Apply changes to LTX2LoraTests

* up

* fixes

* tests

* docs.

* fix

* change loading info.

* up

* up

.github/workflows/benchmark.yml

@@ -7,7 +7,7 @@ on:
 
 env:
   DIFFUSERS_IS_CI: yes
-  HF_HUB_ENABLE_HF_TRANSFER: 1
+  HF_XET_HIGH_PERFORMANCE: 1
   HF_HOME: /mnt/cache
   OMP_NUM_THREADS: 8
   MKL_NUM_THREADS: 8
@@ -28,7 +28,7 @@ jobs:
       options: --shm-size "16gb" --ipc host --gpus all
     steps:
       - name: Checkout diffusers
-        uses: actions/checkout@v3
+        uses: actions/checkout@v6
         with:
           fetch-depth: 2
       - name: NVIDIA-SMI
@@ -58,7 +58,7 @@ jobs:
 
       - name: Test suite reports artifacts
         if: ${{ always() }}
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v6
         with:
           name: benchmark_test_reports
           path: benchmarks/${{ env.BASE_PATH }}

.github/workflows/build_docker_images.yml

@@ -28,7 +28,7 @@ jobs:
         uses: docker/setup-buildx-action@v1
 
       - name: Check out code
-        uses: actions/checkout@v3
+        uses: actions/checkout@v6
 
       - name: Find Changed Dockerfiles
         id: file_changes
@@ -42,18 +42,39 @@ jobs:
           CHANGED_FILES: ${{ steps.file_changes.outputs.all }}
         run: |
           echo "$CHANGED_FILES"
-          for FILE in $CHANGED_FILES; do 
+          ALLOWED_IMAGES=(
+            diffusers-pytorch-cpu
+            diffusers-pytorch-cuda
+            diffusers-pytorch-xformers-cuda
+            diffusers-pytorch-minimum-cuda
+            diffusers-doc-builder
+          )
+
+          declare -A IMAGES_TO_BUILD=()
+
+          for FILE in $CHANGED_FILES; do
             # skip anything that isn't still on disk
-            if [[ ! -f "$FILE" ]]; then
+            if [[ ! -e "$FILE" ]]; then
               echo "Skipping removed file $FILE"
               continue
-            fi           
-            if [[ "$FILE" == docker/*Dockerfile ]]; then
-              DOCKER_PATH="${FILE%/Dockerfile}"
-              DOCKER_TAG=$(basename "$DOCKER_PATH")
-              echo "Building Docker image for $DOCKER_TAG"
-              docker build -t "$DOCKER_TAG" "$DOCKER_PATH"
             fi
+
+            for IMAGE in "${ALLOWED_IMAGES[@]}"; do
+              if [[ "$FILE" == docker/${IMAGE}/* ]]; then
+                IMAGES_TO_BUILD["$IMAGE"]=1
+              fi
+            done
+          done
+
+          if [[ ${#IMAGES_TO_BUILD[@]} -eq 0 ]]; then
+            echo "No relevant Docker changes detected."
+            exit 0
+          fi
+
+          for IMAGE in "${!IMAGES_TO_BUILD[@]}"; do
+            DOCKER_PATH="docker/${IMAGE}"
+            echo "Building Docker image for $IMAGE"
+            docker build -t "$IMAGE" "$DOCKER_PATH"
           done
         if: steps.file_changes.outputs.all != ''
 
@@ -78,7 +99,7 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v3
+        uses: actions/checkout@v6
       - name: Set up Docker Buildx
         uses: docker/setup-buildx-action@v1
       - name: Login to Docker Hub

.github/workflows/build_pr_documentation.yml

@@ -17,10 +17,10 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v4
+        uses: actions/checkout@v6
 
       - name: Set up Python
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v6
         with:
           python-version: '3.10'
 

.github/workflows/codeql.yml

@@ -0,0 +1,22 @@
+---
+name: CodeQL Security Analysis For Github Actions
+
+on:
+  push:
+    branches: ["main"]
+  workflow_dispatch:
+  # pull_request:
+
+jobs:
+  codeql:
+    name: CodeQL Analysis
+    uses: huggingface/security-workflows/.github/workflows/codeql-reusable.yml@v1
+    permissions:
+      security-events: write
+      packages: read
+      actions: read
+      contents: read
+    with:
+      languages: '["actions","python"]'
+      queries: 'security-extended,security-and-quality'
+      runner: 'ubuntu-latest' #optional if need custom runner

.github/workflows/mirror_community_pipeline.yml

@@ -24,7 +24,6 @@ jobs:
   mirror_community_pipeline:
     env:
       SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL_COMMUNITY_MIRROR }}
-
     runs-on: ubuntu-22.04
     steps:
       # Checkout to correct ref
@@ -39,37 +38,41 @@ jobs:
       #     If ref is 'refs/heads/main' => set 'main'
       #     Else it must be a tag => set {tag}
       - name: Set checkout_ref and path_in_repo
+        env:
+          EVENT_NAME: ${{ github.event_name }}
+          EVENT_INPUT_REF: ${{ github.event.inputs.ref }}
+          GITHUB_REF: ${{ github.ref }}
         run: |
-          if [ "${{ github.event_name }}" == "workflow_dispatch" ]; then
-            if [ -z "${{ github.event.inputs.ref }}" ]; then
+          if [ "$EVENT_NAME" == "workflow_dispatch" ]; then
+            if [ -z "$EVENT_INPUT_REF" ]; then
               echo "Error: Missing ref input"
               exit 1
-            elif [ "${{ github.event.inputs.ref }}" == "main" ]; then
+            elif [ "$EVENT_INPUT_REF" == "main" ]; then
               echo "CHECKOUT_REF=refs/heads/main" >> $GITHUB_ENV
               echo "PATH_IN_REPO=main" >> $GITHUB_ENV
             else
-              echo "CHECKOUT_REF=refs/tags/${{ github.event.inputs.ref }}" >> $GITHUB_ENV
-              echo "PATH_IN_REPO=${{ github.event.inputs.ref }}" >> $GITHUB_ENV
+              echo "CHECKOUT_REF=refs/tags/$EVENT_INPUT_REF" >> $GITHUB_ENV
+              echo "PATH_IN_REPO=$EVENT_INPUT_REF" >> $GITHUB_ENV
             fi
-          elif [ "${{ github.ref }}" == "refs/heads/main" ]; then
-            echo "CHECKOUT_REF=${{ github.ref }}" >> $GITHUB_ENV
+          elif [ "$GITHUB_REF" == "refs/heads/main" ]; then
+            echo "CHECKOUT_REF=$GITHUB_REF" >> $GITHUB_ENV
             echo "PATH_IN_REPO=main" >> $GITHUB_ENV
           else
             # e.g. refs/tags/v0.28.1 -> v0.28.1
-            echo "CHECKOUT_REF=${{ github.ref }}" >> $GITHUB_ENV
-            echo "PATH_IN_REPO=$(echo ${{ github.ref }} | sed 's/^refs\/tags\///')" >> $GITHUB_ENV
+            echo "CHECKOUT_REF=$GITHUB_REF" >> $GITHUB_ENV
+            echo "PATH_IN_REPO=$(echo $GITHUB_REF | sed 's/^refs\/tags\///')" >> $GITHUB_ENV
           fi
       - name: Print env vars
         run: |
           echo "CHECKOUT_REF: ${{ env.CHECKOUT_REF }}"
           echo "PATH_IN_REPO: ${{ env.PATH_IN_REPO }}"
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v6
         with:
           ref: ${{ env.CHECKOUT_REF }}
 
       # Setup + install dependencies
       - name: Set up Python
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v6
         with:
           python-version: "3.10"
       - name: Install dependencies
@@ -99,4 +102,4 @@ jobs:
       - name: Report failure status
         if: ${{ failure() }}
         run: |
-          pip install requests && python utils/notify_community_pipelines_mirror.py --status=failure
+          pip install requests && python utils/notify_community_pipelines_mirror.py --status=failure

.github/workflows/nightly_tests.yml

@@ -7,7 +7,7 @@ on:
 
 env:
   DIFFUSERS_IS_CI: yes
-  HF_HUB_ENABLE_HF_TRANSFER: 1
+  HF_XET_HIGH_PERFORMANCE: 1
   OMP_NUM_THREADS: 8
   MKL_NUM_THREADS: 8
   PYTEST_TIMEOUT: 600
@@ -28,7 +28,7 @@ jobs:
       pipeline_test_matrix: ${{ steps.fetch_pipeline_matrix.outputs.pipeline_test_matrix }}
     steps:
       - name: Checkout diffusers
-        uses: actions/checkout@v3
+        uses: actions/checkout@v6
         with:
           fetch-depth: 2
       - name: Install dependencies
@@ -44,7 +44,7 @@ jobs:
 
       - name: Pipeline Tests Artifacts
         if: ${{ always() }}
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v6
         with:
           name: test-pipelines.json
           path: reports
@@ -64,7 +64,7 @@ jobs:
       options: --shm-size "16gb" --ipc host --gpus all
     steps:
       - name: Checkout diffusers
-        uses: actions/checkout@v3
+        uses: actions/checkout@v6
         with:
           fetch-depth: 2
       - name: NVIDIA-SMI
@@ -73,6 +73,8 @@ jobs:
         run: |
           uv pip install -e ".[quality]"
           uv pip uninstall accelerate && uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
+          #uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
+          uv pip uninstall transformers huggingface_hub && uv pip install transformers==4.57.1 
           uv pip install pytest-reportlog
       - name: Environment
         run: |
@@ -84,7 +86,7 @@ jobs:
           CUBLAS_WORKSPACE_CONFIG: :16:8
         run: |
           pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-            -s -v -k "not Flax and not Onnx" \
+             -k "not Flax and not Onnx" \
             --make-reports=tests_pipeline_${{ matrix.module }}_cuda \
             --report-log=tests_pipeline_${{ matrix.module }}_cuda.log \
             tests/pipelines/${{ matrix.module }}
@@ -95,7 +97,7 @@ jobs:
           cat reports/tests_pipeline_${{ matrix.module }}_cuda_failures_short.txt
       - name: Test suite reports artifacts
         if: ${{ always() }}
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v6
         with:
           name: pipeline_${{ matrix.module }}_test_reports
           path: reports
@@ -117,7 +119,7 @@ jobs:
         module: [models, schedulers, lora, others, single_file, examples]
     steps:
     - name: Checkout diffusers
-      uses: actions/checkout@v3
+      uses: actions/checkout@v6
       with:
         fetch-depth: 2
 
@@ -126,6 +128,8 @@ jobs:
         uv pip install -e ".[quality]"
         uv pip install peft@git+https://github.com/huggingface/peft.git
         uv pip uninstall accelerate && uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
+        #uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
+        uv pip uninstall transformers huggingface_hub && uv pip install transformers==4.57.1 
         uv pip install pytest-reportlog
     - name: Environment
       run: python utils/print_env.py
@@ -138,7 +142,7 @@ jobs:
         CUBLAS_WORKSPACE_CONFIG: :16:8
       run: |
         pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-          -s -v -k "not Flax and not Onnx" \
+          -k "not Flax and not Onnx" \
           --make-reports=tests_torch_${{ matrix.module }}_cuda \
           --report-log=tests_torch_${{ matrix.module }}_cuda.log \
           tests/${{ matrix.module }}
@@ -151,7 +155,7 @@ jobs:
         CUBLAS_WORKSPACE_CONFIG: :16:8
       run: |
         pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-          -s -v --make-reports=examples_torch_cuda \
+          --make-reports=examples_torch_cuda \
           --report-log=examples_torch_cuda.log \
           examples/
 
@@ -163,7 +167,7 @@ jobs:
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v4
+      uses: actions/upload-artifact@v6
       with:
         name: torch_${{ matrix.module }}_cuda_test_reports
         path: reports
@@ -180,7 +184,7 @@ jobs:
 
     steps:
     - name: Checkout diffusers
-      uses: actions/checkout@v3
+      uses: actions/checkout@v6
       with:
         fetch-depth: 2
 
@@ -190,6 +194,8 @@ jobs:
     - name: Install dependencies
       run: |
         uv pip install -e ".[quality,training]"
+        #uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
+        uv pip uninstall transformers huggingface_hub && uv pip install transformers==4.57.1 
     - name: Environment
       run: |
         python utils/print_env.py
@@ -198,14 +204,14 @@ jobs:
         HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
         RUN_COMPILE: yes
       run: |
-        pytest -n 1 --max-worker-restart=0 --dist=loadfile -s -v -k "compile" --make-reports=tests_torch_compile_cuda tests/
+        pytest -n 1 --max-worker-restart=0 --dist=loadfile -k "compile" --make-reports=tests_torch_compile_cuda tests/
     - name: Failure short reports
       if: ${{ failure() }}
       run: cat reports/tests_torch_compile_cuda_failures_short.txt
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v4
+      uses: actions/upload-artifact@v6
       with:
         name: torch_compile_test_reports
         path: reports
@@ -222,7 +228,7 @@ jobs:
       options: --shm-size "16gb" --ipc host --gpus all
     steps:
       - name: Checkout diffusers
-        uses: actions/checkout@v3
+        uses: actions/checkout@v6
         with:
           fetch-depth: 2
       - name: NVIDIA-SMI
@@ -232,6 +238,8 @@ jobs:
           uv pip install -e ".[quality]"
           uv pip install peft@git+https://github.com/huggingface/peft.git
           uv pip uninstall accelerate && uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
+          #uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
+          uv pip uninstall transformers huggingface_hub && uv pip install transformers==4.57.1 
           uv pip install pytest-reportlog
       - name: Environment
         run: |
@@ -255,7 +263,7 @@ jobs:
           cat reports/tests_big_gpu_torch_cuda_failures_short.txt
       - name: Test suite reports artifacts
         if: ${{ always() }}
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v6
         with:
           name: torch_cuda_big_gpu_test_reports
           path: reports
@@ -272,7 +280,7 @@ jobs:
         shell: bash
     steps:
       - name: Checkout diffusers
-        uses: actions/checkout@v3
+        uses: actions/checkout@v6
         with:
           fetch-depth: 2
 
@@ -281,6 +289,8 @@ jobs:
           uv pip install -e ".[quality]"
           uv pip install peft@git+https://github.com/huggingface/peft.git
           uv pip uninstall accelerate && uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
+          #uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
+          uv pip uninstall transformers huggingface_hub && uv pip install transformers==4.57.1 
 
       - name: Environment
         run: |
@@ -293,7 +303,7 @@ jobs:
           CUBLAS_WORKSPACE_CONFIG: :16:8
         run: |
           pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-            -s -v -k "not Flax and not Onnx" \
+            -k "not Flax and not Onnx" \
             --make-reports=tests_torch_minimum_version_cuda \
             tests/models/test_modeling_common.py \
             tests/pipelines/test_pipelines_common.py \
@@ -311,7 +321,7 @@ jobs:
 
       - name: Test suite reports artifacts
         if: ${{ always() }}
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v6
         with:
           name: torch_minimum_version_cuda_test_reports
           path: reports
@@ -345,7 +355,7 @@ jobs:
       options: --shm-size "20gb" --ipc host --gpus all
     steps:
       - name: Checkout diffusers
-        uses: actions/checkout@v3
+        uses: actions/checkout@v6
         with:
           fetch-depth: 2
       - name: NVIDIA-SMI
@@ -358,6 +368,8 @@ jobs:
               uv pip install ${{ join(matrix.config.additional_deps, ' ') }}
           fi
           uv pip install pytest-reportlog
+          #uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
+          uv pip uninstall transformers huggingface_hub && uv pip install transformers==4.57.1 
       - name: Environment
         run: |
           python utils/print_env.py
@@ -379,7 +391,7 @@ jobs:
           cat reports/tests_${{ matrix.config.backend }}_torch_cuda_failures_short.txt
       - name: Test suite reports artifacts
         if: ${{ always() }}
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v6
         with:
           name: torch_cuda_${{ matrix.config.backend }}_reports
           path: reports
@@ -396,7 +408,7 @@ jobs:
       options: --shm-size "20gb" --ipc host --gpus all
     steps:
       - name: Checkout diffusers
-        uses: actions/checkout@v3
+        uses: actions/checkout@v6
         with:
           fetch-depth: 2
       - name: NVIDIA-SMI
@@ -405,6 +417,8 @@ jobs:
         run: |
           uv pip install -e ".[quality]"
           uv pip install -U bitsandbytes optimum_quanto
+          #uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
+          uv pip uninstall transformers huggingface_hub && uv pip install transformers==4.57.1 
           uv pip install pytest-reportlog
       - name: Environment
         run: |
@@ -427,7 +441,7 @@ jobs:
           cat reports/tests_pipeline_level_quant_torch_cuda_failures_short.txt
       - name: Test suite reports artifacts
         if: ${{ always() }}
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v6
         with:
           name: torch_cuda_pipeline_level_quant_reports
           path: reports
@@ -452,7 +466,7 @@ jobs:
       image: diffusers/diffusers-pytorch-cpu
     steps:
       - name: Checkout diffusers
-        uses: actions/checkout@v3
+        uses: actions/checkout@v6
         with:
           fetch-depth: 2
 
@@ -460,7 +474,7 @@ jobs:
         run: mkdir -p combined_reports
 
       - name: Download all test reports
-        uses: actions/download-artifact@v4
+        uses: actions/download-artifact@v7
         with:
           path: artifacts
 
@@ -486,7 +500,7 @@ jobs:
           cat $CONSOLIDATED_REPORT_PATH >> $GITHUB_STEP_SUMMARY
 
       - name: Upload consolidated report
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v6
         with:
           name: consolidated_test_report
           path: ${{ env.CONSOLIDATED_REPORT_PATH }}
@@ -500,7 +514,7 @@ jobs:
 #
 #    steps:
 #      - name: Checkout diffusers
-#        uses: actions/checkout@v3
+#        uses: actions/checkout@v6
 #        with:
 #          fetch-depth: 2
 #
@@ -531,7 +545,7 @@ jobs:
 #          HF_HOME: /System/Volumes/Data/mnt/cache
 #          HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
 #        run: |
-#          ${CONDA_RUN} pytest -n 1 -s -v --make-reports=tests_torch_mps \
+#          ${CONDA_RUN} pytest -n 1  --make-reports=tests_torch_mps \
 #            --report-log=tests_torch_mps.log \
 #            tests/
 #      - name: Failure short reports
@@ -540,7 +554,7 @@ jobs:
 #
 #      - name: Test suite reports artifacts
 #        if: ${{ always() }}
-#        uses: actions/upload-artifact@v4
+#        uses: actions/upload-artifact@v6
 #        with:
 #          name: torch_mps_test_reports
 #          path: reports
@@ -556,7 +570,7 @@ jobs:
 #
 #    steps:
 #      - name: Checkout diffusers
-#        uses: actions/checkout@v3
+#        uses: actions/checkout@v6
 #        with:
 #          fetch-depth: 2
 #
@@ -587,7 +601,7 @@ jobs:
 #          HF_HOME: /System/Volumes/Data/mnt/cache
 #          HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
 #        run: |
-#          ${CONDA_RUN} pytest -n 1 -s -v --make-reports=tests_torch_mps \
+#          ${CONDA_RUN} pytest -n 1  --make-reports=tests_torch_mps \
 #            --report-log=tests_torch_mps.log \
 #            tests/
 #      - name: Failure short reports
@@ -596,7 +610,7 @@ jobs:
 #
 #      - name: Test suite reports artifacts
 #        if: ${{ always() }}
-#        uses: actions/upload-artifact@v4
+#        uses: actions/upload-artifact@v6
 #        with:
 #          name: torch_mps_test_reports
 #          path: reports

.github/workflows/notify_slack_about_release.yml

@@ -10,10 +10,10 @@ jobs:
     runs-on: ubuntu-22.04
 
     steps:
-    - uses: actions/checkout@v3
+    - uses: actions/checkout@v6
 
     - name: Setup Python
-      uses: actions/setup-python@v4
+      uses: actions/setup-python@v6
       with:
         python-version: '3.8'
 

.github/workflows/pr_dependency_test.yml

@@ -18,9 +18,9 @@ jobs:
   check_dependencies:
     runs-on: ubuntu-22.04
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v6
       - name: Set up Python
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v6
         with:
           python-version: "3.8"
       - name: Install dependencies

