
+Refer to the [Reduce memory usage](../../optimization/memory) guide for more details about the various memory saving techniques.
+
+The Wan2.1 text-to-video model below requires ~13GB of VRAM.
+
+```py
+# pip install ftfy
+import torch
+import numpy as np
+from diffusers import AutoModel, WanPipeline
+from diffusers.quantizers import PipelineQuantizationConfig
+from diffusers.hooks.group_offloading import apply_group_offloading
+from diffusers.utils import export_to_video, load_image
+from transformers import UMT5EncoderModel
+
+text_encoder = UMT5EncoderModel.from_pretrained("Wan-AI/Wan2.1-T2V-14B-Diffusers", subfolder="text_encoder", torch_dtype=torch.bfloat16)
+vae = AutoModel.from_pretrained("Wan-AI/Wan2.1-T2V-14B-Diffusers", subfolder="vae", torch_dtype=torch.float32)
+transformer = AutoModel.from_pretrained("Wan-AI/Wan2.1-T2V-14B-Diffusers", subfolder="transformer", torch_dtype=torch.bfloat16)
+
+# group-offloading
+onload_device = torch.device("cuda")
+offload_device = torch.device("cpu")
+apply_group_offloading(text_encoder,
+    onload_device=onload_device,
+    offload_device=offload_device,
+    offload_type="block_level",
+    num_blocks_per_group=4
+)
+transformer.enable_group_offload(
+    onload_device=onload_device,
+    offload_device=offload_device,
+    offload_type="leaf_level",
+    use_stream=True
+)
+
+pipeline = WanPipeline.from_pretrained(
+    "Wan-AI/Wan2.1-T2V-14B-Diffusers",
+    vae=vae,
+    transformer=transformer,
+    text_encoder=text_encoder,
+    torch_dtype=torch.bfloat16
+)
+pipeline.to("cuda")
+
+prompt = """
+The camera rushes from far to near in a low-angle shot, 
+revealing a white ferret on a log. It plays, leaps into the water, and emerges, as the camera zooms in 
+for a close-up. Water splashes berry bushes nearby, while moss, snow, and leaves blanket the ground. 
+Birch trees and a light blue sky frame the scene, with ferns in the foreground. Side lighting casts dynamic 
+shadows and warm highlights. Medium composition, front view, low angle, with depth of field.
+"""
+negative_prompt = """
+Bright tones, overexposed, static, blurred details, subtitles, style, works, paintings, images, static, overall gray, worst quality, 
+low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, 
+misshapen limbs, fused fingers, still picture, messy background, three legs, many people in the background, walking backwards
+"""
+
+output = pipeline(
+    prompt=prompt,
+    negative_prompt=negative_prompt,
+    num_frames=81,
+    guidance_scale=5.0,
+).frames[0]
+export_to_video(output, "output.mp4", fps=16)
+```
+
+</hfoption>
+<hfoption id="T2V inference speed">
+
+[Compilation](../../optimization/fp16#torchcompile) is slow the first time but subsequent calls to the pipeline are faster.
+
+```py
+# pip install ftfy
+import torch
+import numpy as np
+from diffusers import AutoModel, WanPipeline
+from diffusers.hooks.group_offloading import apply_group_offloading
+from diffusers.utils import export_to_video, load_image
+from transformers import UMT5EncoderModel
+
+text_encoder = UMT5EncoderModel.from_pretrained("Wan-AI/Wan2.1-T2V-14B-Diffusers", subfolder="text_encoder", torch_dtype=torch.bfloat16)
+vae = AutoModel.from_pretrained("Wan-AI/Wan2.1-T2V-14B-Diffusers", subfolder="vae", torch_dtype=torch.float32)
+transformer = AutoModel.from_pretrained("Wan-AI/Wan2.1-T2V-14B-Diffusers", subfolder="transformer", torch_dtype=torch.bfloat16)
+
+pipeline = WanPipeline.from_pretrained(
+    "Wan-AI/Wan2.1-T2V-14B-Diffusers",
+    vae=vae,
+    transformer=transformer,
+    text_encoder=text_encoder,
+    torch_dtype=torch.bfloat16
+)
+pipeline.to("cuda")
+
+# torch.compile
+pipeline.transformer.to(memory_format=torch.channels_last)
+pipeline.transformer = torch.compile(
+    pipeline.transformer, mode="max-autotune", fullgraph=True
+)
+
+prompt = """
+The camera rushes from far to near in a low-angle shot, 
+revealing a white ferret on a log. It plays, leaps into the water, and emerges, as the camera zooms in 
+for a close-up. Water splashes berry bushes nearby, while moss, snow, and leaves blanket the ground. 