.github/workflows/pr_modular_tests.yml

@@ -1,3 +1,4 @@
+
 name: Fast PR tests for Modular
 
 on:
@@ -26,7 +27,7 @@ concurrency:
 
 env:
   DIFFUSERS_IS_CI: yes
-  HF_HUB_ENABLE_HF_TRANSFER: 1
+  HF_XET_HIGH_PERFORMANCE: 1
   OMP_NUM_THREADS: 4
   MKL_NUM_THREADS: 4
   PYTEST_TIMEOUT: 60
@@ -35,9 +36,9 @@ jobs:
   check_code_quality:
     runs-on: ubuntu-22.04
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v6
       - name: Set up Python
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v6
         with:
           python-version: "3.10"
       - name: Install dependencies
@@ -55,9 +56,9 @@ jobs:
     needs: check_code_quality
     runs-on: ubuntu-22.04
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v6
       - name: Set up Python
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v6
         with:
           python-version: "3.10"
       - name: Install dependencies
@@ -77,23 +78,13 @@ jobs:
 
   run_fast_tests:
     needs: [check_code_quality, check_repository_consistency]
-    strategy:
-      fail-fast: false
-      matrix:
-        config:
-          - name: Fast PyTorch Modular Pipeline CPU tests
-            framework: pytorch_pipelines
-            runner: aws-highmemory-32-plus
-            image: diffusers/diffusers-pytorch-cpu
-            report: torch_cpu_modular_pipelines
-
-    name: ${{ matrix.config.name }}
+    name: Fast PyTorch Modular Pipeline CPU tests
 
     runs-on:
-      group: ${{ matrix.config.runner }}
+      group: aws-highmemory-32-plus
 
     container:
-      image: ${{ matrix.config.image }}
+      image: diffusers/diffusers-pytorch-cpu
       options: --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/
 
     defaults:
@@ -102,14 +93,15 @@ jobs:
 
     steps:
     - name: Checkout diffusers
-      uses: actions/checkout@v3
+      uses: actions/checkout@v6
       with:
         fetch-depth: 2
 
     - name: Install dependencies
       run: |
         uv pip install -e ".[quality]"
-        uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
+        #uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
+        uv pip uninstall transformers huggingface_hub && uv pip install transformers==4.57.1
         uv pip uninstall accelerate && uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git --no-deps
 
     - name: Environment
@@ -117,22 +109,19 @@ jobs:
         python utils/print_env.py
 
     - name: Run fast PyTorch Pipeline CPU tests
-      if: ${{ matrix.config.framework == 'pytorch_pipelines' }}
       run: |
         pytest -n 8 --max-worker-restart=0 --dist=loadfile \
-          -s -v -k "not Flax and not Onnx" \
-          --make-reports=tests_${{ matrix.config.report }} \
+          -k "not Flax and not Onnx" \
+          --make-reports=tests_torch_cpu_modular_pipelines \
           tests/modular_pipelines
 
     - name: Failure short reports
       if: ${{ failure() }}
-      run: cat reports/tests_${{ matrix.config.report }}_failures_short.txt
+      run: cat reports/tests_torch_cpu_modular_pipelines_failures_short.txt
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v4
+      uses: actions/upload-artifact@v6
       with:
-        name: pr_${{ matrix.config.framework }}_${{ matrix.config.report }}_test_reports
+        name: pr_pytorch_pipelines_torch_cpu_modular_pipelines_test_reports
         path: reports
-
-

.github/workflows/pr_test_fetcher.yml

@@ -28,7 +28,7 @@ jobs:
       test_map: ${{ steps.set_matrix.outputs.test_map }}
     steps:
     - name: Checkout diffusers
-      uses: actions/checkout@v3
+      uses: actions/checkout@v6
       with:
         fetch-depth: 0
     - name: Install dependencies
@@ -42,7 +42,7 @@ jobs:
       run: |
         python utils/tests_fetcher.py | tee test_preparation.txt
     - name: Report fetched tests
-      uses: actions/upload-artifact@v3
+      uses: actions/upload-artifact@v6
       with:
         name: test_fetched
         path: test_preparation.txt
@@ -83,7 +83,7 @@ jobs:
         shell: bash
     steps:
     - name: Checkout diffusers
-      uses: actions/checkout@v3
+      uses: actions/checkout@v6
       with:
         fetch-depth: 2
 
@@ -109,7 +109,7 @@ jobs:
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v3
+      uses: actions/upload-artifact@v6
       with:
           name: ${{ matrix.modules }}_test_reports
           path: reports
@@ -138,7 +138,7 @@ jobs:
 
     steps:
     - name: Checkout diffusers
-      uses: actions/checkout@v3
+      uses: actions/checkout@v6
       with:
         fetch-depth: 2
 
@@ -164,7 +164,7 @@ jobs:
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v4
+      uses: actions/upload-artifact@v6
       with:
         name: pr_${{ matrix.config.report }}_test_reports
         path: reports

.github/workflows/pr_tests.yml

@@ -22,7 +22,7 @@ concurrency:
 
 env:
   DIFFUSERS_IS_CI: yes
-  HF_HUB_ENABLE_HF_TRANSFER: 1
+  HF_XET_HIGH_PERFORMANCE: 1
   OMP_NUM_THREADS: 4
   MKL_NUM_THREADS: 4
   PYTEST_TIMEOUT: 60
@@ -31,9 +31,9 @@ jobs:
   check_code_quality:
     runs-on: ubuntu-22.04
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v6
       - name: Set up Python
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v6
         with:
           python-version: "3.8"
       - name: Install dependencies
@@ -51,9 +51,9 @@ jobs:
     needs: check_code_quality
     runs-on: ubuntu-22.04
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v6
       - name: Set up Python
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v6
         with:
           python-version: "3.8"
       - name: Install dependencies
@@ -108,14 +108,15 @@ jobs:
 
     steps:
     - name: Checkout diffusers
-      uses: actions/checkout@v3
+      uses: actions/checkout@v6
       with:
         fetch-depth: 2
 
     - name: Install dependencies
       run: |
         uv pip install -e ".[quality]"
-        uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
+        #uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
+        uv pip uninstall transformers huggingface_hub && uv pip install transformers==4.57.1
         uv pip uninstall accelerate && uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git --no-deps
 
     - name: Environment
@@ -126,7 +127,7 @@ jobs:
       if: ${{ matrix.config.framework == 'pytorch_pipelines' }}
       run: |
         pytest -n 8 --max-worker-restart=0 --dist=loadfile \
-          -s -v -k "not Flax and not Onnx" \
+          -k "not Flax and not Onnx" \
           --make-reports=tests_${{ matrix.config.report }} \
           tests/pipelines
 
@@ -134,7 +135,7 @@ jobs:
       if: ${{ matrix.config.framework == 'pytorch_models' }}
       run: |
         pytest -n 4 --max-worker-restart=0 --dist=loadfile \
-          -s -v -k "not Flax and not Onnx and not Dependency" \
+          -k "not Flax and not Onnx and not Dependency" \
           --make-reports=tests_${{ matrix.config.report }} \
           tests/models tests/schedulers tests/others
 
@@ -152,7 +153,7 @@ jobs:
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v4
+      uses: actions/upload-artifact@v6
       with:
         name: pr_${{ matrix.config.framework }}_${{ matrix.config.report }}_test_reports
         path: reports
@@ -184,7 +185,7 @@ jobs:
 
     steps:
     - name: Checkout diffusers
-      uses: actions/checkout@v3
+      uses: actions/checkout@v6
       with:
         fetch-depth: 2
 
@@ -210,7 +211,7 @@ jobs:
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v4
+      uses: actions/upload-artifact@v6
       with:
         name: pr_${{ matrix.config.report }}_test_reports
         path: reports
@@ -235,7 +236,7 @@ jobs:
 
     steps:
     - name: Checkout diffusers
-      uses: actions/checkout@v3
+      uses: actions/checkout@v6
       with:
         fetch-depth: 2
 
@@ -246,7 +247,8 @@ jobs:
         uv pip install -U peft@git+https://github.com/huggingface/peft.git --no-deps
         uv pip install -U tokenizers
         uv pip uninstall accelerate && uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git --no-deps
-        uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
+        #uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
+        uv pip uninstall transformers huggingface_hub && uv pip install transformers==4.57.1
 
     - name: Environment
       run: |
@@ -255,11 +257,11 @@ jobs:
     - name: Run fast PyTorch LoRA tests with PEFT
       run: |
         pytest -n 4 --max-worker-restart=0 --dist=loadfile \
-          -s -v \
+          \
           --make-reports=tests_peft_main \
           tests/lora/
         pytest -n 4 --max-worker-restart=0 --dist=loadfile \
-          -s -v \
+          \
           --make-reports=tests_models_lora_peft_main \
           tests/models/ -k "lora"
 
@@ -271,7 +273,7 @@ jobs:
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v4
+      uses: actions/upload-artifact@v6
       with:
         name: pr_main_test_reports
         path: reports

.github/workflows/pr_tests_gpu.yml

@@ -1,4 +1,4 @@
-name: Fast GPU Tests on PR 
+name: Fast GPU Tests on PR
 
 on:
   pull_request:
@@ -24,7 +24,7 @@ env:
   DIFFUSERS_IS_CI: yes
   OMP_NUM_THREADS: 8
   MKL_NUM_THREADS: 8
-  HF_HUB_ENABLE_HF_TRANSFER: 1
+  HF_XET_HIGH_PERFORMANCE: 1
   PYTEST_TIMEOUT: 600
   PIPELINE_USAGE_CUTOFF: 1000000000 # set high cutoff so that only always-test pipelines run
 
@@ -32,9 +32,9 @@ jobs:
   check_code_quality:
     runs-on: ubuntu-22.04
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v6
       - name: Set up Python
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v6
         with:
           python-version: "3.8"
       - name: Install dependencies
@@ -52,9 +52,9 @@ jobs:
     needs: check_code_quality
     runs-on: ubuntu-22.04
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v6
       - name: Set up Python
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v6
         with:
           python-version: "3.8"
       - name: Install dependencies
@@ -71,7 +71,7 @@ jobs:
         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
@@ -83,7 +83,7 @@ jobs:
       pipeline_test_matrix: ${{ steps.fetch_pipeline_matrix.outputs.pipeline_test_matrix }}
     steps:
       - name: Checkout diffusers
-        uses: actions/checkout@v3
+        uses: actions/checkout@v6
         with:
           fetch-depth: 2
       - name: Install dependencies
@@ -100,7 +100,7 @@ jobs:
           echo "pipeline_test_matrix=$matrix" >> $GITHUB_OUTPUT
       - name: Pipeline Tests Artifacts
         if: ${{ always() }}
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v6
         with:
           name: test-pipelines.json
           path: reports
@@ -120,7 +120,7 @@ jobs:
       options: --shm-size "16gb" --ipc host --gpus all
     steps:
       - name: Checkout diffusers
-        uses: actions/checkout@v3
+        uses: actions/checkout@v6
         with:
           fetch-depth: 2
 
@@ -131,7 +131,8 @@ jobs:
         run: |
           uv pip install -e ".[quality]"
           uv pip uninstall accelerate && uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
-          uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
+          #uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
+          uv pip uninstall transformers huggingface_hub && uv pip install transformers==4.57.1
 
       - name: Environment
         run: |
@@ -149,18 +150,18 @@ jobs:
           # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
           CUBLAS_WORKSPACE_CONFIG: :16:8
         run: |
-          if [ "${{ matrix.module }}" = "ip_adapters" ]; then 
+          if [ "${{ matrix.module }}" = "ip_adapters" ]; then
               pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-              -s -v -k "not Flax and not Onnx" \
+              -k "not Flax and not Onnx" \
               --make-reports=tests_pipeline_${{ matrix.module }}_cuda \
               tests/pipelines/${{ matrix.module }}
-          else 
+          else
               pattern=$(cat ${{ steps.extract_tests.outputs.pattern_file }})
               pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-              -s -v -k "not Flax and not Onnx and $pattern" \
+              -k "not Flax and not Onnx and $pattern" \
               --make-reports=tests_pipeline_${{ matrix.module }}_cuda \
               tests/pipelines/${{ matrix.module }}
-          fi 
+          fi
 
       - name: Failure short reports
         if: ${{ failure() }}
@@ -169,7 +170,7 @@ jobs:
           cat reports/tests_pipeline_${{ matrix.module }}_cuda_failures_short.txt
       - name: Test suite reports artifacts
         if: ${{ always() }}
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v6
         with:
           name: pipeline_${{ matrix.module }}_test_reports
           path: reports
@@ -192,7 +193,7 @@ jobs:
         module: [models, schedulers, lora, others]
     steps:
     - name: Checkout diffusers
-      uses: actions/checkout@v3
+      uses: actions/checkout@v6
       with:
         fetch-depth: 2
 
@@ -201,7 +202,8 @@ jobs:
         uv pip install -e ".[quality]"
         uv pip install peft@git+https://github.com/huggingface/peft.git
         uv pip uninstall accelerate && uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
-        uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
+        #uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
+        uv pip uninstall transformers huggingface_hub && uv pip install transformers==4.57.1
 
     - name: Environment
       run: |
@@ -222,11 +224,11 @@ jobs:
       run: |
         pattern=$(cat ${{ steps.extract_tests.outputs.pattern_file }})
         if [ -z "$pattern" ]; then
-          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 }}  
+          pytest -n 1  --max-worker-restart=0 --dist=loadfile -k "not Flax and not Onnx" tests/${{ matrix.module }} \
+          --make-reports=tests_torch_cuda_${{ matrix.module }}
         else
-          pytest -n 1 -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 }}  
+          pytest -n 1  --max-worker-restart=0 --dist=loadfile -k "not Flax and not Onnx and $pattern" tests/${{ matrix.module }} \
+          --make-reports=tests_torch_cuda_${{ matrix.module }}
         fi
 
     - name: Failure short reports
@@ -237,7 +239,7 @@ jobs:
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v4
+      uses: actions/upload-artifact@v6
       with:
         name: torch_cuda_test_reports_${{ matrix.module }}
         path: reports
@@ -253,7 +255,7 @@ jobs:
       options: --gpus all --shm-size "16gb" --ipc host
     steps:
     - name: Checkout diffusers
-      uses: actions/checkout@v3
+      uses: actions/checkout@v6
       with:
         fetch-depth: 2
 
@@ -262,7 +264,8 @@ jobs:
         nvidia-smi
     - name: Install dependencies
       run: |
-        uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
+        #uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
+        uv pip uninstall transformers huggingface_hub && uv pip install transformers==4.57.1
         uv pip install -e ".[quality,training]"
 
     - name: Environment
@@ -274,7 +277,7 @@ jobs:
         HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
       run: |
         uv pip install ".[training]"
-        pytest -n 1 --max-worker-restart=0 --dist=loadfile -s -v --make-reports=examples_torch_cuda examples/
+        pytest -n 1 --max-worker-restart=0 --dist=loadfile --make-reports=examples_torch_cuda examples/
 
     - name: Failure short reports
       if: ${{ failure() }}
@@ -284,7 +287,7 @@ jobs:
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v4
+      uses: actions/upload-artifact@v6
       with:
         name: examples_test_reports
         path: reports

.github/workflows/pr_torch_dependency_test.yml

@@ -18,9 +18,9 @@ jobs:
   check_torch_dependencies:
     runs-on: ubuntu-22.04
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v6
       - name: Set up Python
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v6
         with:
           python-version: "3.8"
       - name: Install dependencies

.github/workflows/push_tests.yml

@@ -14,7 +14,7 @@ env:
   DIFFUSERS_IS_CI: yes
   OMP_NUM_THREADS: 8
   MKL_NUM_THREADS: 8
-  HF_HUB_ENABLE_HF_TRANSFER: 1
+  HF_XET_HIGH_PERFORMANCE: 1
   PYTEST_TIMEOUT: 600
   PIPELINE_USAGE_CUTOFF: 50000
 
@@ -29,7 +29,7 @@ jobs:
       pipeline_test_matrix: ${{ steps.fetch_pipeline_matrix.outputs.pipeline_test_matrix }}
     steps:
       - name: Checkout diffusers
-        uses: actions/checkout@v3
+        uses: actions/checkout@v6
         with:
           fetch-depth: 2
       - name: Install dependencies
@@ -46,7 +46,7 @@ jobs:
           echo "pipeline_test_matrix=$matrix" >> $GITHUB_OUTPUT
       - name: Pipeline Tests Artifacts
         if: ${{ always() }}
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v6
         with:
           name: test-pipelines.json
           path: reports
@@ -66,7 +66,7 @@ jobs:
       options: --shm-size "16gb" --ipc host --gpus all
     steps:
       - name: Checkout diffusers
-        uses: actions/checkout@v3
+        uses: actions/checkout@v6
         with:
           fetch-depth: 2
       - name: NVIDIA-SMI
@@ -76,6 +76,8 @@ jobs:
         run: |
           uv pip install -e ".[quality]"
           uv pip uninstall accelerate && uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
+          #uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
+          uv pip uninstall transformers huggingface_hub && uv pip install transformers==4.57.1
       - name: Environment
         run: |
           python utils/print_env.py
@@ -86,7 +88,7 @@ jobs:
           CUBLAS_WORKSPACE_CONFIG: :16:8
         run: |
           pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-            -s -v -k "not Flax and not Onnx" \
+            -k "not Flax and not Onnx" \
             --make-reports=tests_pipeline_${{ matrix.module }}_cuda \
             tests/pipelines/${{ matrix.module }}
       - name: Failure short reports
@@ -96,7 +98,7 @@ jobs:
           cat reports/tests_pipeline_${{ matrix.module }}_cuda_failures_short.txt
       - name: Test suite reports artifacts
         if: ${{ always() }}
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v6
         with:
           name: pipeline_${{ matrix.module }}_test_reports
           path: reports
@@ -118,7 +120,7 @@ jobs:
         module: [models, schedulers, lora, others, single_file]
     steps:
     - name: Checkout diffusers
-      uses: actions/checkout@v3
+      uses: actions/checkout@v6
       with:
         fetch-depth: 2
 
@@ -127,6 +129,8 @@ jobs:
         uv pip install -e ".[quality]"
         uv pip install peft@git+https://github.com/huggingface/peft.git
         uv pip uninstall accelerate && uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
+        #uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
+        uv pip uninstall transformers huggingface_hub && uv pip install transformers==4.57.1
 
     - name: Environment
       run: |
@@ -139,7 +143,7 @@ jobs:
         CUBLAS_WORKSPACE_CONFIG: :16:8
       run: |
         pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-          -s -v -k "not Flax and not Onnx" \
+          -k "not Flax and not Onnx" \
           --make-reports=tests_torch_cuda_${{ matrix.module }} \
           tests/${{ matrix.module }}
 
@@ -151,7 +155,7 @@ jobs:
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v4
+      uses: actions/upload-artifact@v6
       with:
         name: torch_cuda_test_reports_${{ matrix.module }}
         path: reports
@@ -168,7 +172,7 @@ jobs:
 
     steps:
     - name: Checkout diffusers
-      uses: actions/checkout@v3
+      uses: actions/checkout@v6
       with:
         fetch-depth: 2
 
@@ -178,6 +182,8 @@ jobs:
     - name: Install dependencies
       run: |
         uv pip install -e ".[quality,training]"
+        #uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
+        uv pip uninstall transformers huggingface_hub && uv pip install transformers==4.57.1
     - name: Environment
       run: |
         python utils/print_env.py
@@ -186,14 +192,14 @@ jobs:
         HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
         RUN_COMPILE: yes
       run: |
-        pytest -n 1 --max-worker-restart=0 --dist=loadfile -s -v -k "compile" --make-reports=tests_torch_compile_cuda tests/
+        pytest -n 1 --max-worker-restart=0 --dist=loadfile -k "compile" --make-reports=tests_torch_compile_cuda tests/
     - name: Failure short reports
       if: ${{ failure() }}
       run: cat reports/tests_torch_compile_cuda_failures_short.txt
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v4
+      uses: actions/upload-artifact@v6
       with:
         name: torch_compile_test_reports
         path: reports
@@ -210,7 +216,7 @@ jobs:
 
     steps:
     - name: Checkout diffusers
-      uses: actions/checkout@v3
+      uses: actions/checkout@v6
       with:
         fetch-depth: 2
 
@@ -227,14 +233,14 @@ jobs:
       env:
         HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
       run: |
-        pytest -n 1 --max-worker-restart=0 --dist=loadfile -s -v -k "xformers" --make-reports=tests_torch_xformers_cuda tests/
+        pytest -n 1 --max-worker-restart=0 --dist=loadfile -k "xformers" --make-reports=tests_torch_xformers_cuda tests/
     - name: Failure short reports
       if: ${{ failure() }}
       run: cat reports/tests_torch_xformers_cuda_failures_short.txt
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v4
+      uses: actions/upload-artifact@v6
       with:
         name: torch_xformers_test_reports
         path: reports
@@ -250,7 +256,7 @@ jobs:
       options: --gpus all --shm-size "16gb" --ipc host
     steps:
     - name: Checkout diffusers
-      uses: actions/checkout@v3
+      uses: actions/checkout@v6
       with:
         fetch-depth: 2
 
@@ -270,7 +276,7 @@ jobs:
         HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
       run: |
         uv pip install ".[training]"
-        pytest -n 1 --max-worker-restart=0 --dist=loadfile -s -v --make-reports=examples_torch_cuda examples/
+        pytest -n 1 --max-worker-restart=0 --dist=loadfile --make-reports=examples_torch_cuda examples/
 
     - name: Failure short reports
       if: ${{ failure() }}
@@ -280,7 +286,7 @@ jobs:
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v4
+      uses: actions/upload-artifact@v6
       with:
         name: examples_test_reports
         path: reports

.github/workflows/push_tests_fast.yml

@@ -18,7 +18,7 @@ env:
   HF_HOME: /mnt/cache
   OMP_NUM_THREADS: 8
   MKL_NUM_THREADS: 8
-  HF_HUB_ENABLE_HF_TRANSFER: 1
+  HF_XET_HIGH_PERFORMANCE: 1
   PYTEST_TIMEOUT: 600
   RUN_SLOW: no
 
@@ -54,7 +54,7 @@ jobs:
 
     steps:
     - name: Checkout diffusers
-      uses: actions/checkout@v3
+      uses: actions/checkout@v6
       with:
         fetch-depth: 2
 
@@ -70,7 +70,7 @@ jobs:
       if: ${{ matrix.config.framework == 'pytorch' }}
       run: |
         pytest -n 4 --max-worker-restart=0 --dist=loadfile \
-          -s -v -k "not Flax and not Onnx" \
+          -k "not Flax and not Onnx" \
           --make-reports=tests_${{ matrix.config.report }} \
           tests/
 
@@ -88,7 +88,7 @@ jobs:
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v4
+      uses: actions/upload-artifact@v6
       with:
         name: pr_${{ matrix.config.report }}_test_reports
         path: reports

.github/workflows/push_tests_mps.yml

@@ -8,7 +8,7 @@ env:
   HF_HOME: /mnt/cache
   OMP_NUM_THREADS: 8
   MKL_NUM_THREADS: 8
-  HF_HUB_ENABLE_HF_TRANSFER: 1
+  HF_XET_HIGH_PERFORMANCE: 1
   PYTEST_TIMEOUT: 600
   RUN_SLOW: no
 
@@ -23,7 +23,7 @@ jobs:
 
     steps:
     - name: Checkout diffusers
-      uses: actions/checkout@v3
+      uses: actions/checkout@v6
       with:
         fetch-depth: 2
 
@@ -57,7 +57,7 @@ jobs:
         HF_HOME: /System/Volumes/Data/mnt/cache
         HF_TOKEN: ${{ secrets.HF_TOKEN }}
       run: |
-        ${CONDA_RUN} python -m pytest -n 0 -s -v --make-reports=tests_torch_mps tests/
+        ${CONDA_RUN} python -m pytest -n 0 --make-reports=tests_torch_mps tests/
 
     - name: Failure short reports
       if: ${{ failure() }}
@@ -65,7 +65,7 @@ jobs:
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v4
+      uses: actions/upload-artifact@v6
       with:
         name: pr_torch_mps_test_reports
         path: reports

.github/workflows/pypi_publish.yaml

@@ -15,10 +15,10 @@ jobs:
       latest_branch: ${{ steps.set_latest_branch.outputs.latest_branch }}
     steps:
       - name: Checkout Repo
-        uses: actions/checkout@v3
+        uses: actions/checkout@v6
 
       - name: Set up Python
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v6
         with:
           python-version: '3.8'
 
@@ -40,12 +40,12 @@ jobs:
 
     steps:
       - name: Checkout Repo
-        uses: actions/checkout@v3
+        uses: actions/checkout@v6
         with:
           ref: ${{ needs.find-and-checkout-latest-branch.outputs.latest_branch }}
 
       - name: Setup Python
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v6
         with:
           python-version: "3.8"
 

.github/workflows/release_tests_fast.yml

@@ -27,7 +27,7 @@ jobs:
       pipeline_test_matrix: ${{ steps.fetch_pipeline_matrix.outputs.pipeline_test_matrix }}
     steps:
       - name: Checkout diffusers
-        uses: actions/checkout@v3
+        uses: actions/checkout@v6
         with:
           fetch-depth: 2
       - name: Install dependencies
@@ -44,7 +44,7 @@ jobs:
           echo "pipeline_test_matrix=$matrix" >> $GITHUB_OUTPUT
       - name: Pipeline Tests Artifacts
         if: ${{ always() }}
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v6
         with:
           name: test-pipelines.json
           path: reports
@@ -64,7 +64,7 @@ jobs:
       options: --shm-size "16gb" --ipc host --gpus all
     steps:
       - name: Checkout diffusers
-        uses: actions/checkout@v3
+        uses: actions/checkout@v6
         with:
           fetch-depth: 2
       - name: NVIDIA-SMI
@@ -84,7 +84,7 @@ jobs:
           CUBLAS_WORKSPACE_CONFIG: :16:8
         run: |
           pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-            -s -v -k "not Flax and not Onnx" \
+            -k "not Flax and not Onnx" \
             --make-reports=tests_pipeline_${{ matrix.module }}_cuda \
             tests/pipelines/${{ matrix.module }}
       - name: Failure short reports
@@ -94,7 +94,7 @@ jobs:
           cat reports/tests_pipeline_${{ matrix.module }}_cuda_failures_short.txt
       - name: Test suite reports artifacts
         if: ${{ always() }}
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v6
         with:
           name: pipeline_${{ matrix.module }}_test_reports
           path: reports
@@ -116,7 +116,7 @@ jobs:
         module: [models, schedulers, lora, others, single_file]
     steps:
     - name: Checkout diffusers
-      uses: actions/checkout@v3
+      uses: actions/checkout@v6
       with:
         fetch-depth: 2
 
@@ -137,7 +137,7 @@ jobs:
         CUBLAS_WORKSPACE_CONFIG: :16:8
       run: |
         pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-          -s -v -k "not Flax and not Onnx" \
+          -k "not Flax and not Onnx" \
           --make-reports=tests_torch_${{ matrix.module }}_cuda \
           tests/${{ matrix.module }}
 
@@ -149,7 +149,7 @@ jobs:
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v4
+      uses: actions/upload-artifact@v6
       with:
         name: torch_cuda_${{ matrix.module }}_test_reports
         path: reports
@@ -166,7 +166,7 @@ jobs:
         shell: bash
     steps:
       - name: Checkout diffusers
-        uses: actions/checkout@v3
+        uses: actions/checkout@v6
         with:
           fetch-depth: 2
 
@@ -187,7 +187,7 @@ jobs:
           CUBLAS_WORKSPACE_CONFIG: :16:8
         run: |
           pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-            -s -v -k "not Flax and not Onnx" \
+            -k "not Flax and not Onnx" \
             --make-reports=tests_torch_minimum_cuda \
             tests/models/test_modeling_common.py \
             tests/pipelines/test_pipelines_common.py \
@@ -205,7 +205,7 @@ jobs:
 
       - name: Test suite reports artifacts
         if: ${{ always() }}
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v6
         with:
           name: torch_minimum_version_cuda_test_reports
           path: reports
@@ -222,7 +222,7 @@ jobs:
 
     steps:
     - name: Checkout diffusers
-      uses: actions/checkout@v3
+      uses: actions/checkout@v6
       with:
         fetch-depth: 2
 
@@ -240,14 +240,14 @@ jobs:
         HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
         RUN_COMPILE: yes
       run: |
-        pytest -n 1 --max-worker-restart=0 --dist=loadfile -s -v -k "compile" --make-reports=tests_torch_compile_cuda tests/
+        pytest -n 1 --max-worker-restart=0 --dist=loadfile -k "compile" --make-reports=tests_torch_compile_cuda tests/
     - name: Failure short reports
       if: ${{ failure() }}
       run: cat reports/tests_torch_compile_cuda_failures_short.txt
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v4
+      uses: actions/upload-artifact@v6
       with:
         name: torch_compile_test_reports
         path: reports
@@ -264,7 +264,7 @@ jobs:
 
     steps:
     - name: Checkout diffusers
-      uses: actions/checkout@v3
+      uses: actions/checkout@v6
       with:
         fetch-depth: 2
 
@@ -281,14 +281,14 @@ jobs:
       env:
         HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
       run: |
-        pytest -n 1 --max-worker-restart=0 --dist=loadfile -s -v -k "xformers" --make-reports=tests_torch_xformers_cuda tests/
+        pytest -n 1 --max-worker-restart=0 --dist=loadfile -k "xformers" --make-reports=tests_torch_xformers_cuda tests/
     - name: Failure short reports
       if: ${{ failure() }}
       run: cat reports/tests_torch_xformers_cuda_failures_short.txt
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v4
+      uses: actions/upload-artifact@v6
       with:
         name: torch_xformers_test_reports
         path: reports
@@ -305,7 +305,7 @@ jobs:
 
     steps:
     - name: Checkout diffusers
-      uses: actions/checkout@v3
+      uses: actions/checkout@v6
       with:
         fetch-depth: 2
 
@@ -326,7 +326,7 @@ jobs:
         HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
       run: |
         uv pip install ".[training]"
-        pytest -n 1 --max-worker-restart=0 --dist=loadfile -s -v --make-reports=examples_torch_cuda examples/
+        pytest -n 1 --max-worker-restart=0 --dist=loadfile --make-reports=examples_torch_cuda examples/
 
     - name: Failure short reports
       if: ${{ failure() }}
@@ -336,7 +336,7 @@ jobs:
 
     - name: Test suite reports artifacts
       if: ${{ always() }}
-      uses: actions/upload-artifact@v4
+      uses: actions/upload-artifact@v6
       with:
         name: examples_test_reports
         path: reports

.github/workflows/run_tests_from_a_pr.yml

@@ -57,7 +57,7 @@ jobs:
         shell: bash -e {0}
 
       - name: Checkout PR branch
-        uses: actions/checkout@v4
+        uses: actions/checkout@v6
         with:
           ref: refs/pull/${{ inputs.pr_number }}/head
 

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

@@ -27,7 +27,7 @@ jobs:
 
     steps:
       - name: Checkout diffusers
-        uses: actions/checkout@v3
+        uses: actions/checkout@v6
         with:
           fetch-depth: 2
 

.github/workflows/ssh-runner.yml

@@ -35,7 +35,7 @@ jobs:
 
     steps:
       - name: Checkout diffusers
-        uses: actions/checkout@v3
+        uses: actions/checkout@v6
         with:
           fetch-depth: 2
 

.github/workflows/stale.yml

@@ -15,10 +15,10 @@ jobs:
     env:
       GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
     steps:
-    - uses: actions/checkout@v2
+    - uses: actions/checkout@v6
 
     - name: Setup Python
-      uses: actions/setup-python@v1
+      uses: actions/setup-python@v6
       with:
         python-version: 3.8
 

.github/workflows/trufflehog.yml

@@ -8,7 +8,7 @@ jobs:
     runs-on: ubuntu-22.04
     steps:
     - name: Checkout code
-      uses: actions/checkout@v4
+      uses: actions/checkout@v6
       with:
         fetch-depth: 0
     - name: Secret Scanning

.github/workflows/typos.yml

@@ -8,7 +8,7 @@ jobs:
     runs-on: ubuntu-22.04
 
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v6
 
       - name: typos-action
         uses: crate-ci/typos@v1.12.4

.github/workflows/update_metadata.yml

@@ -15,7 +15,7 @@ jobs:
         shell: bash -l {0}
 
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v6
 
       - name: Setup environment
         run: |

docker/diffusers-doc-builder/Dockerfile

@@ -33,7 +33,7 @@ RUN uv pip install --no-cache-dir "git+https://github.com/huggingface/diffusers.
 RUN uv pip install --no-cache-dir \
     accelerate \
     numpy==1.26.4 \
-    hf_transfer \
+    hf_xet \
     setuptools==69.5.1 \
     bitsandbytes \
     torchao \

docker/diffusers-onnxruntime-cpu/Dockerfile

@@ -44,6 +44,6 @@ RUN python3 -m pip install --no-cache-dir --upgrade pip uv==0.1.11 && \
         scipy \
         tensorboard \
         transformers \
-        hf_transfer
+        hf_xet
 
 CMD ["/bin/bash"]

docker/diffusers-onnxruntime-cuda/Dockerfile

@@ -38,13 +38,12 @@ RUN python3.10 -m pip install --no-cache-dir --upgrade pip uv==0.1.11 && \
         datasets \
         hf-doc-builder \
         huggingface-hub \
-        hf_transfer \
+        hf_xet \
         Jinja2 \
         librosa \
         numpy==1.26.4 \
         scipy \
         tensorboard \
-        transformers \
-        hf_transfer
+        transformers
 
 CMD ["/bin/bash"]

docker/diffusers-pytorch-cpu/Dockerfile

@@ -31,7 +31,7 @@ RUN uv pip install --no-cache-dir "git+https://github.com/huggingface/diffusers.
 RUN uv pip install --no-cache-dir \
     accelerate \
     numpy==1.26.4 \
-    hf_transfer
+    hf_xet
 
 RUN apt-get clean && rm -rf /var/lib/apt/lists/* && apt-get autoremove && apt-get autoclean
 

docker/diffusers-pytorch-cuda/Dockerfile

@@ -44,6 +44,6 @@ RUN uv pip install --no-cache-dir \
     accelerate \
     numpy==1.26.4 \
     pytorch-lightning \
-    hf_transfer
+    hf_xet
 
 CMD ["/bin/bash"]

docker/diffusers-pytorch-minimum-cuda/Dockerfile

@@ -47,6 +47,6 @@ RUN uv pip install --no-cache-dir \
     accelerate \
     numpy==1.26.4 \
     pytorch-lightning \
-    hf_transfer
+    hf_xet
 
 CMD ["/bin/bash"]

docker/diffusers-pytorch-xformers-cuda/Dockerfile

@@ -44,7 +44,7 @@ RUN uv pip install --no-cache-dir \
     accelerate \
     numpy==1.26.4 \
     pytorch-lightning \
-    hf_transfer \
+    hf_xet \
     xformers
 
 CMD ["/bin/bash"]

docs/source/en/_toctree.yml

@@ -22,6 +22,8 @@
     title: Reproducibility
   - local: using-diffusers/schedulers
     title: Schedulers
+  - local: using-diffusers/automodel
+    title: AutoModel
   - local: using-diffusers/other-formats
     title: Model formats
   - local: using-diffusers/push_to_hub
@@ -52,6 +54,8 @@
     title: Batch inference
   - local: training/distributed_inference
     title: Distributed inference
+  - local: hybrid_inference/overview
+    title: Remote inference
   title: Inference
 - isExpanded: false
   sections:
@@ -86,17 +90,6 @@
       title: FreeU
     title: Community optimizations
   title: Inference optimization
-- isExpanded: false
-  sections:
-  - 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
 - isExpanded: false
   sections:
   - local: modular_diffusers/overview
@@ -119,6 +112,8 @@
     title: ComponentsManager
   - local: modular_diffusers/guiders
     title: Guiders
+  - local: modular_diffusers/custom_blocks
+    title: Building Custom Blocks
   title: Modular Diffusers
 - isExpanded: false
   sections:
@@ -266,6 +261,8 @@
       title: Outputs
     - local: api/quantization
       title: Quantization
+    - local: hybrid_inference/api_reference
+      title: Remote inference
     - local: api/parallel
       title: Parallel inference
     title: Main Classes
@@ -323,10 +320,14 @@
         title: AllegroTransformer3DModel
       - local: api/models/aura_flow_transformer2d
         title: AuraFlowTransformer2DModel
+      - local: api/models/transformer_bria_fibo
+        title: BriaFiboTransformer2DModel
       - local: api/models/bria_transformer
         title: BriaTransformer2DModel
       - local: api/models/chroma_transformer
         title: ChromaTransformer2DModel
+      - local: api/models/chronoedit_transformer_3d
+        title: ChronoEditTransformer3DModel
       - local: api/models/cogvideox_transformer3d
         title: CogVideoXTransformer3DModel
       - local: api/models/cogview3plus_transformer2d
@@ -341,16 +342,26 @@
         title: DiTTransformer2DModel
       - local: api/models/easyanimate_transformer3d
         title: EasyAnimateTransformer3DModel
+      - local: api/models/flux2_transformer
+        title: Flux2Transformer2DModel
       - 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/hunyuanimage_transformer_2d
+        title: HunyuanImageTransformer2DModel
+      - local: api/models/hunyuan_video15_transformer_3d
+        title: HunyuanVideo15Transformer3DModel
       - local: api/models/hunyuan_video_transformer_3d
         title: HunyuanVideoTransformer3DModel
       - local: api/models/latte_transformer3d
         title: LatteTransformer3DModel
+      - local: api/models/longcat_image_transformer2d
+        title: LongCatImageTransformer2DModel
+      - local: api/models/ltx2_video_transformer3d
+        title: LTX2VideoTransformer3DModel
       - local: api/models/ltx_video_transformer3d
         title: LTXVideoTransformer3DModel
       - local: api/models/lumina2_transformer2d
@@ -361,6 +372,8 @@
         title: MochiTransformer3DModel
       - local: api/models/omnigen_transformer
         title: OmniGenTransformer2DModel
+      - local: api/models/ovisimage_transformer2d
+        title: OvisImageTransformer2DModel
       - local: api/models/pixart_transformer2d
         title: PixArtTransformer2DModel
       - local: api/models/prior_transformer
@@ -369,6 +382,8 @@
         title: QwenImageTransformer2DModel
       - local: api/models/sana_transformer2d
         title: SanaTransformer2DModel
+      - local: api/models/sana_video_transformer3d
+        title: SanaVideoTransformer3DModel
       - local: api/models/sd3_transformer2d
         title: SD3Transformer2DModel
       - local: api/models/skyreels_v2_transformer_3d
@@ -379,8 +394,12 @@
         title: Transformer2DModel
       - local: api/models/transformer_temporal
         title: TransformerTemporalModel
+      - local: api/models/wan_animate_transformer_3d
+        title: WanAnimateTransformer3DModel
       - local: api/models/wan_transformer_3d
         title: WanTransformer3DModel
+      - local: api/models/z_image_transformer2d
+        title: ZImageTransformer2DModel
       title: Transformers
     - sections:
       - local: api/models/stable_cascade_unet
@@ -411,8 +430,18 @@
         title: AutoencoderKLCogVideoX
       - local: api/models/autoencoderkl_cosmos
         title: AutoencoderKLCosmos
+      - local: api/models/autoencoder_kl_hunyuanimage
+        title: AutoencoderKLHunyuanImage
+      - local: api/models/autoencoder_kl_hunyuanimage_refiner
+        title: AutoencoderKLHunyuanImageRefiner
       - local: api/models/autoencoder_kl_hunyuan_video
         title: AutoencoderKLHunyuanVideo
+      - local: api/models/autoencoder_kl_hunyuan_video15
+        title: AutoencoderKLHunyuanVideo15
+      - local: api/models/autoencoderkl_audio_ltx_2
+        title: AutoencoderKLLTX2Audio
+      - local: api/models/autoencoderkl_ltx_2
+        title: AutoencoderKLLTX2Video
       - local: api/models/autoencoderkl_ltx_video
         title: AutoencoderKLLTXVideo
       - local: api/models/autoencoderkl_magvit
@@ -436,6 +465,8 @@
   - sections:
     - local: api/pipelines/overview
       title: Overview
+    - local: api/pipelines/auto_pipeline
+      title: AutoPipeline
     - sections:
       - local: api/pipelines/audioldm
         title: AudioLDM
@@ -448,8 +479,6 @@
       - local: api/pipelines/stable_audio
         title: Stable Audio
       title: Audio
-    - local: api/pipelines/auto_pipeline
-      title: AutoPipeline
     - sections:
       - local: api/pipelines/amused
         title: aMUSEd
@@ -463,6 +492,8 @@
         title: BLIP-Diffusion
       - local: api/pipelines/bria_3_2
         title: Bria 3.2
+      - local: api/pipelines/bria_fibo
+        title: Bria Fibo
       - local: api/pipelines/chroma
         title: Chroma
       - local: api/pipelines/cogview3
@@ -505,12 +536,16 @@
         title: EasyAnimate
       - local: api/pipelines/flux
         title: Flux
+      - local: api/pipelines/flux2
+        title: Flux2
       - local: api/pipelines/control_flux_inpaint
         title: FluxControlInpaint
       - local: api/pipelines/hidream
         title: HiDream-I1
       - local: api/pipelines/hunyuandit
         title: Hunyuan-DiT
+      - local: api/pipelines/hunyuanimage21
+        title: HunyuanImage2.1
       - local: api/pipelines/pix2pix
         title: InstructPix2Pix
       - local: api/pipelines/kandinsky
@@ -519,6 +554,8 @@
         title: Kandinsky 2.2
       - local: api/pipelines/kandinsky3
         title: Kandinsky 3
+      - local: api/pipelines/kandinsky5_image
+        title: Kandinsky 5.0 Image
       - local: api/pipelines/kolors
         title: Kolors
       - local: api/pipelines/latent_consistency_models
@@ -527,6 +564,8 @@
         title: Latent Diffusion
       - local: api/pipelines/ledits_pp
         title: LEDITS++
+      - local: api/pipelines/longcat_image
+        title: LongCat-Image
       - local: api/pipelines/lumina2
         title: Lumina 2.0
       - local: api/pipelines/lumina
@@ -537,6 +576,8 @@
         title: MultiDiffusion
       - local: api/pipelines/omnigen
         title: OmniGen
+      - local: api/pipelines/ovis_image
+        title: Ovis-Image
       - local: api/pipelines/pag
         title: PAG
       - local: api/pipelines/paint_by_example
@@ -545,12 +586,16 @@
         title: PixArt-α
       - local: api/pipelines/pixart_sigma
         title: PixArt-Σ
+      - local: api/pipelines/prx
+        title: PRX
       - local: api/pipelines/qwenimage
         title: QwenImage
       - local: api/pipelines/sana
         title: Sana
       - local: api/pipelines/sana_sprint
         title: Sana Sprint
+      - local: api/pipelines/sana_video
+        title: Sana Video
       - local: api/pipelines/self_attention_guidance
         title: Self-Attention Guidance
       - local: api/pipelines/semantic_stable_diffusion
@@ -608,10 +653,14 @@
         title: VisualCloze
       - local: api/pipelines/wuerstchen
         title: Wuerstchen
+      - local: api/pipelines/z_image
+        title: Z-Image
       title: Image
     - sections:
       - local: api/pipelines/allegro
         title: Allegro
+      - local: api/pipelines/chronoedit
+        title: ChronoEdit
       - local: api/pipelines/cogvideox
         title: CogVideoX
       - local: api/pipelines/consisid
@@ -620,10 +669,16 @@
         title: Framepack
       - local: api/pipelines/hunyuan_video
         title: HunyuanVideo
+      - local: api/pipelines/hunyuan_video15
+        title: HunyuanVideo1.5
       - local: api/pipelines/i2vgenxl
         title: I2VGen-XL
+      - local: api/pipelines/kandinsky5_video
+        title: Kandinsky 5.0 Video
       - local: api/pipelines/latte
         title: Latte
+      - local: api/pipelines/ltx2
+        title: LTX-2
       - local: api/pipelines/ltx_video
         title: LTXVideo
       - local: api/pipelines/mochi