+Birch trees and a light blue sky frame the scene, with ferns in the foreground. Side lighting casts dynamic 
+shadows and warm highlights. Medium composition, front view, low angle, with depth of field.
+"""
+negative_prompt = """
+Bright tones, overexposed, static, blurred details, subtitles, style, works, paintings, images, static, overall gray, worst quality, 
+low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, 
+misshapen limbs, fused fingers, still picture, messy background, three legs, many people in the background, walking backwards
+"""
+
+output = pipeline(
+    prompt=prompt,
+    negative_prompt=negative_prompt,
+    num_frames=81,
+    guidance_scale=5.0,
+).frames[0]
+export_to_video(output, "output.mp4", fps=16)
+```
+
+</hfoption>
+</hfoptions>
+
+### First-Last-Frame-to-Video Generation
+
+The example below demonstrates how to use the image-to-video pipeline to generate a video using a text description, a starting frame, and an ending frame.
+
+<hfoptions id="FLF2V usage">
+<hfoption id="usage">
+
+```python
+import numpy as np
+import torch
+import torchvision.transforms.functional as TF
+from diffusers import AutoencoderKLWan, WanImageToVideoPipeline
+from diffusers.utils import export_to_video, load_image
+from transformers import CLIPVisionModel
+
+
+model_id = "Wan-AI/Wan2.1-FLF2V-14B-720P-diffusers"
+image_encoder = CLIPVisionModel.from_pretrained(model_id, subfolder="image_encoder", torch_dtype=torch.float32)
+vae = AutoencoderKLWan.from_pretrained(model_id, subfolder="vae", torch_dtype=torch.float32)
+pipe = WanImageToVideoPipeline.from_pretrained(
+    model_id, vae=vae, image_encoder=image_encoder, torch_dtype=torch.bfloat16
+)
+pipe.to("cuda")
+
+first_frame = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/flf2v_input_first_frame.png")
+last_frame = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/flf2v_input_last_frame.png")
+
+def aspect_ratio_resize(image, pipe, max_area=720 * 1280):
+    aspect_ratio = image.height / image.width
+    mod_value = pipe.vae_scale_factor_spatial * pipe.transformer.config.patch_size[1]
+    height = round(np.sqrt(max_area * aspect_ratio)) // mod_value * mod_value
+    width = round(np.sqrt(max_area / aspect_ratio)) // mod_value * mod_value
+    image = image.resize((width, height))
+    return image, height, width
+
+def center_crop_resize(image, height, width):
+    # Calculate resize ratio to match first frame dimensions
+    resize_ratio = max(width / image.width, height / image.height)
+
+    # Resize the image
+    width = round(image.width * resize_ratio)
+    height = round(image.height * resize_ratio)
+    size = [width, height]
+    image = TF.center_crop(image, size)
+
+    return image, height, width
+
+first_frame, height, width = aspect_ratio_resize(first_frame, pipe)
+if last_frame.size != first_frame.size:
+    last_frame, _, _ = center_crop_resize(last_frame, height, width)
+
+prompt = "CG animation style, a small blue bird takes off from the ground, flapping its wings. The bird's feathers are delicate, with a unique pattern on its chest. The background shows a blue sky with white clouds under bright sunshine. The camera follows the bird upward, capturing its flight and the vastness of the sky from a close-up, low-angle perspective."
+
+output = pipe(
+    image=first_frame, last_image=last_frame, prompt=prompt, height=height, width=width, guidance_scale=5.5
+).frames[0]
+export_to_video(output, "output.mp4", fps=16)
+```
+
+</hfoption>
+</hfoptions>
+
+### Any-to-Video Controllable Generation
+
+Wan VACE supports various generation techniques which achieve controllable video generation. Some of the capabilities include:
+- Control to Video (Depth, Pose, Sketch, Flow, Grayscale, Scribble, Layout, Boundary Box, etc.). Recommended library for preprocessing videos to obtain control videos: [huggingface/controlnet_aux]()
+- Image/Video to Video (first frame, last frame, starting clip, ending clip, random clips)
+- Inpainting and Outpainting
+- Subject to Video (faces, object, characters, etc.)
+- Composition to Video (reference anything, animate anything, swap anything, expand anything, move anything, etc.)