docs/source/en/api/cache.md

@@ -34,3 +34,9 @@ Cache methods speedup diffusion transformers by storing and reusing intermediate
 [[autodoc]] FirstBlockCacheConfig
 
 [[autodoc]] apply_first_block_cache
+
+### TaylorSeerCacheConfig
+
+[[autodoc]] TaylorSeerCacheConfig
+
+[[autodoc]] apply_taylorseer_cache

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

@@ -30,7 +30,10 @@ LoRA is a fast and lightweight training method that inserts and trains a signifi
 - [`CogView4LoraLoaderMixin`] provides similar functions for [CogView4](https://huggingface.co/docs/diffusers/main/en/api/pipelines/cogview4).
 - [`AmusedLoraLoaderMixin`] is for the [`AmusedPipeline`].
 - [`HiDreamImageLoraLoaderMixin`] provides similar functions for [HiDream Image](https://huggingface.co/docs/diffusers/main/en/api/pipelines/hidream)
-- [`QwenImageLoraLoaderMixin`] provides similar functions for [Qwen Image](https://huggingface.co/docs/diffusers/main/en/api/pipelines/qwen)
+- [`QwenImageLoraLoaderMixin`] provides similar functions for [Qwen Image](https://huggingface.co/docs/diffusers/main/en/api/pipelines/qwen).
+- [`ZImageLoraLoaderMixin`] provides similar functions for [Z-Image](https://huggingface.co/docs/diffusers/main/en/api/pipelines/zimage).
+- [`Flux2LoraLoaderMixin`] provides similar functions for [Flux2](https://huggingface.co/docs/diffusers/main/en/api/pipelines/flux2).
+- [`LTX2LoraLoaderMixin`] provides similar functions for [Flux2](https://huggingface.co/docs/diffusers/main/en/api/pipelines/ltx2).
 - [`LoraBaseMixin`] provides a base class with several utility methods to fuse, unfuse, unload, LoRAs and more.
 
 > [!TIP]
@@ -56,6 +59,14 @@ LoRA is a fast and lightweight training method that inserts and trains a signifi
 
 [[autodoc]] loaders.lora_pipeline.FluxLoraLoaderMixin
 
+## Flux2LoraLoaderMixin
+
+[[autodoc]] loaders.lora_pipeline.Flux2LoraLoaderMixin
+
+## LTX2LoraLoaderMixin
+
+[[autodoc]] loaders.lora_pipeline.LTX2LoraLoaderMixin
+
 ## CogVideoXLoraLoaderMixin
 
 [[autodoc]] loaders.lora_pipeline.CogVideoXLoraLoaderMixin
@@ -107,6 +118,10 @@ LoRA is a fast and lightweight training method that inserts and trains a signifi
 
 [[autodoc]] loaders.lora_pipeline.QwenImageLoraLoaderMixin
 
+## ZImageLoraLoaderMixin
+
+[[autodoc]] loaders.lora_pipeline.ZImageLoraLoaderMixin
+
 ## KandinskyLoraLoaderMixin
 [[autodoc]] loaders.lora_pipeline.KandinskyLoraLoaderMixin
 

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

@@ -12,15 +12,7 @@ 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`] automatically retrieves the correct model class from the checkpoint `config.json` file.
 
 ## AutoModel
 

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

@@ -0,0 +1,36 @@
+<!-- Copyright 2025 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License. -->
+
+# AutoencoderKLHunyuanVideo15
+
+The 3D variational autoencoder (VAE) model with KL loss used in [HunyuanVideo1.5](https://github.com/Tencent/HunyuanVideo1-1.5) by Tencent.
+
+The model can be loaded with the following code snippet.
+
+```python
+from diffusers import AutoencoderKLHunyuanVideo15
+
+vae = AutoencoderKLHunyuanVideo15.from_pretrained("hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-480p_t2v", subfolder="vae", torch_dtype=torch.float32)
+
+# make sure to enable tiling to avoid OOM
+vae.enable_tiling()
+```
+
+## AutoencoderKLHunyuanVideo15
+
+[[autodoc]] AutoencoderKLHunyuanVideo15
+  - decode
+  - encode
+  - all
+
+## DecoderOutput
+
+[[autodoc]] models.autoencoders.vae.DecoderOutput

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

@@ -0,0 +1,32 @@
+<!-- Copyright 2025 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License. -->
+
+# AutoencoderKLHunyuanImage
+
+The 2D variational autoencoder (VAE) model with KL loss used in [HunyuanImage2.1].
+
+The model can be loaded with the following code snippet.
+
+```python
+from diffusers import AutoencoderKLHunyuanImage
+
+vae = AutoencoderKLHunyuanImage.from_pretrained("hunyuanvideo-community/HunyuanImage-2.1-Diffusers", subfolder="vae", torch_dtype=torch.bfloat16)
+```
+
+## AutoencoderKLHunyuanImage
+
+[[autodoc]] AutoencoderKLHunyuanImage
+  - decode
+  - all
+
+## DecoderOutput
+
+[[autodoc]] models.autoencoders.vae.DecoderOutput

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

@@ -0,0 +1,32 @@
+<!-- Copyright 2025 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License. -->
+
+# AutoencoderKLHunyuanImageRefiner
+
+The 3D variational autoencoder (VAE) model with KL loss used in [HunyuanImage2.1](https://github.com/Tencent-Hunyuan/HunyuanImage-2.1) for its refiner pipeline.
+
+The model can be loaded with the following code snippet.
+
+```python
+from diffusers import AutoencoderKLHunyuanImageRefiner
+
+vae = AutoencoderKLHunyuanImageRefiner.from_pretrained("hunyuanvideo-community/HunyuanImage-2.1-Refiner-Diffusers", subfolder="vae", torch_dtype=torch.bfloat16)
+```
+
+## AutoencoderKLHunyuanImageRefiner
+
+[[autodoc]] AutoencoderKLHunyuanImageRefiner
+  - decode
+  - all
+
+## DecoderOutput
+
+[[autodoc]] models.autoencoders.vae.DecoderOutput

docs/source/en/api/models/autoencoderkl_audio_ltx_2.md

@@ -0,0 +1,29 @@
+<!-- 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. -->
+
+# AutoencoderKLLTX2Audio
+
+The 3D variational autoencoder (VAE) model with KL loss used in [LTX-2](https://huggingface.co/Lightricks/LTX-2) was introduced by Lightricks. This is for encoding and decoding audio latent representations.
+
+The model can be loaded with the following code snippet.
+
+```python
+from diffusers import AutoencoderKLLTX2Audio
+
+vae = AutoencoderKLLTX2Audio.from_pretrained("Lightricks/LTX-2", subfolder="vae", torch_dtype=torch.float32).to("cuda")
+```
+
+## AutoencoderKLLTX2Audio
+
+[[autodoc]] AutoencoderKLLTX2Audio
+    - encode
+    - decode
+    - all

docs/source/en/api/models/autoencoderkl_ltx_2.md

@@ -0,0 +1,29 @@
+<!-- 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. -->
+
+# AutoencoderKLLTX2Video
+
+The 3D variational autoencoder (VAE) model with KL loss used in [LTX-2](https://huggingface.co/Lightricks/LTX-2) was introduced by Lightricks.
+
+The model can be loaded with the following code snippet.
+
+```python
+from diffusers import AutoencoderKLLTX2Video
+
+vae = AutoencoderKLLTX2Video.from_pretrained("Lightricks/LTX-2", subfolder="vae", torch_dtype=torch.float32).to("cuda")
+```
+
+## AutoencoderKLLTX2Video
+
+[[autodoc]] AutoencoderKLLTX2Video
+    - decode
+    - encode
+    - all

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

@@ -12,7 +12,7 @@ specific language governing permissions and limitations under the License.
 
 # ChromaTransformer2DModel
 
-A modified flux Transformer model from [Chroma](https://huggingface.co/lodestones/Chroma)
+A modified flux Transformer model from [Chroma](https://huggingface.co/lodestones/Chroma1-HD)
 
 ## ChromaTransformer2DModel
 

docs/source/en/api/models/chronoedit_transformer_3d.md

@@ -0,0 +1,32 @@
+<!-- Copyright 2025 The ChronoEdit Team and 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. -->
+
+# ChronoEditTransformer3DModel
+
+A Diffusion Transformer model for 3D video-like data from [ChronoEdit: Towards Temporal Reasoning for Image Editing and World Simulation](https://huggingface.co/papers/2510.04290) from NVIDIA and University of Toronto, by Jay Zhangjie Wu, Xuanchi Ren, Tianchang Shen, Tianshi Cao, Kai He, Yifan Lu, Ruiyuan Gao, Enze Xie, Shiyi Lan, Jose M. Alvarez, Jun Gao, Sanja Fidler, Zian Wang, Huan Ling.
+
+> **TL;DR:** ChronoEdit reframes image editing as a video generation task, using input and edited images as start/end frames to leverage pretrained video models with temporal consistency. A temporal reasoning stage introduces reasoning tokens to ensure physically plausible edits and visualize the editing trajectory.
+
+The model can be loaded with the following code snippet.
+
+```python
+from diffusers import ChronoEditTransformer3DModel
+
+transformer = ChronoEditTransformer3DModel.from_pretrained("nvidia/ChronoEdit-14B-Diffusers", subfolder="transformer", torch_dtype=torch.bfloat16)
+```
+
+## ChronoEditTransformer3DModel
+
+[[autodoc]] ChronoEditTransformer3DModel
+
+## Transformer2DModelOutput
+
+[[autodoc]] models.modeling_outputs.Transformer2DModelOutput

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

@@ -33,6 +33,21 @@ url = "https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5/blob/m
 pipe = StableDiffusionControlNetPipeline.from_single_file(url, controlnet=controlnet)
 ```
 
+## Loading from Control LoRA
+
+Control-LoRA is introduced by Stability AI in [stabilityai/control-lora](https://huggingface.co/stabilityai/control-lora) by adding low-rank parameter efficient fine tuning to ControlNet. This approach offers a more efficient and compact method to bring model control to a wider variety of consumer GPUs.
+
+```py
+from diffusers import ControlNetModel, UNet2DConditionModel
+
+lora_id = "stabilityai/control-lora"
+lora_filename = "control-LoRAs-rank128/control-lora-canny-rank128.safetensors"
+
+unet = UNet2DConditionModel.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", subfolder="unet", torch_dtype=torch.bfloat16).to("cuda")
+controlnet = ControlNetModel.from_unet(unet).to(device="cuda", dtype=torch.bfloat16)
+controlnet.load_lora_adapter(lora_id, weight_name=lora_filename, prefix=None, controlnet_config=controlnet.config)
+```
+
 ## ControlNetModel
 
 [[autodoc]] ControlNetModel

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

@@ -42,4 +42,4 @@ pipe = FluxControlNetPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", co
 
 ## FluxControlNetOutput
 
-[[autodoc]] models.controlnet_flux.FluxControlNetOutput
+[[autodoc]] models.controlnets.controlnet_flux.FluxControlNetOutput

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

@@ -43,4 +43,4 @@ controlnet = SparseControlNetModel.from_pretrained("guoyww/animatediff-sparsectr
 
 ## SparseControlNetOutput
 
-[[autodoc]] models.controlnet_sparsectrl.SparseControlNetOutput
+[[autodoc]] models.controlnets.controlnet_sparsectrl.SparseControlNetOutput

docs/source/en/api/models/flux2_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.
+-->
+
+# Flux2Transformer2DModel
+
+A Transformer model for image-like data from [Flux2](https://hf.co/black-forest-labs/FLUX.2-dev).
+
+## Flux2Transformer2DModel
+
+[[autodoc]] Flux2Transformer2DModel

docs/source/en/api/models/hunyuan_video15_transformer_3d.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. -->
+
+# HunyuanVideo15Transformer3DModel
+
+A Diffusion Transformer model for 3D video-like data used in [HunyuanVideo1.5](https://github.com/Tencent/HunyuanVideo1-1.5).
+
+The model can be loaded with the following code snippet.
+
+```python
+from diffusers import HunyuanVideo15Transformer3DModel
+
+transformer = HunyuanVideo15Transformer3DModel.from_pretrained("hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-480p_t2v" subfolder="transformer", torch_dtype=torch.bfloat16)
+```
+
+## HunyuanVideo15Transformer3DModel
+
+[[autodoc]] HunyuanVideo15Transformer3DModel
+
+## Transformer2DModelOutput
+
+[[autodoc]] models.modeling_outputs.Transformer2DModelOutput

docs/source/en/api/models/hunyuanimage_transformer_2d.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. -->
+
+# HunyuanImageTransformer2DModel
+
+A Diffusion Transformer model for [HunyuanImage2.1](https://github.com/Tencent-Hunyuan/HunyuanImage-2.1).
+
+The model can be loaded with the following code snippet.
+
+```python
+from diffusers import HunyuanImageTransformer2DModel
+
+transformer = HunyuanImageTransformer2DModel.from_pretrained("hunyuanvideo-community/HunyuanImage-2.1-Diffusers", subfolder="transformer", torch_dtype=torch.bfloat16)
+```
+
+## HunyuanImageTransformer2DModel
+
+[[autodoc]] HunyuanImageTransformer2DModel
+
+## Transformer2DModelOutput
+
+[[autodoc]] models.modeling_outputs.Transformer2DModelOutput

docs/source/en/api/models/longcat_image_transformer2d.md

@@ -0,0 +1,25 @@
+<!--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.
+-->
+
+# LongCatImageTransformer2DModel
+
+The model can be loaded with the following code snippet.
+
+```python
+from diffusers import LongCatImageTransformer2DModel
+
+transformer = LongCatImageTransformer2DModel.from_pretrained("meituan-longcat/LongCat-Image ", subfolder="transformer", torch_dtype=torch.bfloat16)
+```
+
+## LongCatImageTransformer2DModel
+
+[[autodoc]] LongCatImageTransformer2DModel

docs/source/en/api/models/ltx2_video_transformer3d.md

@@ -0,0 +1,26 @@
+<!-- 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. -->
+
+# LTX2VideoTransformer3DModel
+
+A Diffusion Transformer model for 3D data from [LTX](https://huggingface.co/Lightricks/LTX-2) was introduced by Lightricks.
+
+The model can be loaded with the following code snippet.
+
+```python
+from diffusers import LTX2VideoTransformer3DModel
+
+transformer = LTX2VideoTransformer3DModel.from_pretrained("Lightricks/LTX-2", subfolder="transformer", torch_dtype=torch.bfloat16).to("cuda")
+```
+
+## LTX2VideoTransformer3DModel
+
+[[autodoc]] LTX2VideoTransformer3DModel

docs/source/en/api/models/ovisimage_transformer2d.md

@@ -0,0 +1,24 @@
+<!-- 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. -->
+
+# OvisImageTransformer2DModel
+
+The model can be loaded with the following code snippet.
+
+```python
+from diffusers import OvisImageTransformer2DModel
+
+transformer = OvisImageTransformer2DModel.from_pretrained("AIDC-AI/Ovis-Image-7B", subfolder="transformer", torch_dtype=torch.bfloat16)
+```
+
+## OvisImageTransformer2DModel
+
+[[autodoc]] OvisImageTransformer2DModel

docs/source/en/api/models/sana_video_transformer3d.md

@@ -0,0 +1,36 @@
+<!-- Copyright 2025 The SANA-Video Authors and 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. -->
+
+# SanaVideoTransformer3DModel
+
+A Diffusion Transformer model for 3D data (video) from [SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer](https://huggingface.co/papers/2509.24695) from NVIDIA and MIT HAN Lab, by Junsong Chen, Yuyang Zhao, Jincheng Yu, Ruihang Chu, Junyu Chen, Shuai Yang, Xianbang Wang, Yicheng Pan, Daquan Zhou, Huan Ling, Haozhe Liu, Hongwei Yi, Hao Zhang, Muyang Li, Yukang Chen, Han Cai, Sanja Fidler, Ping Luo, Song Han, Enze Xie.
+
+The abstract from the paper is:
+
+*We introduce SANA-Video, a small diffusion model that can efficiently generate videos up to 720x1280 resolution and minute-length duration. SANA-Video synthesizes high-resolution, high-quality and long videos with strong text-video alignment at a remarkably fast speed, deployable on RTX 5090 GPU. Two core designs ensure our efficient, effective and long video generation: (1) Linear DiT: We leverage linear attention as the core operation, which is more efficient than vanilla attention given the large number of tokens processed in video generation. (2) Constant-Memory KV cache for Block Linear Attention: we design block-wise autoregressive approach for long video generation by employing a constant-memory state, derived from the cumulative properties of linear attention. This KV cache provides the Linear DiT with global context at a fixed memory cost, eliminating the need for a traditional KV cache and enabling efficient, minute-long video generation. In addition, we explore effective data filters and model training strategies, narrowing the training cost to 12 days on 64 H100 GPUs, which is only 1% of the cost of MovieGen. Given its low cost, SANA-Video achieves competitive performance compared to modern state-of-the-art small diffusion models (e.g., Wan 2.1-1.3B and SkyReel-V2-1.3B) while being 16x faster in measured latency. Moreover, SANA-Video can be deployed on RTX 5090 GPUs with NVFP4 precision, accelerating the inference speed of generating a 5-second 720p video from 71s to 29s (2.4x speedup). In summary, SANA-Video enables low-cost, high-quality video generation.*
+
+The model can be loaded with the following code snippet.
+
+```python
+from diffusers import SanaVideoTransformer3DModel
+import torch
+
+transformer = SanaVideoTransformer3DModel.from_pretrained("Efficient-Large-Model/SANA-Video_2B_480p_diffusers", subfolder="transformer", torch_dtype=torch.bfloat16)
+```
+
+## SanaVideoTransformer3DModel
+
+[[autodoc]] SanaVideoTransformer3DModel
+
+## Transformer2DModelOutput
+
+[[autodoc]] models.modeling_outputs.Transformer2DModelOutput
+

docs/source/en/api/models/transformer_bria_fibo.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.
+-->
+
+# BriaFiboTransformer2DModel
+
+A modified flux Transformer model from [Bria](https://huggingface.co/briaai/FIBO)
+
+## BriaFiboTransformer2DModel
+
+[[autodoc]] BriaFiboTransformer2DModel

docs/source/en/api/models/wan_animate_transformer_3d.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. -->
+
+# WanAnimateTransformer3DModel
+
+A Diffusion Transformer model for 3D video-like data was introduced in [Wan Animate](https://github.com/Wan-Video/Wan2.2) by the Alibaba Wan Team.
+
+The model can be loaded with the following code snippet.
+
+```python
+from diffusers import WanAnimateTransformer3DModel
+
+transformer = WanAnimateTransformer3DModel.from_pretrained("Wan-AI/Wan2.2-Animate-14B-Diffusers", subfolder="transformer", torch_dtype=torch.bfloat16)
+```
+
+## WanAnimateTransformer3DModel
+
+[[autodoc]] WanAnimateTransformer3DModel
+
+## Transformer2DModelOutput
+
+[[autodoc]] models.modeling_outputs.Transformer2DModelOutput

docs/source/en/api/models/z_image_transformer2d.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.
+-->
+
+# ZImageTransformer2DModel
+
+A Transformer model for image-like data from [Z-Image](https://huggingface.co/Tongyi-MAI/Z-Image-Turbo).
+
+## ZImageTransformer2DModel
+
+[[autodoc]] ZImageTransformer2DModel

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

@@ -0,0 +1,45 @@
+<!--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.
+-->
+
+# Bria Fibo
+
+Text-to-image models have mastered imagination - but not control. FIBO changes that.
+
+FIBO is trained on structured JSON captions up to 1,000+ words and designed to understand and control different visual parameters such as lighting, composition, color, and camera settings, enabling precise and reproducible outputs.
+
+With only 8 billion parameters, FIBO provides a new level of image quality, prompt adherence and proffesional control.
+
+FIBO is trained exclusively on a structured prompt and will not work with freeform text prompts.
+you can use the [FIBO-VLM-prompt-to-JSON](https://huggingface.co/briaai/FIBO-VLM-prompt-to-JSON) model or the [FIBO-gemini-prompt-to-JSON](https://huggingface.co/briaai/FIBO-gemini-prompt-to-JSON)  to convert your freeform text prompt to a structured JSON prompt.
+
+> [!NOTE]
+> Avoid using freeform text prompts directly with FIBO because it does not produce the best results.
+
+Refer to the Bria Fibo Hugging Face [page](https://huggingface.co/briaai/FIBO) to learn more.
+
+
+## Usage
+
+_As the model is gated, before using it with diffusers you first need to go to the [Bria Fibo Hugging Face page](https://huggingface.co/briaai/FIBO), fill in the form and accept the gate. Once you are in, you need to login so that your system knows you’ve accepted the gate._
+
+Use the command below to log in:
+
+```bash
+hf auth login
+```
+
+
+## BriaFiboPipeline
+
+[[autodoc]] BriaFiboPipeline
+	- all
+	- __call__

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

@@ -19,20 +19,21 @@ specific language governing permissions and limitations under the License.
 
 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).
+Original model checkpoints for Chroma can be found here:
+* High-resolution finetune: [lodestones/Chroma1-HD](https://huggingface.co/lodestones/Chroma1-HD)
+* Base model: [lodestones/Chroma1-Base](https://huggingface.co/lodestones/Chroma1-Base)
+* Original repo with progress checkpoints: [lodestones/Chroma](https://huggingface.co/lodestones/Chroma) (loading this repo with `from_pretrained` will load a Diffusers-compatible version of the `unlocked-v37` checkpoint)
 
 > [!TIP]
 > Chroma can use all the same optimizations as Flux.
 
 ## Inference
 
-The Diffusers version of Chroma is based on the [`unlocked-v37`](https://huggingface.co/lodestones/Chroma/blob/main/chroma-unlocked-v37.safetensors) version of the original model, which is available in the [Chroma repository](https://huggingface.co/lodestones/Chroma).
-
 ```python
 import torch
 from diffusers import ChromaPipeline
 
-pipe = ChromaPipeline.from_pretrained("lodestones/Chroma", torch_dtype=torch.bfloat16)
+pipe = ChromaPipeline.from_pretrained("lodestones/Chroma1-HD", torch_dtype=torch.bfloat16)
 pipe.enable_model_cpu_offload()
 
 prompt = [
@@ -63,10 +64,10 @@ Then run the following example
 import torch
 from diffusers import ChromaTransformer2DModel, ChromaPipeline
 
-model_id = "lodestones/Chroma"
+model_id = "lodestones/Chroma1-HD"
 dtype = torch.bfloat16
 
-transformer = ChromaTransformer2DModel.from_single_file("https://huggingface.co/lodestones/Chroma/blob/main/chroma-unlocked-v37.safetensors", torch_dtype=dtype)
+transformer = ChromaTransformer2DModel.from_single_file("https://huggingface.co/lodestones/Chroma1-HD/blob/main/Chroma1-HD.safetensors", torch_dtype=dtype)
 
 pipe = ChromaPipeline.from_pretrained(model_id, transformer=transformer, torch_dtype=dtype)
 pipe.enable_model_cpu_offload()

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

@@ -0,0 +1,211 @@
+<!-- Copyright 2025 The ChronoEdit Team and 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>
+
+# ChronoEdit
+
+[ChronoEdit: Towards Temporal Reasoning for Image Editing and World Simulation](https://huggingface.co/papers/2510.04290) from NVIDIA and University of Toronto, by Jay Zhangjie Wu, Xuanchi Ren, Tianchang Shen, Tianshi Cao, Kai He, Yifan Lu, Ruiyuan Gao, Enze Xie, Shiyi Lan, Jose M. Alvarez, Jun Gao, Sanja Fidler, Zian Wang, Huan Ling.
+
+> **TL;DR:** ChronoEdit reframes image editing as a video generation task, using input and edited images as start/end frames to leverage pretrained video models with temporal consistency. A temporal reasoning stage introduces reasoning tokens to ensure physically plausible edits and visualize the editing trajectory.
+
+*Recent advances in large generative models have greatly enhanced both image editing and in-context image generation, yet a critical gap remains in ensuring physical consistency, where edited objects must remain coherent. This capability is especially vital for world simulation related tasks. In this paper, we present ChronoEdit, a framework that reframes image editing as a video generation problem. First, ChronoEdit treats the input and edited images as the first and last frames of a video, allowing it to leverage large pretrained video generative models that capture not only object appearance but also the implicit physics of motion and interaction through learned temporal consistency. Second, ChronoEdit introduces a temporal reasoning stage that explicitly performs editing at inference time. Under this setting, target frame is jointly denoised with reasoning tokens to imagine a plausible editing trajectory that constrains the solution space to physically viable transformations. The reasoning tokens are then dropped after a few steps to avoid the high computational cost of rendering a full video. To validate ChronoEdit, we introduce PBench-Edit, a new benchmark of image-prompt pairs for contexts that require physical consistency, and demonstrate that ChronoEdit surpasses state-of-the-art baselines in both visual fidelity and physical plausibility. Project page for code and models: [this https URL](https://research.nvidia.com/labs/toronto-ai/chronoedit).*
+
+The ChronoEdit pipeline is developed by the ChronoEdit Team. The original code is available on [GitHub](https://github.com/nv-tlabs/ChronoEdit), and pretrained models can be found in the [nvidia/ChronoEdit](https://huggingface.co/collections/nvidia/chronoedit) collection on Hugging Face.
+
+Available Models/LoRAs:
+- [nvidia/ChronoEdit-14B-Diffusers](https://huggingface.co/nvidia/ChronoEdit-14B-Diffusers)
+- [nvidia/ChronoEdit-14B-Diffusers-Upscaler-Lora](https://huggingface.co/nvidia/ChronoEdit-14B-Diffusers-Upscaler-Lora)
+- [nvidia/ChronoEdit-14B-Diffusers-Paint-Brush-Lora](https://huggingface.co/nvidia/ChronoEdit-14B-Diffusers-Paint-Brush-Lora)
+
+### Image Editing
+
+```py
+import torch
+import numpy as np
+from diffusers import AutoencoderKLWan, ChronoEditTransformer3DModel, ChronoEditPipeline
+from diffusers.utils import export_to_video, load_image
+from transformers import CLIPVisionModel
+from PIL import Image
+
+model_id = "nvidia/ChronoEdit-14B-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)
+transformer = ChronoEditTransformer3DModel.from_pretrained(model_id, subfolder="transformer", torch_dtype=torch.bfloat16)
+pipe = ChronoEditPipeline.from_pretrained(model_id, image_encoder=image_encoder, transformer=transformer, vae=vae, torch_dtype=torch.bfloat16)
+pipe.to("cuda")
+
+image = load_image(
+    "https://huggingface.co/spaces/nvidia/ChronoEdit/resolve/main/examples/3.png"
+)
+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
+print("width", width, "height", height)
+image = image.resize((width, height))
+prompt = (
+    "The user wants to transform the image by adding a small, cute mouse sitting inside the floral teacup, enjoying a spa bath. The mouse should appear relaxed and cheerful, with a tiny white bath towel draped over its head like a turban. It should be positioned comfortably in the cup’s liquid, with gentle steam rising around it to blend with the cozy atmosphere. "
+    "The mouse’s pose should be natural—perhaps sitting upright with paws resting lightly on the rim or submerged in the tea. The teacup’s floral design, gold trim, and warm lighting must remain unchanged to preserve the original aesthetic. The steam should softly swirl around the mouse, enhancing the spa-like, whimsical mood."
+)
+
+output = pipe(
+    image=image,
+    prompt=prompt,
+    height=height,
+    width=width,
+    num_frames=5,
+    num_inference_steps=50,
+    guidance_scale=5.0,
+    enable_temporal_reasoning=False,
+    num_temporal_reasoning_steps=0,
+).frames[0]
+Image.fromarray((output[-1] * 255).clip(0, 255).astype("uint8")).save("output.png")
+```
+
+Optionally, enable **temporal reasoning** for improved physical consistency:
+```py
+output = pipe(
+    image=image,
+    prompt=prompt,
+    height=height,
+    width=width,
+    num_frames=29,
+    num_inference_steps=50,
+    guidance_scale=5.0,
+    enable_temporal_reasoning=True,
+    num_temporal_reasoning_steps=50,
+).frames[0]
+export_to_video(output, "output.mp4", fps=16)
+Image.fromarray((output[-1] * 255).clip(0, 255).astype("uint8")).save("output.png")
+```
+
+### Inference with 8-Step Distillation Lora
+
+```py
+import torch
+import numpy as np
+from diffusers import AutoencoderKLWan, ChronoEditTransformer3DModel, ChronoEditPipeline
+from diffusers.schedulers import UniPCMultistepScheduler
+from diffusers.utils import export_to_video, load_image
+from transformers import CLIPVisionModel
+from PIL import Image
+
+model_id = "nvidia/ChronoEdit-14B-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)
+transformer = ChronoEditTransformer3DModel.from_pretrained(model_id, subfolder="transformer", torch_dtype=torch.bfloat16)
+pipe = ChronoEditPipeline.from_pretrained(model_id, image_encoder=image_encoder, transformer=transformer, vae=vae, torch_dtype=torch.bfloat16)
+pipe.load_lora_weights("nvidia/ChronoEdit-14B-Diffusers", weight_name="lora/chronoedit_distill_lora.safetensors", adapter_name="distill")
+pipe.fuse_lora(adapter_names=["distill"], lora_scale=1.0)
+pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config, flow_shift=2.0)
+pipe.to("cuda")
+
+image = load_image(
+    "https://huggingface.co/spaces/nvidia/ChronoEdit/resolve/main/examples/3.png"
+)
+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
+print("width", width, "height", height)
+image = image.resize((width, height))
+prompt = (
+    "The user wants to transform the image by adding a small, cute mouse sitting inside the floral teacup, enjoying a spa bath. The mouse should appear relaxed and cheerful, with a tiny white bath towel draped over its head like a turban. It should be positioned comfortably in the cup’s liquid, with gentle steam rising around it to blend with the cozy atmosphere. "
+    "The mouse’s pose should be natural—perhaps sitting upright with paws resting lightly on the rim or submerged in the tea. The teacup’s floral design, gold trim, and warm lighting must remain unchanged to preserve the original aesthetic. The steam should softly swirl around the mouse, enhancing the spa-like, whimsical mood."
+)
+
+output = pipe(
+    image=image,
+    prompt=prompt,
+    height=height,
+    width=width,
+    num_frames=5,
+    num_inference_steps=8,
+    guidance_scale=1.0,
+    enable_temporal_reasoning=False,
+    num_temporal_reasoning_steps=0,
+).frames[0]
+export_to_video(output, "output.mp4", fps=16)
+Image.fromarray((output[-1] * 255).clip(0, 255).astype("uint8")).save("output.png")
+```
+
+### Inference with Multiple LoRAs
+
+```py
+import torch
+import numpy as np
+from diffusers import AutoencoderKLWan, ChronoEditTransformer3DModel, ChronoEditPipeline
+from diffusers.schedulers import UniPCMultistepScheduler
+from diffusers.utils import export_to_video, load_image
+from transformers import CLIPVisionModel
+from PIL import Image
+
+model_id = "nvidia/ChronoEdit-14B-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)
+transformer = ChronoEditTransformer3DModel.from_pretrained(model_id, subfolder="transformer", torch_dtype=torch.bfloat16)
+pipe = ChronoEditPipeline.from_pretrained(model_id, image_encoder=image_encoder, transformer=transformer, vae=vae, torch_dtype=torch.bfloat16)
+pipe.load_lora_weights("nvidia/ChronoEdit-14B-Diffusers-Paint-Brush-Lora", weight_name="paintbrush_lora_diffusers.safetensors", adapter_name="paintbrush")
+pipe.load_lora_weights("nvidia/ChronoEdit-14B-Diffusers", weight_name="lora/chronoedit_distill_lora.safetensors", adapter_name="distill")
+pipe.fuse_lora(adapter_names=["paintbrush", "distill"], lora_scale=1.0)
+pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config, flow_shift=2.0)
+pipe.to("cuda")
+
+image = load_image(
+    "https://raw.githubusercontent.com/nv-tlabs/ChronoEdit/refs/heads/main/assets/images/input_paintbrush.png"
+)
+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
+print("width", width, "height", height)
+image = image.resize((width, height))
+prompt = (
+    "Turn the pencil sketch in the image into an actual object that is consistent with the image’s content. The user wants to change the sketch to a crown and a hat."
+)
+
+output = pipe(
+    image=image,
+    prompt=prompt,
+    height=height,
+    width=width,
+    num_frames=5,
+    num_inference_steps=8,
+    guidance_scale=1.0,
+    enable_temporal_reasoning=False,
+    num_temporal_reasoning_steps=0,
+).frames[0]
+export_to_video(output, "output.mp4", fps=16)
+Image.fromarray((output[-1] * 255).clip(0, 255).astype("uint8")).save("output_1.png")
+```
+
+## ChronoEditPipeline
+
+[[autodoc]] ChronoEditPipeline
+  - all
+  - __call__
+
+## ChronoEditPipelineOutput
+
+[[autodoc]] pipelines.chronoedit.pipeline_output.ChronoEditPipelineOutput

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

@@ -70,6 +70,12 @@ output.save("output.png")
   - all
   - __call__
 
+## Cosmos2_5_PredictBasePipeline
+
+[[autodoc]] Cosmos2_5_PredictBasePipeline
+  - all
+  - __call__
+
 ## CosmosPipelineOutput
 