+
+The code snippets available in [this](https://github.com/huggingface/diffusers/pull/11582) pull request demonstrate some examples of how videos can be generated with controllability signals.
+
+The general rule of thumb to keep in mind when preparing inputs for the VACE pipeline is that the input images, or frames of a video that you want to use for conditioning, should have a corresponding mask that is black in color. The black mask signifies that the model will not generate new content for that area, and only use those parts for conditioning the generation process. For parts/frames that should be generated by the model, the mask should be white in color.
+
+## Notes
+
+- Wan2.1 supports LoRAs with [`~loaders.WanLoraLoaderMixin.load_lora_weights`].
+
+  <details>
+  <summary>Show example code</summary>
+
+  ```py
+  # pip install ftfy
+  import torch
+  from diffusers import AutoModel, WanPipeline
+  from diffusers.schedulers.scheduling_unipc_multistep import UniPCMultistepScheduler
+  from diffusers.utils import export_to_video
+
+  vae = AutoModel.from_pretrained(
+      "Wan-AI/Wan2.1-T2V-1.3B-Diffusers", subfolder="vae", torch_dtype=torch.float32
+  )
+  pipeline = WanPipeline.from_pretrained(
+      "Wan-AI/Wan2.1-T2V-1.3B-Diffusers", vae=vae, torch_dtype=torch.bfloat16
+  )
+  pipeline.scheduler = UniPCMultistepScheduler.from_config(
+      pipeline.scheduler.config, flow_shift=5.0
+  )
+  pipeline.to("cuda")
+
+  pipeline.load_lora_weights("benjamin-paine/steamboat-willie-1.3b", adapter_name="steamboat-willie")
+  pipeline.set_adapters("steamboat-willie")
+
+  pipeline.enable_model_cpu_offload()
+
+  # use "steamboat willie style" to trigger the LoRA
+  prompt = """
+  steamboat willie style, golden era animation, The camera rushes from far to near in a low-angle shot, 
+  revealing a white ferret on a log. It plays, leaps into the water, and emerges, as the camera zooms in 
+  for a close-up. Water splashes berry bushes nearby, while moss, snow, and leaves blanket the ground. 
+  Birch trees and a light blue sky frame the scene, with ferns in the foreground. Side lighting casts dynamic 
+  shadows and warm highlights. Medium composition, front view, low angle, with depth of field.
+  """
+
+  output = pipeline(
+      prompt=prompt,
+      num_frames=81,
+      guidance_scale=5.0,
+  ).frames[0]
+  export_to_video(output, "output.mp4", fps=16)
+  ```
+
+  </details>
+
+- [`WanTransformer3DModel`] and [`AutoencoderKLWan`] supports loading from single files with [`~loaders.FromSingleFileMixin.from_single_file`].
+
+  <details>
+  <summary>Show example code</summary>
+
+  ```py
+  # pip install ftfy
+  import torch
+  from diffusers import WanPipeline, AutoModel
+
+  vae = AutoModel.from_single_file(
+      "https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/blob/main/split_files/vae/wan_2.1_vae.safetensors"
+  )
+  transformer = AutoModel.from_single_file(
+      "https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/blob/main/split_files/diffusion_models/wan2.1_t2v_1.3B_bf16.safetensors",
+      torch_dtype=torch.bfloat16
+  )
+  pipeline = WanPipeline.from_pretrained(
+      "Wan-AI/Wan2.1-T2V-1.3B-Diffusers",
+      vae=vae,
+      transformer=transformer,
+      torch_dtype=torch.bfloat16
+  )
+  ```
+
+  </details>
+
+- Set the [`AutoencoderKLWan`] dtype to `torch.float32` for better decoding quality.
+
+- The number of frames per second (fps) or `k` should be calculated by `4 * k + 1`.
+
+- Try lower `shift` values (`2.0` to `5.0`) for lower resolution videos and higher `shift` values (`7.0` to `12.0`) for higher resolution images.
+
+## WanPipeline
+
+[[autodoc]] WanPipeline
+  - all
+  - __call__
+
+## WanImageToVideoPipeline
+
+[[autodoc]] WanImageToVideoPipeline
+  - all
+  - __call__
+
+## WanVACEPipeline
+
+[[autodoc]] WanVACEPipeline
+  - all
+  - __call__
+
+## WanVideoToVideoPipeline
+
+[[autodoc]] WanVideoToVideoPipeline
+  - all
+  - __call__
+
+## WanPipelineOutput
+
+[[autodoc]] pipelines.wan.pipeline_output.WanPipelineOutput