 [[autodoc]] pipelines.cosmos.pipeline_output.CosmosPipelineOutput

docs/source/en/api/pipelines/flux2.md

@@ -0,0 +1,39 @@
+<!--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.
+-->
+
+# Flux2
+
+<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.2 is the recent series of image generation models from Black Forest Labs, preceded by the [Flux.1](./flux.md) series. It is an entirely new model with a new architecture and pre-training done from scratch!
+
+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/flux2).
+
+> [!TIP]
+> Flux2 can be quite expensive to run on consumer hardware devices. However, you can perform a suite of optimizations to run it faster and in a more memory-friendly manner. Check out [this section](https://huggingface.co/blog/sd3#memory-optimizations-for-sd3) for more details. Additionally, Flux can benefit from quantization for memory efficiency with a trade-off in inference latency. Refer to [this blog post](https://huggingface.co/blog/quanto-diffusers) to learn more.
+>
+> [Caching](../../optimization/cache) may also speed up inference by storing and reusing intermediate outputs.
+
+## Caption upsampling
+
+Flux.2 can potentially generate better better outputs with better prompts. We can "upsample"
+an input prompt by setting the `caption_upsample_temperature` argument in the pipeline call arguments.
+The [official implementation](https://github.com/black-forest-labs/flux2/blob/5a5d316b1b42f6b59a8c9194b77c8256be848432/src/flux2/text_encoder.py#L140) recommends this value to be 0.15.
+
+## Flux2Pipeline
+
+[[autodoc]] Flux2Pipeline
+	- all
+	- __call__

docs/source/en/api/pipelines/hunyuan_video15.md

@@ -0,0 +1,120 @@
+<!-- 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. -->
+
+
+# HunyuanVideo-1.5
+
+HunyuanVideo-1.5 is a lightweight yet powerful video generation model that achieves state-of-the-art visual quality and motion coherence with only 8.3 billion parameters, enabling efficient inference on consumer-grade GPUs. This achievement is built upon several key components, including meticulous data curation, an advanced DiT architecture with selective and sliding tile attention (SSTA), enhanced bilingual understanding through glyph-aware text encoding, progressive pre-training and post-training, and an efficient video super-resolution network. Leveraging these designs, we developed a unified framework capable of high-quality text-to-video and image-to-video generation across multiple durations and resolutions. Extensive experiments demonstrate that this compact and proficient model establishes a new state-of-the-art among open-source models.
+
+You can find all the original HunyuanVideo checkpoints under the [Tencent](https://huggingface.co/tencent) organization.
+
+> [!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.
+
+The example below demonstrates how to generate a video optimized for memory or inference speed.
+
+<hfoptions id="usage">
+<hfoption id="memory">
+
+Refer to the [Reduce memory usage](../../optimization/memory) guide for more details about the various memory saving techniques.
+
+
+```py
+import torch
+from diffusers import AutoModel, HunyuanVideo15Pipeline
+from diffusers.utils import export_to_video
+
+
+pipeline = HunyuanVideo15Pipeline.from_pretrained(
+    "HunyuanVideo-1.5-Diffusers-480p_t2v",
+    torch_dtype=torch.bfloat16,
+)
+
+# 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, "output.mp4", fps=15)
+```
+
+## Notes
+
+- HunyuanVideo1.5 use attention masks with variable-length sequences. For best performance, we recommend using an attention backend that handles padding efficiently.
+
+    - **H100/H800:** `_flash_3_hub` or `_flash_3_varlen_hub`
+    - **A100/A800/RTX 4090:** `flash_hub` or `flash_varlen_hub`
+    - **Other GPUs:** `sage_hub`
+
+Refer to the [Attention backends](../../optimization/attention_backends) guide for more details about using a different backend.
+
+
+```py
+pipe.transformer.set_attention_backend("flash_hub")  # or your preferred backend
+```
+
+- [`HunyuanVideo15Pipeline`] use guider and does not take `guidance_scale` parameter at runtime. 
+
+You can check the default guider configuration using `pipe.guider`:
+
+```py
+>>> pipe.guider 
+ClassifierFreeGuidance {
+  "_class_name": "ClassifierFreeGuidance",
+  "_diffusers_version": "0.36.0.dev0",
+  "enabled": true,
+  "guidance_rescale": 0.0,
+  "guidance_scale": 6.0,
+  "start": 0.0,
+  "stop": 1.0,
+  "use_original_formulation": false
+}
+
+State:
+  step: None
+  num_inference_steps: None
+  timestep: None
+  count_prepared: 0
+  enabled: True
+  num_conditions: 2
+```
+
+To update guider configuration, you can run `pipe.guider = pipe.guider.new(...)`
+
+```py
+pipe.guider = pipe.guider.new(guidance_scale=5.0)
+```
+
+Read more on Guider [here](../../modular_diffusers/guiders).
+
+
+
+## HunyuanVideo15Pipeline
+
+[[autodoc]] HunyuanVideo15Pipeline
+  - all
+  - __call__
+
+## HunyuanVideo15ImageToVideoPipeline
+
+[[autodoc]] HunyuanVideo15ImageToVideoPipeline
+  - all
+  - __call__
+
+## HunyuanVideo15PipelineOutput
+
+[[autodoc]] pipelines.hunyuan_video1_5.pipeline_output.HunyuanVideo15PipelineOutput

docs/source/en/api/pipelines/hunyuanimage21.md

@@ -0,0 +1,152 @@
+<!-- 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. -->
+
+# HunyuanImage2.1
+
+
+HunyuanImage-2.1 is a 17B text-to-image model that is capable of generating 2K (2048 x 2048) resolution images
+
+HunyuanImage-2.1 comes in the following variants:
+
+| model type | model id |
+|:----------:|:--------:|
+| HunyuanImage-2.1 | [hunyuanvideo-community/HunyuanImage-2.1-Diffusers](https://huggingface.co/hunyuanvideo-community/HunyuanImage-2.1-Diffusers) |
+| HunyuanImage-2.1-Distilled | [hunyuanvideo-community/HunyuanImage-2.1-Distilled-Diffusers](https://huggingface.co/hunyuanvideo-community/HunyuanImage-2.1-Distilled-Diffusers) |
+| HunyuanImage-2.1-Refiner | [hunyuanvideo-community/HunyuanImage-2.1-Refiner-Diffusers](https://huggingface.co/hunyuanvideo-community/HunyuanImage-2.1-Refiner-Diffusers) |
+
+> [!TIP]
+> [Caching](../../optimization/cache) may also speed up inference by storing and reusing intermediate outputs.
+
+## HunyuanImage-2.1
+
+HunyuanImage-2.1 applies [Adaptive Projected Guidance (APG)](https://huggingface.co/papers/2410.02416) combined with Classifier-Free Guidance (CFG) in the denoising loop. `HunyuanImagePipeline` has a `guider` component (read more about [Guider](../modular_diffusers/guiders.md)) and does not take a `guidance_scale` parameter at runtime. To change guider-related parameters, e.g., `guidance_scale`, you can update the `guider` configuration instead.
+
+```python
+import torch
+from diffusers import HunyuanImagePipeline
+
+pipe = HunyuanImagePipeline.from_pretrained(
+    "hunyuanvideo-community/HunyuanImage-2.1-Diffusers", 
+    torch_dtype=torch.bfloat16
+)
+pipe = pipe.to("cuda")
+``` 
+
+You can inspect the `guider` object:
+
+```py
+>>> pipe.guider
+AdaptiveProjectedMixGuidance {
+  "_class_name": "AdaptiveProjectedMixGuidance",
+  "_diffusers_version": "0.36.0.dev0",
+  "adaptive_projected_guidance_momentum": -0.5,
+  "adaptive_projected_guidance_rescale": 10.0,
+  "adaptive_projected_guidance_scale": 10.0,
+  "adaptive_projected_guidance_start_step": 5,
+  "enabled": true,
+  "eta": 0.0,
+  "guidance_rescale": 0.0,
+  "guidance_scale": 3.5,
+  "start": 0.0,
+  "stop": 1.0,
+  "use_original_formulation": false
+}
+
+State:
+  step: None
+  num_inference_steps: None
+  timestep: None
+  count_prepared: 0
+  enabled: True
+  num_conditions: 2
+  momentum_buffer: None
+  is_apg_enabled: False
+  is_cfg_enabled: True
+```
+
+To update the guider with a different configuration, use the `new()` method. For example, to generate an image with `guidance_scale=5.0` while keeping all other default guidance parameters:
+
+```py
+import torch
+from diffusers import HunyuanImagePipeline
+
+pipe = HunyuanImagePipeline.from_pretrained(
+    "hunyuanvideo-community/HunyuanImage-2.1-Diffusers", 
+    torch_dtype=torch.bfloat16
+)
+pipe = pipe.to("cuda")
+
+# Update the guider configuration
+pipe.guider = pipe.guider.new(guidance_scale=5.0)
+
+prompt = (
+    "A cute, cartoon-style anthropomorphic penguin plush toy with fluffy fur, standing in a painting studio, "
+    "wearing a red knitted scarf and a red beret with the word 'Tencent' on it, holding a paintbrush with a "
+    "focused expression as it paints an oil painting of the Mona Lisa, rendered in a photorealistic photographic style."
+)
+
+image = pipe(
+    prompt=prompt, 
+    num_inference_steps=50, 
+    height=2048, 
+    width=2048,
+).images[0]
+image.save("image.png")
+```
+
+
+## HunyuanImage-2.1-Distilled
+
+use `distilled_guidance_scale` with the guidance-distilled checkpoint, 
+
+```py
+import torch
+from diffusers import HunyuanImagePipeline
+pipe = HunyuanImagePipeline.from_pretrained("hunyuanvideo-community/HunyuanImage-2.1-Distilled-Diffusers", torch_dtype=torch.bfloat16)
+pipe = pipe.to("cuda")
+
+prompt = (
+    "A cute, cartoon-style anthropomorphic penguin plush toy with fluffy fur, standing in a painting studio, "
+    "wearing a red knitted scarf and a red beret with the word 'Tencent' on it, holding a paintbrush with a "
+    "focused expression as it paints an oil painting of the Mona Lisa, rendered in a photorealistic photographic style."
+)
+
+out = pipe(
+    prompt,
+    num_inference_steps=8,
+    distilled_guidance_scale=3.25,
+    height=2048,
+    width=2048,
+    generator=generator,
+).images[0]
+
+```
+
+
+## HunyuanImagePipeline
+
+[[autodoc]] HunyuanImagePipeline
+  - all
+  - __call__
+
+## HunyuanImageRefinerPipeline
+
+[[autodoc]] HunyuanImageRefinerPipeline
+  - all
+  - __call__
+
+
+## HunyuanImagePipelineOutput
+
+[[autodoc]] pipelines.hunyuan_image.pipeline_output.HunyuanImagePipelineOutput

docs/source/en/api/pipelines/kandinsky5_image.md

@@ -0,0 +1,116 @@
+<!--Copyright 2025 The HuggingFace Team and Kandinsky Lab 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.
+-->
+
+# Kandinsky 5.0 Image
+
+[Kandinsky 5.0](https://arxiv.org/abs/2511.14993) is a family of diffusion models for Video & Image generation. 
+
+Kandinsky 5.0 Image Lite is a lightweight image generation model (6B parameters).
+
+The model introduces several key innovations:
+- **Latent diffusion pipeline** with **Flow Matching** for improved training stability
+- **Diffusion Transformer (DiT)** as the main generative backbone with cross-attention to text embeddings
+- Dual text encoding using **Qwen2.5-VL** and **CLIP** for comprehensive text understanding
+- **Flux VAE** for efficient image encoding and decoding
+
+The original codebase can be found at [kandinskylab/Kandinsky-5](https://github.com/kandinskylab/Kandinsky-5).
+
+> [!TIP]
+> Check out the [Kandinsky Lab](https://huggingface.co/kandinskylab) organization on the Hub for the official model checkpoints for text-to-video generation, including pretrained, SFT, no-CFG, and distilled variants.
+
+
+## Available Models
+
+Kandinsky 5.0 Image Lite:
+
+| model_id | Description | Use Cases |
+|------------|-------------|-----------|
+| [**kandinskylab/Kandinsky-5.0-T2I-Lite-sft-Diffusers**](https://huggingface.co/kandinskylab/Kandinsky-5.0-T2I-Lite-sft-Diffusers) | 6B image Supervised Fine-Tuned model | Highest generation quality |
+| [**kandinskylab/Kandinsky-5.0-I2I-Lite-sft-Diffusers**](https://huggingface.co/kandinskylab/Kandinsky-5.0-I2I-Lite-sft-Diffusers) | 6B image editing Supervised Fine-Tuned model | Highest generation quality |
+| [**kandinskylab/Kandinsky-5.0-T2I-Lite-pretrain-Diffusers**](https://huggingface.co/kandinskylab/Kandinsky-5.0-T2I-Lite-pretrain-Diffusers) | 6B image Base pretrained model | Research and fine-tuning |
+| [**kandinskylab/Kandinsky-5.0-I2I-Lite-pretrain-Diffusers**](https://huggingface.co/kandinskylab/Kandinsky-5.0-I2I-Lite-pretrain-Diffusers) | 6B image editing Base pretrained model | Research and fine-tuning |
+
+## Usage Examples
+
+### Basic Text-to-Image Generation
+
+```python
+import torch
+from diffusers import Kandinsky5T2IPipeline
+
+# Load the pipeline
+model_id = "kandinskylab/Kandinsky-5.0-T2I-Lite-sft-Diffusers"
+pipe = Kandinsky5T2IPipeline.from_pretrained(model_id)
+_ = pipe.to(device='cuda',dtype=torch.bfloat16)
+
+# Generate image
+prompt = "A fluffy, expressive cat wearing a bright red hat with a soft, slightly textured fabric. The hat should look cozy and well-fitted on the cat’s head. On the front of the hat, add clean, bold white text that reads “SWEET”, clearly visible and neatly centered. Ensure the overall lighting highlights the hat’s color and the cat’s fur details."
+
+output = pipe(
+    prompt=prompt,
+    negative_prompt="",
+    height=1024,
+    width=1024,
+    num_inference_steps=50,
+    guidance_scale=3.5,
+).image[0]
+```
+
+### Basic Image-to-Image Generation
+
+```python
+import torch
+from diffusers import Kandinsky5I2IPipeline
+from diffusers.utils import load_image 
+# Load the pipeline
+model_id = "kandinskylab/Kandinsky-5.0-I2I-Lite-sft-Diffusers"
+pipe = Kandinsky5I2IPipeline.from_pretrained(model_id)
+
+_ = pipe.to(device='cuda',dtype=torch.bfloat16)
+pipe.enable_model_cpu_offload()                                               # <--- Enable CPU offloading for single GPU inference
+
+# Edit the input image
+image = load_image(
+    "https://huggingface.co/kandinsky-community/kandinsky-3/resolve/main/assets/title.jpg?download=true"
+)
+
+prompt = "Change the background from a winter night scene to a bright summer day. Place the character on a sandy beach with clear blue sky, soft sunlight, and gentle waves in the distance. Replace the winter clothing with a light short-sleeved T-shirt (in soft pastel colors) and casual shorts. Ensure the character’s fur reflects warm daylight instead of cold winter tones. Add small beach details such as seashells, footprints in the sand, and a few scattered beach toys nearby. Keep the oranges in the scene, but place them naturally on the sand."
+negative_prompt = ""
+
+output = pipe(
+    image=image,
+    prompt=prompt,
+    negative_prompt=negative_prompt,
+    guidance_scale=3.5,
+).image[0]
+```
+
+
+## Kandinsky5T2IPipeline
+
+[[autodoc]] Kandinsky5T2IPipeline
+    - all
+    - __call__
+
+## Kandinsky5I2IPipeline
+
+[[autodoc]] Kandinsky5I2IPipeline
+    - all
+    - __call__
+
+
+## Citation
+```bibtex
+@misc{kandinsky2025,
+    author = {Alexander Belykh and Alexander Varlamov and Alexey Letunovskiy and Anastasia Aliaskina and Anastasia Maltseva and Anastasiia Kargapoltseva and Andrey Shutkin and Anna Averchenkova and Anna Dmitrienko and Bulat Akhmatov and Denis Dimitrov and Denis Koposov and Denis Parkhomenko and Dmitrii and Ilya Vasiliev and Ivan Kirillov and Julia Agafonova and Kirill Chernyshev and Kormilitsyn Semen and Lev Novitskiy and Maria Kovaleva and Mikhail Mamaev and Mikhailov and Nikita Kiselev and Nikita Osterov and Nikolai Gerasimenko and Nikolai Vaulin and Olga Kim and Olga Vdovchenko and Polina Gavrilova and Polina Mikhailova and Tatiana Nikulina and Viacheslav Vasilev and Vladimir Arkhipkin and Vladimir Korviakov and Vladimir Polovnikov and Yury Kolabushin},
+    title = {Kandinsky 5.0: A family of diffusion models for Video & Image generation},
+    howpublished = {\url{https://github.com/kandinskylab/Kandinsky-5}},
+    year = 2025
+}
+```

docs/source/en/api/pipelines/kandinsky5_video.md

@@ -0,0 +1,310 @@
+<!--Copyright 2025 The HuggingFace Team Kandinsky Lab 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.
+-->
+
+# Kandinsky 5.0 Video
+
+[Kandinsky 5.0](https://arxiv.org/abs/2511.14993) is a family of diffusion models for Video & Image generation.
+
+Kandinsky 5.0 Lite line-up of lightweight video generation models (2B parameters) that ranks #1 among open-source models in its class. It outperforms larger models and offers the best understanding of Russian concepts in the open-source ecosystem.
+
+Kandinsky 5.0 Pro line-up of large high quality video generation models (19B parameters). It offers high qualty generation in HD and more generation formats like I2V.
+
+The model introduces several key innovations:
+- **Latent diffusion pipeline** with **Flow Matching** for improved training stability
+- **Diffusion Transformer (DiT)** as the main generative backbone with cross-attention to text embeddings
+- Dual text encoding using **Qwen2.5-VL** and **CLIP** for comprehensive text understanding
+- **HunyuanVideo 3D VAE** for efficient video encoding and decoding
+- **Sparse attention mechanisms** (NABLA) for efficient long-sequence processing
+
+The original codebase can be found at [kandinskylab/Kandinsky-5](https://github.com/kandinskylab/Kandinsky-5).
+
+> [!TIP]
+> Check out the [Kandinsky Lab](https://huggingface.co/kandinskylab) organization on the Hub for the official model checkpoints for text-to-video generation, including pretrained, SFT, no-CFG, and distilled variants.
+
+## Available Models
+
+Kandinsky 5.0 T2V Pro:
+
+| model_id | Description | Use Cases |
+|------------|-------------|-----------|
+| **kandinskylab/Kandinsky-5.0-T2V-Pro-sft-5s-Diffusers** | 5 second Text-to-Video Pro model | High-quality text-to-video generation |
+| **kandinskylab/Kandinsky-5.0-I2V-Pro-sft-5s-Diffusers** | 5 second Image-to-Video Pro model | High-quality image-to-video generation |
+
+Kandinsky 5.0 T2V Lite:
+| model_id | Description | Use Cases |
+|------------|-------------|-----------|
+| **kandinskylab/Kandinsky-5.0-T2V-Lite-sft-5s-Diffusers** | 5 second Supervised Fine-Tuned model | Highest generation quality |
+| **kandinskylab/Kandinsky-5.0-T2V-Lite-sft-10s-Diffusers** | 10 second Supervised Fine-Tuned model | Highest generation quality |
+| **kandinskylab/Kandinsky-5.0-T2V-Lite-nocfg-5s-Diffusers** | 5 second Classifier-Free Guidance distilled | 2× faster inference |
+| **kandinskylab/Kandinsky-5.0-T2V-Lite-nocfg-10s-Diffusers** | 10 second Classifier-Free Guidance distilled | 2× faster inference |
+| **kandinskylab/Kandinsky-5.0-T2V-Lite-distilled16steps-5s-Diffusers** | 5 second Diffusion distilled to 16 steps | 6× faster inference, minimal quality loss |
+| **kandinskylab/Kandinsky-5.0-T2V-Lite-distilled16steps-10s-Diffusers** | 10 second Diffusion distilled to 16 steps | 6× faster inference, minimal quality loss |
+| **kandinskylab/Kandinsky-5.0-T2V-Lite-pretrain-5s-Diffusers** | 5 second Base pretrained model | Research and fine-tuning |
+| **kandinskylab/Kandinsky-5.0-T2V-Lite-pretrain-10s-Diffusers** | 10 second Base pretrained model | Research and fine-tuning |
+
+
+## Usage Examples
+
+### Basic Text-to-Video Generation
+
+#### Pro
+**⚠️ Warning!** all Pro models should be infered with pipeline.enable_model_cpu_offload()  
+```python
+import torch
+from diffusers import Kandinsky5T2VPipeline
+from diffusers.utils import export_to_video
+
+# Load the pipeline
+model_id = "kandinskylab/Kandinsky-5.0-T2V-Pro-sft-5s-Diffusers"
+pipe = Kandinsky5T2VPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16)
+
+pipe = pipe.to("cuda")
+pipeline.transformer.set_attention_backend("flex")                            # <--- Set attention bakend to Flex
+pipeline.enable_model_cpu_offload()                                           # <--- Enable cpu offloading for single GPU inference
+pipeline.transformer.compile(mode="max-autotune-no-cudagraphs", dynamic=True) # <--- Compile with max-autotune-no-cudagraphs
+
+# Generate video
+prompt = "A cat and a dog baking a cake together in a kitchen."
+negative_prompt = "Static, 2D cartoon, cartoon, 2d animation, paintings, images, worst quality, low quality, ugly, deformed, walking backwards"
+
+output = pipe(
+    prompt=prompt,
+    negative_prompt=negative_prompt,
+    height=768,
+    width=1024,
+    num_frames=121,  # ~5 seconds at 24fps
+    num_inference_steps=50,
+    guidance_scale=5.0,
+).frames[0]
+
+export_to_video(output, "output.mp4", fps=24, quality=9)
+```
+
+#### Lite
+```python
+import torch
+from diffusers import Kandinsky5T2VPipeline
+from diffusers.utils import export_to_video
+
+# Load the pipeline
+model_id = "kandinskylab/Kandinsky-5.0-T2V-Lite-sft-5s-Diffusers"
+pipe = Kandinsky5T2VPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16)
+pipe = pipe.to("cuda")
+
+# Generate video
+prompt = "A cat and a dog baking a cake together in a kitchen."
+negative_prompt = "Static, 2D cartoon, cartoon, 2d animation, paintings, images, worst quality, low quality, ugly, deformed, walking backwards"
+
+output = pipe(
+    prompt=prompt,
+    negative_prompt=negative_prompt,
+    height=512,
+    width=768,
+    num_frames=121,  # ~5 seconds at 24fps
+    num_inference_steps=50,
+    guidance_scale=5.0,
+).frames[0]
+
+export_to_video(output, "output.mp4", fps=24, quality=9)
+```
+
+### 10 second Models
+**⚠️ Warning!** all 10 second models should be used with Flex attention and max-autotune-no-cudagraphs compilation:
+
+```python
+pipe = Kandinsky5T2VPipeline.from_pretrained(
+    "kandinskylab/Kandinsky-5.0-T2V-Lite-sft-10s-Diffusers", 
+    torch_dtype=torch.bfloat16
+)
+pipe = pipe.to("cuda")
+
+pipe.transformer.set_attention_backend(
+    "flex"
+)                                       # <--- Set attention bakend to Flex
+pipe.transformer.compile(
+    mode="max-autotune-no-cudagraphs", 
+    dynamic=True
+)                                       # <--- Compile with max-autotune-no-cudagraphs
+
+prompt = "A cat and a dog baking a cake together in a kitchen."
+negative_prompt = "Static, 2D cartoon, cartoon, 2d animation, paintings, images, worst quality, low quality, ugly, deformed, walking backwards"
+
+output = pipe(
+    prompt=prompt,
+    negative_prompt=negative_prompt,
+    height=512,
+    width=768,
+    num_frames=241,
+    num_inference_steps=50,
+    guidance_scale=5.0,
+).frames[0]
+
+export_to_video(output, "output.mp4", fps=24, quality=9)
+```
+
+### Diffusion Distilled model
+**⚠️ Warning!** all nocfg and diffusion distilled models should be infered wothout CFG (```guidance_scale=1.0```):
+
+```python
+model_id = "kandinskylab/Kandinsky-5.0-T2V-Lite-distilled16steps-5s-Diffusers"
+pipe = Kandinsky5T2VPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16)
+pipe = pipe.to("cuda")
+
+output = pipe(
+    prompt="A beautiful sunset over mountains",
+    num_inference_steps=16,  # <--- Model is distilled in 16 steps
+    guidance_scale=1.0,      # <--- no CFG
+).frames[0]
+
+export_to_video(output, "output.mp4", fps=24, quality=9)
+```
+
+
+### Basic Image-to-Video Generation
+**⚠️ Warning!** all Pro models should be infered with pipeline.enable_model_cpu_offload()  
+```python
+import torch
+from diffusers import Kandinsky5T2VPipeline
+from diffusers.utils import export_to_video
+
+# Load the pipeline
+model_id = "kandinskylab/Kandinsky-5.0-I2V-Pro-sft-5s-Diffusers"
+pipe = Kandinsky5T2VPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16)
+
+pipe = pipe.to("cuda")
+pipeline.transformer.set_attention_backend("flex")                            # <--- Set attention bakend to Flex
+pipeline.enable_model_cpu_offload()                                           # <--- Enable cpu offloading for single GPU inference
+pipeline.transformer.compile(mode="max-autotune-no-cudagraphs", dynamic=True) # <--- Compile with max-autotune-no-cudagraphs
+
+# Generate video
+image = load_image(
+    "https://huggingface.co/kandinsky-community/kandinsky-3/resolve/main/assets/title.jpg?download=true"
+)
+height = 896
+width = 896
+image = image.resize((width, height))
+
+prompt = "An funny furry creture smiles happily and holds a sign that says 'Kandinsky'"
+negative_prompt = ""
+
+output = pipe(
+    prompt=prompt,
+    negative_prompt=negative_prompt,
+    height=height,
+    width=width,
+    num_frames=121,  # ~5 seconds at 24fps
+    num_inference_steps=50,
+    guidance_scale=5.0,
+).frames[0]
+
+export_to_video(output, "output.mp4", fps=24, quality=9)
+```
+
+
+
+## Kandinsky 5.0 Pro Side-by-Side evaluation
+
+<table border="0" style="width: 200; text-align: left; margin-top: 20px;">
+  <tr>
+      <td>
+          <img width="200" alt="image" src="https://github.com/user-attachments/assets/73e5ff00-2735-40fd-8f01-767de9181918" />
+      </td>
+      <td>
+         <img width="200" alt="image" src="https://github.com/user-attachments/assets/f449a9e7-74b7-481d-82da-02723e396acd" />
+      </td>
+
+  <tr>
+      <td>
+          Comparison with Veo 3 
+      </td>
+      <td>
+          Comparison with Veo 3 fast
+      </td>
+  <tr>
+      <td>
+          <img width="200" alt="image" src="https://github.com/user-attachments/assets/a6902fb6-b5e8-4093-adad-aa4caab79c6d" />
+      </td>
+      <td>
+          <img width="200" alt="image" src="https://github.com/user-attachments/assets/09986015-3d07-4de8-b942-c145039b9b2d" />
+      </td>
+  <tr>
+      <td>
+          Comparison with Wan 2.2 A14B Text-to-Video mode
+      </td>
+      <td>
+          Comparison with Wan 2.2 A14B Image-to-Video mode
+      </td>
+
+</table>
+
+
+## Kandinsky 5.0 Lite Side-by-Side evaluation
+
+The evaluation is based on the expanded prompts from the [Movie Gen benchmark](https://github.com/facebookresearch/MovieGenBench), which are available in the expanded_prompt column of the benchmark/moviegen_bench.csv file.
+
+<table border="0" style="width: 400; text-align: left; margin-top: 20px;">
+  <tr>
+      <td>
+          <img src="https://github.com/kandinskylab/kandinsky-5/raw/main/assets/sbs/kandinsky_5_video_lite_vs_sora.jpg" width=400 >
+      </td>
+      <td>
+          <img src="https://github.com/kandinskylab/kandinsky-5/raw/main/assets/sbs/kandinsky_5_video_lite_vs_wan_2.1_14B.jpg" width=400 >
+      </td>
+  <tr>
+      <td>
+          <img src="https://github.com/kandinskylab/kandinsky-5/raw/main/assets/sbs/kandinsky_5_video_lite_vs_wan_2.2_5B.jpg" width=400 >
+      </td>
+      <td>
+          <img src="https://github.com/kandinskylab/kandinsky-5/raw/main/assets/sbs/kandinsky_5_video_lite_vs_wan_2.2_A14B.jpg" width=400 >
+      </td>
+  <tr>
+      <td>
+          <img src="https://github.com/kandinskylab/kandinsky-5/raw/main/assets/sbs/kandinsky_5_video_lite_vs_wan_2.1_1.3B.jpg" width=400 >
+      </td>
+
+</table>
+
+
+
+
+## Kandinsky 5.0 Lite Distill Side-by-Side evaluation
+
+<table border="0" style="width: 400; text-align: left; margin-top: 20px;">
+  <tr>
+      <td>
+          <img src="https://github.com/kandinskylab/kandinsky-5/raw/main/assets/sbs/kandinsky_5_video_lite_5s_vs_kandinsky_5_video_lite_distill_5s.jpg" width=400 >
+      </td>
+      <td>
+          <img src="https://github.com/kandinskylab/kandinsky-5/raw/main/assets/sbs/kandinsky_5_video_lite_10s_vs_kandinsky_5_video_lite_distill_10s.jpg" width=400 >
+      </td>
+
+</table>
+
+## Kandinsky5T2VPipeline
+
+[[autodoc]] Kandinsky5T2VPipeline
+    - all
+    - __call__
+
+## Kandinsky5I2VPipeline
+
+[[autodoc]] Kandinsky5I2VPipeline
+    - all
+    - __call__
+
+
+## Citation
+```bibtex
+@misc{kandinsky2025,
+    author = {Alexander Belykh and Alexander Varlamov and Alexey Letunovskiy and Anastasia Aliaskina and Anastasia Maltseva and Anastasiia Kargapoltseva and Andrey Shutkin and Anna Averchenkova and Anna Dmitrienko and Bulat Akhmatov and Denis Dimitrov and Denis Koposov and Denis Parkhomenko and Dmitrii and Ilya Vasiliev and Ivan Kirillov and Julia Agafonova and Kirill Chernyshev and Kormilitsyn Semen and Lev Novitskiy and Maria Kovaleva and Mikhail Mamaev and Mikhailov and Nikita Kiselev and Nikita Osterov and Nikolai Gerasimenko and Nikolai Vaulin and Olga Kim and Olga Vdovchenko and Polina Gavrilova and Polina Mikhailova and Tatiana Nikulina and Viacheslav Vasilev and Vladimir Arkhipkin and Vladimir Korviakov and Vladimir Polovnikov and Yury Kolabushin},
+    title = {Kandinsky 5.0: A family of diffusion models for Video & Image generation},
+    howpublished = {\url{https://github.com/kandinskylab/Kandinsky-5}},
+    year = 2025
+}
+```

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

@@ -0,0 +1,114 @@
+<!--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.
+-->
+
+# LongCat-Image
+
+<div class="flex flex-wrap space-x-1">
+  <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
+</div>
+
+
+We introduce LongCat-Image, a pioneering open-source and bilingual (Chinese-English) foundation model for image generation, designed to address core challenges in multilingual text rendering, photorealism, deployment efficiency, and developer accessibility prevalent in current leading models.
+
+
+### Key Features
+- 🌟 **Exceptional Efficiency and Performance**: With only **6B parameters**, LongCat-Image surpasses numerous open-source models that are several times larger across multiple benchmarks, demonstrating the immense potential of efficient model design.
+- 🌟 **Superior Editing Performance**: LongCat-Image-Edit model achieves state-of-the-art performance among open-source models, delivering leading instruction-following and image quality with superior visual consistency.
+- 🌟 **Powerful Chinese Text Rendering**: LongCat-Image demonstrates superior accuracy and stability in rendering common Chinese characters compared to existing SOTA open-source models and achieves industry-leading coverage of the Chinese dictionary.
+- 🌟 **Remarkable Photorealism**: Through an innovative data strategy and training framework, LongCat-Image achieves remarkable photorealism in generated images.
+- 🌟 **Comprehensive Open-Source Ecosystem**: We provide a complete toolchain, from intermediate checkpoints to full training code, significantly lowering the barrier for further research and development.
+
+For more details, please refer to the comprehensive [***LongCat-Image Technical Report***](https://arxiv.org/abs/2412.11963)
+
+
+## Usage Example
+
+```py
+import torch
+import diffusers
+from diffusers import LongCatImagePipeline
+
+weight_dtype = torch.bfloat16
+pipe = LongCatImagePipeline.from_pretrained("meituan-longcat/LongCat-Image", torch_dtype=torch.bfloat16 )
+pipe.to('cuda')
+# pipe.enable_model_cpu_offload()
+
+prompt = '一个年轻的亚裔女性，身穿黄色针织衫，搭配白色项链。她的双手放在膝盖上，表情恬静。背景是一堵粗糙的砖墙，午后的阳光温暖地洒在她身上，营造出一种宁静而温馨的氛围。镜头采用中距离视角，突出她的神态和服饰的细节。光线柔和地打在她的脸上，强调她的五官和饰品的质感，增加画面的层次感与亲和力。整个画面构图简洁，砖墙的纹理与阳光的光影效果相得益彰，突显出人物的优雅与从容。'
+image = pipe(
+    prompt,
+    height=768,
+    width=1344,
+    guidance_scale=4.0,
+    num_inference_steps=50,
+    num_images_per_prompt=1,
+    generator=torch.Generator("cpu").manual_seed(43),
+    enable_cfg_renorm=True,
+    enable_prompt_rewrite=True,
+).images[0]
+image.save(f'./longcat_image_t2i_example.png')
+```
+
+
+This pipeline was contributed by LongCat-Image Team. The original codebase can be found [here](https://github.com/meituan-longcat/LongCat-Image).
+
+Available models:
+<div style="overflow-x: auto; margin-bottom: 16px;">
+  <table style="border-collapse: collapse; width: 100%;">
+    <thead>
+      <tr>
+        <th style="white-space: nowrap; padding: 8px; border: 1px solid #d0d7de; background-color: #f6f8fa;">Models</th>
+        <th style="white-space: nowrap; padding: 8px; border: 1px solid #d0d7de; background-color: #f6f8fa;">Type</th>
+        <th style="padding: 8px; border: 1px solid #d0d7de; background-color: #f6f8fa;">Description</th>
+        <th style="padding: 8px; border: 1px solid #d0d7de; background-color: #f6f8fa;">Download Link</th>
+      </tr>
+    </thead>
+    <tbody>
+      <tr>
+        <td style="white-space: nowrap; padding: 8px; border: 1px solid #d0d7de;">LongCat&#8209;Image</td>
+        <td style="white-space: nowrap; padding: 8px; border: 1px solid #d0d7de;">Text&#8209;to&#8209;Image</td>
+        <td style="padding: 8px; border: 1px solid #d0d7de;">Final Release. The standard model for out&#8209;of&#8209;the&#8209;box inference.</td>
+        <td style="padding: 8px; border: 1px solid #d0d7de;">
+          <span style="white-space: nowrap;">🤗&nbsp;<a href="https://huggingface.co/meituan-longcat/LongCat-Image">Huggingface</a></span>
+        </td>
+      </tr>
+      <tr>
+        <td style="white-space: nowrap; padding: 8px; border: 1px solid #d0d7de;">LongCat&#8209;Image&#8209;Dev</td>
+        <td style="white-space: nowrap; padding: 8px; border: 1px solid #d0d7de;">Text&#8209;to&#8209;Image</td>
+        <td style="padding: 8px; border: 1px solid #d0d7de;">Development. Mid-training checkpoint, suitable for fine-tuning.</td>
+        <td style="padding: 8px; border: 1px solid #d0d7de;">
+          <span style="white-space: nowrap;">🤗&nbsp;<a href="https://huggingface.co/meituan-longcat/LongCat-Image-Dev">Huggingface</a></span>
+        </td>
+      </tr>
+      <tr>
+        <td style="white-space: nowrap; padding: 8px; border: 1px solid #d0d7de;">LongCat&#8209;Image&#8209;Edit</td>
+        <td style="white-space: nowrap; padding: 8px; border: 1px solid #d0d7de;">Image Editing</td>
+        <td style="padding: 8px; border: 1px solid #d0d7de;">Specialized model for image editing.</td>
+        <td style="padding: 8px; border: 1px solid #d0d7de;">
+          <span style="white-space: nowrap;">🤗&nbsp;<a href="https://huggingface.co/meituan-longcat/LongCat-Image-Edit">Huggingface</a></span>
+        </td>
+      </tr>
+    </tbody>
+  </table>
+</div>
+
+## LongCatImagePipeline
+
+[[autodoc]] LongCatImagePipeline
+- all
+- __call__
+
+## LongCatImagePipelineOutput
+
+[[autodoc]] pipelines.longcat_image.pipeline_output.LongCatImagePipelineOutput
+
+
+

docs/source/en/api/pipelines/ltx2.md

@@ -0,0 +1,47 @@
+<!-- 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. -->
+
+# LTX-2
+
+<div class="flex flex-wrap space-x-1">
+  <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
+</div>
+
+LTX-2 is a DiT-based audio-video foundation model designed to generate synchronized video and audio within a single model. It brings together the core building blocks of modern video generation, with open weights and a focus on practical, local execution.
+
+You can find all the original LTX-Video checkpoints under the [Lightricks](https://huggingface.co/Lightricks) organization.
+
+The original codebase for LTX-2 can be found [here](https://github.com/Lightricks/LTX-2).
+
+## LTX2Pipeline
+
+[[autodoc]] LTX2Pipeline
+  - all
+  - __call__
+
+## LTX2ImageToVideoPipeline
+
+[[autodoc]] LTX2ImageToVideoPipeline
+  - all
+  - __call__
+
+## LTX2LatentUpsamplePipeline
+
+[[autodoc]] LTX2LatentUpsamplePipeline
+  - all
+  - __call__
+
+## LTX2PipelineOutput
+
+[[autodoc]] pipelines.ltx2.pipeline_output.LTX2PipelineOutput

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

@@ -136,7 +136,7 @@ export_to_video(video, "output.mp4", fps=24)
   - 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.
+  - 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 transitions 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.
 
@@ -329,7 +329,7 @@ export_to_video(video, "output.mp4", fps=24)
 
   <details>
   <summary>Show example code</summary>
-  
+
   ```python
   import torch
   from diffusers import LTXConditionPipeline, LTXLatentUpsamplePipeline
@@ -474,6 +474,12 @@ export_to_video(video, "output.mp4", fps=24)
 
   </details>
 
+## LTXI2VLongMultiPromptPipeline
+
+[[autodoc]] LTXI2VLongMultiPromptPipeline
+  - all
+  - __call__
+
 ## LTXPipeline
 
 [[autodoc]] LTXPipeline

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

@@ -0,0 +1,50 @@
+<!--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.
+-->
+
+# Ovis-Image
+
+![concepts](https://github.com/AIDC-AI/Ovis-Image/blob/main/docs/imgs/ovis_image_case.png)
+
+Ovis-Image is a 7B text-to-image model specifically optimized for high-quality text rendering, designed to operate efficiently under stringent computational constraints.
+
+[Ovis-Image Technical Report](https://arxiv.org/abs/2511.22982) from Alibaba Group, by Guo-Hua Wang, Liangfu Cao, Tianyu Cui, Minghao Fu, Xiaohao Chen, Pengxin Zhan, Jianshan Zhao, Lan Li, Bowen Fu, Jiaqi Liu, Qing-Guo Chen.
+
+The abstract from the paper is:
+
+*We introduce Ovis-Image, a 7B text-to-image model specifically optimized for high-quality text rendering, designed to operate efficiently under stringent computational constraints. Built upon our previous Ovis-U1 framework, Ovis-Image integrates a diffusion-based visual decoder with the stronger Ovis 2.5 multimodal backbone, leveraging a text-centric training pipeline that combines large-scale pre-training with carefully tailored post-training refinements. Despite its compact architecture, Ovis-Image achieves text rendering performance on par with significantly larger open models such as Qwen-Image and approaches closed-source systems like Seedream and GPT4o. Crucially, the model remains deployable on a single high-end GPU with moderate memory, narrowing the gap between frontier-level text rendering and practical deployment. Our results indicate that combining a strong multimodal backbone with a carefully designed, text-focused training recipe is sufficient to achieve reliable bilingual text rendering without resorting to oversized or proprietary models.*
+
+**Highlights**: 
+
+*   **Strong text rendering at a compact 7B scale**: Ovis-Image is a 7B text-to-image model that delivers text rendering quality comparable to much larger 20B-class systems such as Qwen-Image and competitive with leading closed-source models like GPT4o in text-centric scenarios, while remaining small enough to run on widely accessible hardware.
+*   **High fidelity on text-heavy, layout-sensitive prompts**: The model excels on prompts that demand tight alignment between linguistic content and rendered typography (e.g., posters, banners, logos, UI mockups, infographics), producing legible, correctly spelled, and semantically consistent text across diverse fonts, sizes, and aspect ratios without compromising overall visual quality.
+*   **Efficiency and deployability**: With its 7B parameter budget and streamlined architecture, Ovis-Image fits on a single high-end GPU with moderate memory, supports low-latency interactive use, and scales to batch production serving, bringing near–frontier text rendering to applications where tens-of-billions–parameter models are impractical.
+
+
+This pipeline was contributed by Ovis-Image Team. The original codebase can be found [here](https://github.com/AIDC-AI/Ovis-Image).
+
+Available models:
+
+| Model | Recommended dtype |
+|:-----:|:-----------------:|
+| [`AIDC-AI/Ovis-Image-7B`](https://huggingface.co/AIDC-AI/Ovis-Image-7B) | `torch.bfloat16` |
+
+Refer to [this](https://huggingface.co/collections/AIDC-AI/ovis-image) collection for more information.
+
+## OvisImagePipeline
+
+[[autodoc]] OvisImagePipeline
+	- all
+	- __call__
+
+## OvisImagePipelineOutput
+
+[[autodoc]] pipelines.ovis_image.pipeline_output.OvisImagePipelineOutput

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

@@ -0,0 +1,131 @@
+<!-- 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. -->
+
+# PRX
+
+
+PRX generates high-quality images from text using a simplified MMDIT architecture where text tokens don't update through transformer blocks. It employs flow matching with discrete scheduling for efficient sampling and uses Google's T5Gemma-2B-2B-UL2 model for multi-language text encoding. The ~1.3B parameter transformer delivers fast inference without sacrificing quality. You can choose between Flux VAE (8x compression, 16 latent channels) for balanced quality and speed or DC-AE (32x compression, 32 latent channels) for latent compression and faster processing.
+
+## Available models
+
+PRX offers multiple variants with different VAE configurations, each optimized for specific resolutions. Base models excel with detailed prompts, capturing complex compositions and subtle details. Fine-tuned models trained on the [Alchemist dataset](https://huggingface.co/datasets/yandex/alchemist) improve aesthetic quality, especially with simpler prompts.
+
+
+| Model | Resolution | Fine-tuned | Distilled | Description | Suggested prompts | Suggested parameters | Recommended dtype |
+|:-----:|:-----------------:|:----------:|:----------:|:----------:|:----------:|:----------:|:----------:|
+| [`Photoroom/prx-256-t2i`](https://huggingface.co/Photoroom/prx-256-t2i)| 256 | No | No | Base model pre-trained at 256 with Flux VAE|Works best with detailed prompts in natural language|28 steps, cfg=5.0| `torch.bfloat16` |
+| [`Photoroom/prx-256-t2i-sft`](https://huggingface.co/Photoroom/prx-256-t2i-sft)| 512 | Yes | No | Fine-tuned on the [Alchemist dataset](https://huggingface.co/datasets/yandex/alchemist) dataset with Flux VAE | Can handle less detailed prompts|28 steps, cfg=5.0| `torch.bfloat16` |
+| [`Photoroom/prx-512-t2i`](https://huggingface.co/Photoroom/prx-512-t2i)| 512 | No | No | Base model pre-trained at 512 with Flux VAE |Works best with detailed prompts in natural language|28 steps, cfg=5.0| `torch.bfloat16` |
+| [`Photoroom/prx-512-t2i-sft`](https://huggingface.co/Photoroom/prx-512-t2i-sft)| 512 | Yes | No | Fine-tuned on the [Alchemist dataset](https://huggingface.co/datasets/yandex/alchemist) dataset with Flux VAE | Can handle less detailed prompts in natural language|28 steps, cfg=5.0| `torch.bfloat16` |
+| [`Photoroom/prx-512-t2i-sft-distilled`](https://huggingface.co/Photoroom/prx-512-t2i-sft-distilled)| 512 | Yes | Yes | 8-step distilled model from [`Photoroom/prx-512-t2i-sft`](https://huggingface.co/Photoroom/prx-512-t2i-sft) | Can handle less detailed prompts in natural language|8 steps, cfg=1.0| `torch.bfloat16` |
+| [`Photoroom/prx-512-t2i-dc-ae`](https://huggingface.co/Photoroom/prx-512-t2i-dc-ae)| 512 | No | No | Base model pre-trained at 512 with [Deep Compression Autoencoder (DC-AE)](https://hanlab.mit.edu/projects/dc-ae)|Works best with detailed prompts in natural language|28 steps, cfg=5.0| `torch.bfloat16` |
+| [`Photoroom/prx-512-t2i-dc-ae-sft`](https://huggingface.co/Photoroom/prx-512-t2i-dc-ae-sft)| 512 | Yes | No | Fine-tuned on the [Alchemist dataset](https://huggingface.co/datasets/yandex/alchemist) dataset with [Deep Compression Autoencoder (DC-AE)](https://hanlab.mit.edu/projects/dc-ae) | Can handle less detailed prompts in natural language|28 steps, cfg=5.0| `torch.bfloat16` |
+| [`Photoroom/prx-512-t2i-dc-ae-sft-distilled`](https://huggingface.co/Photoroom/prx-512-t2i-dc-ae-sft-distilled)| 512 | Yes | Yes | 8-step distilled model from [`Photoroom/prx-512-t2i-dc-ae-sft-distilled`](https://huggingface.co/Photoroom/prx-512-t2i-dc-ae-sft-distilled) | Can handle less detailed prompts in natural language|8 steps, cfg=1.0| `torch.bfloat16` |s
+
+Refer to [this](https://huggingface.co/collections/Photoroom/prx-models-68e66254c202ebfab99ad38e) collection for more information.
+
+## Loading the pipeline
+
+Load the pipeline with [`~DiffusionPipeline.from_pretrained`].
+
+```py
+from diffusers.pipelines.prx import PRXPipeline
+
+# Load pipeline - VAE and text encoder will be loaded from HuggingFace
+pipe = PRXPipeline.from_pretrained("Photoroom/prx-512-t2i-sft", torch_dtype=torch.bfloat16)
+pipe.to("cuda")
+
+prompt = "A front-facing portrait of a lion the golden savanna at sunset."
+image = pipe(prompt, num_inference_steps=28, guidance_scale=5.0).images[0]
+image.save("prx_output.png")
+```
+
+### Manual Component Loading
+
+Load components individually to customize the pipeline for instance to use quantized models.
+
+```py
+import torch
+from diffusers.pipelines.prx import PRXPipeline
+from diffusers.models import AutoencoderKL, AutoencoderDC
+from diffusers.models.transformers.transformer_prx import PRXTransformer2DModel
+from diffusers.schedulers import FlowMatchEulerDiscreteScheduler
+from transformers import T5GemmaModel, GemmaTokenizerFast
+from diffusers import BitsAndBytesConfig as DiffusersBitsAndBytesConfig
+from transformers import BitsAndBytesConfig as BitsAndBytesConfig
+
+quant_config = DiffusersBitsAndBytesConfig(load_in_8bit=True)
+# Load transformer
+transformer = PRXTransformer2DModel.from_pretrained(
+    "checkpoints/prx-512-t2i-sft",
+    subfolder="transformer",
+    quantization_config=quant_config,
+    torch_dtype=torch.bfloat16,
+)
+
+# Load scheduler
+scheduler = FlowMatchEulerDiscreteScheduler.from_pretrained(
+    "checkpoints/prx-512-t2i-sft", subfolder="scheduler"
+)
+
+# Load T5Gemma text encoder
+t5gemma_model = T5GemmaModel.from_pretrained("google/t5gemma-2b-2b-ul2",
+                                            quantization_config=quant_config,
+                                            torch_dtype=torch.bfloat16)
+text_encoder = t5gemma_model.encoder.to(dtype=torch.bfloat16)
+tokenizer = GemmaTokenizerFast.from_pretrained("google/t5gemma-2b-2b-ul2")
+tokenizer.model_max_length = 256
+
+# Load VAE - choose either Flux VAE or DC-AE
+# Flux VAE
+vae = AutoencoderKL.from_pretrained("black-forest-labs/FLUX.1-dev",
+                                    subfolder="vae",
+                                    quantization_config=quant_config,
+                                    torch_dtype=torch.bfloat16)
+
+pipe = PRXPipeline(
+    transformer=transformer,
+    scheduler=scheduler,
+    text_encoder=text_encoder,
+    tokenizer=tokenizer,
+    vae=vae
+)
+pipe.to("cuda")
+```
+
+
+## Memory Optimization
+
+For memory-constrained environments:
+
+```py
+import torch
+from diffusers.pipelines.prx import PRXPipeline
+
+pipe = PRXPipeline.from_pretrained("Photoroom/prx-512-t2i-sft", torch_dtype=torch.bfloat16)
+pipe.enable_model_cpu_offload()  # Offload components to CPU when not in use
+
+# Or use sequential CPU offload for even lower memory
+pipe.enable_sequential_cpu_offload()
+```
+
+## PRXPipeline
+
+[[autodoc]] PRXPipeline
+  - all
+  - __call__
+
+## PRXPipelineOutput
+
+[[autodoc]] pipelines.prx.pipeline_output.PRXPipelineOutput

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

@@ -95,7 +95,7 @@ image.save("qwen_fewsteps.png")
 
 With [`QwenImageEditPlusPipeline`], one can provide multiple images as input reference.
 
-```
+```py
 import torch
 from PIL import Image
 from diffusers import QwenImageEditPlusPipeline

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

@@ -24,9 +24,6 @@ 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.
-
 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:

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

@@ -0,0 +1,189 @@
+<!-- Copyright 2025 The SANA-Video Authors and 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-Video
+
+<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-Video: Efficient Video Generation with Block Linear Diffusion Transformer](https://huggingface.co/papers/2509.24695) from NVIDIA and MIT HAN Lab, by Junsong Chen, Yuyang Zhao, Jincheng Yu, Ruihang Chu, Junyu Chen, Shuai Yang, Xianbang Wang, Yicheng Pan, Daquan Zhou, Huan Ling, Haozhe Liu, Hongwei Yi, Hao Zhang, Muyang Li, Yukang Chen, Han Cai, Sanja Fidler, Ping Luo, Song Han, Enze Xie.
+
+The abstract from the paper is:
+
+*We introduce SANA-Video, a small diffusion model that can efficiently generate videos up to 720x1280 resolution and minute-length duration. SANA-Video synthesizes high-resolution, high-quality and long videos with strong text-video alignment at a remarkably fast speed, deployable on RTX 5090 GPU. Two core designs ensure our efficient, effective and long video generation: (1) Linear DiT: We leverage linear attention as the core operation, which is more efficient than vanilla attention given the large number of tokens processed in video generation. (2) Constant-Memory KV cache for Block Linear Attention: we design block-wise autoregressive approach for long video generation by employing a constant-memory state, derived from the cumulative properties of linear attention. This KV cache provides the Linear DiT with global context at a fixed memory cost, eliminating the need for a traditional KV cache and enabling efficient, minute-long video generation. In addition, we explore effective data filters and model training strategies, narrowing the training cost to 12 days on 64 H100 GPUs, which is only 1% of the cost of MovieGen. Given its low cost, SANA-Video achieves competitive performance compared to modern state-of-the-art small diffusion models (e.g., Wan 2.1-1.3B and SkyReel-V2-1.3B) while being 16x faster in measured latency. Moreover, SANA-Video can be deployed on RTX 5090 GPUs with NVFP4 precision, accelerating the inference speed of generating a 5-second 720p video from 71s to 29s (2.4x speedup). In summary, SANA-Video enables low-cost, high-quality video generation. [this https URL](https://github.com/NVlabs/SANA).*
+
+This pipeline was contributed by SANA Team. 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://hf.co/collections/Efficient-Large-Model/sana-video).
+
+Available models:
+
+| Model | Recommended dtype |
+|:-----:|:-----------------:|
+| [`Efficient-Large-Model/SANA-Video_2B_480p_diffusers`](https://huggingface.co/Efficient-Large-Model/ANA-Video_2B_480p_diffusers) | `torch.bfloat16` |
+
+Refer to [this](https://huggingface.co/collections/Efficient-Large-Model/sana-video) collection for more information.
+
+Note: The recommended dtype mentioned is for the transformer weights. The text encoder 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. 
+
+
+## Generation Pipelines
+
+<hfoptions id="generation pipelines">`
+<hfoption id="Text-to-Video">
+
+The example below demonstrates how to use the text-to-video pipeline to generate a video using a text description.
+
+```python
+pipe = SanaVideoPipeline.from_pretrained(
+    "Efficient-Large-Model/SANA-Video_2B_480p_diffusers", 
+    torch_dtype=torch.bfloat16,
+)
+pipe.text_encoder.to(torch.bfloat16)
+pipe.vae.to(torch.float32)
+pipe.to("cuda")
+
+prompt = "A cat and a dog baking a cake together in a kitchen. The cat is carefully measuring flour, while the dog is stirring the batter with a wooden spoon. The kitchen is cozy, with sunlight streaming through the window."
+negative_prompt = "A chaotic sequence with misshapen, deformed limbs in heavy motion blur, sudden disappearance, jump cuts, jerky movements, rapid shot changes, frames out of sync, inconsistent character shapes, temporal artifacts, jitter, and ghosting effects, creating a disorienting visual experience."
+motion_scale = 30
+motion_prompt = f" motion score: {motion_scale}."
+prompt = prompt + motion_prompt
+
+video = pipe(
+    prompt=prompt,
+    negative_prompt=negative_prompt,
+    height=480,
+    width=832,
+    frames=81,
+    guidance_scale=6,
+    num_inference_steps=50,
+    generator=torch.Generator(device="cuda").manual_seed(0),
+).frames[0]
+
+export_to_video(video, "sana_video.mp4", fps=16)
+```
+
+</hfoption>
+<hfoption id="Image-to-Video">
+
+The example below demonstrates how to use the image-to-video pipeline to generate a video using a text description and a starting frame.
+
+```python
+pipe = SanaImageToVideoPipeline.from_pretrained(
+    "Efficient-Large-Model/SANA-Video_2B_480p_diffusers",
+    torch_dtype=torch.bfloat16,
+)
+pipe.scheduler = FlowMatchEulerDiscreteScheduler.from_config(pipe.scheduler.config, flow_shift=8.0)
+pipe.vae.to(torch.float32)
+pipe.text_encoder.to(torch.bfloat16)
+pipe.to("cuda")
+
+image = load_image("https://raw.githubusercontent.com/NVlabs/Sana/refs/heads/main/asset/samples/i2v-1.png")
+prompt = "A woman stands against a stunning sunset backdrop, her long, wavy brown hair gently blowing in the breeze. She wears a sleeveless, light-colored blouse with a deep V-neckline, which accentuates her graceful posture. The warm hues of the setting sun cast a golden glow across her face and hair, creating a serene and ethereal atmosphere. The background features a blurred landscape with soft, rolling hills and scattered clouds, adding depth to the scene. The camera remains steady, capturing the tranquil moment from a medium close-up angle."
+negative_prompt = "A chaotic sequence with misshapen, deformed limbs in heavy motion blur, sudden disappearance, jump cuts, jerky movements, rapid shot changes, frames out of sync, inconsistent character shapes, temporal artifacts, jitter, and ghosting effects, creating a disorienting visual experience."
+motion_scale = 30
+motion_prompt = f" motion score: {motion_scale}."
+prompt = prompt + motion_prompt
+
+motion_scale = 30.0
+
+video = pipe(
+    image=image,
+    prompt=prompt,
+    negative_prompt=negative_prompt,
+    height=480,
+    width=832,
+    frames=81,
+    guidance_scale=6,
+    num_inference_steps=50,
+    generator=torch.Generator(device="cuda").manual_seed(0),
+).frames[0]
+
+export_to_video(video, "sana-i2v.mp4", fps=16)
+```
+
+</hfoption>
+</hfoptions>
+
+
+## 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 [`SanaVideoPipeline`] for inference with bitsandbytes.
+
+```py
+import torch
+from diffusers import BitsAndBytesConfig as DiffusersBitsAndBytesConfig, SanaVideoTransformer3DModel, SanaVideoPipeline
+from transformers import BitsAndBytesConfig as BitsAndBytesConfig, AutoModel
+
+quant_config = BitsAndBytesConfig(load_in_8bit=True)
+text_encoder_8bit = AutoModel.from_pretrained(
+    "Efficient-Large-Model/SANA-Video_2B_480p_diffusers",
+    subfolder="text_encoder",
+    quantization_config=quant_config,
+    torch_dtype=torch.float16,
+)
+
+quant_config = DiffusersBitsAndBytesConfig(load_in_8bit=True)
+transformer_8bit = SanaVideoTransformer3DModel.from_pretrained(
+    "Efficient-Large-Model/SANA-Video_2B_480p_diffusers",
+    subfolder="transformer",
+    quantization_config=quant_config,
+    torch_dtype=torch.float16,
+)
+
+pipeline = SanaVideoPipeline.from_pretrained(
+    "Efficient-Large-Model/SANA-Video_2B_480p_diffusers",
+    text_encoder=text_encoder_8bit,
+    transformer=transformer_8bit,
+    torch_dtype=torch.float16,
+    device_map="balanced",
+)
+
+model_score = 30
+prompt = "Evening, backlight, side lighting, soft light, high contrast, mid-shot, centered composition, clean solo shot, warm color. A young Caucasian man stands in a forest, golden light glimmers on his hair as sunlight filters through the leaves. He wears a light shirt, wind gently blowing his hair and collar, light dances across his face with his movements. The background is blurred, with dappled light and soft tree shadows in the distance. The camera focuses on his lifted gaze, clear and emotional."
+negative_prompt = "A chaotic sequence with misshapen, deformed limbs in heavy motion blur, sudden disappearance, jump cuts, jerky movements, rapid shot changes, frames out of sync, inconsistent character shapes, temporal artifacts, jitter, and ghosting effects, creating a disorienting visual experience."
+motion_prompt = f" motion score: {model_score}."
+prompt = prompt + motion_prompt
+
+output = pipeline(
+    prompt=prompt,
+    negative_prompt=negative_prompt,
+    height=480,
+    width=832,
+    num_frames=81,
+    guidance_scale=6.0,
+    num_inference_steps=50
+).frames[0]
+export_to_video(output, "sana-video-output.mp4", fps=16)
+```
+
+## SanaVideoPipeline
+
+[[autodoc]] SanaVideoPipeline
+  - all
+  - __call__
+
+
+## SanaImageToVideoPipeline
+
+[[autodoc]] SanaImageToVideoPipeline
+  - all
+  - __call__
+
+
+## SanaVideoPipelineOutput
+
+[[autodoc]] pipelines.sana_video.pipeline_sana_video.SanaVideoPipelineOutput

docs/source/en/api/pipelines/skyreels_v2.md

@@ -37,7 +37,8 @@ The following SkyReels-V2 models are supported in Diffusers:
 - [SkyReels-V2 I2V 1.3B - 540P](https://huggingface.co/Skywork/SkyReels-V2-I2V-1.3B-540P-Diffusers)
 - [SkyReels-V2 I2V 14B - 540P](https://huggingface.co/Skywork/SkyReels-V2-I2V-14B-540P-Diffusers)
 - [SkyReels-V2 I2V 14B - 720P](https://huggingface.co/Skywork/SkyReels-V2-I2V-14B-720P-Diffusers)
-- [SkyReels-V2 FLF2V 1.3B - 540P](https://huggingface.co/Skywork/SkyReels-V2-FLF2V-1.3B-540P-Diffusers)
+
+This model was contributed by [M. Tolga Cangöz](https://github.com/tolgacangoz).
 
 > [!TIP]
 > Click on the SkyReels-V2 models in the right sidebar for more examples of video generation.

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

@@ -40,6 +40,7 @@ The following Wan models are supported in Diffusers:
 - [Wan 2.2 T2V 14B](https://huggingface.co/Wan-AI/Wan2.2-T2V-A14B-Diffusers)
 - [Wan 2.2 I2V 14B](https://huggingface.co/Wan-AI/Wan2.2-I2V-A14B-Diffusers)
 - [Wan 2.2 TI2V 5B](https://huggingface.co/Wan-AI/Wan2.2-TI2V-5B-Diffusers)
+- [Wan 2.2 Animate 14B](https://huggingface.co/Wan-AI/Wan2.2-Animate-14B-Diffusers)
 
 > [!TIP]
 > Click on the Wan models in the right sidebar for more examples of video generation.
@@ -95,15 +96,15 @@ pipeline = WanPipeline.from_pretrained(
 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 
+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, 
+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
 """
 
@@ -150,15 +151,15 @@ pipeline.transformer = torch.compile(
 )
 
 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 
+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, 
+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
 """
 
@@ -249,6 +250,205 @@ The code snippets available in [this](https://github.com/huggingface/diffusers/p
 
 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.
 
+### Wan-Animate: Unified Character Animation and Replacement with Holistic Replication
+
+[Wan-Animate](https://huggingface.co/papers/2509.14055) by the Wan Team.
+
+*We introduce Wan-Animate, a unified framework for character animation and replacement. Given a character image and a reference video, Wan-Animate can animate the character by precisely replicating the expressions and movements of the character in the video to generate high-fidelity character videos. Alternatively, it can integrate the animated character into the reference video to replace the original character, replicating the scene's lighting and color tone to achieve seamless environmental integration. Wan-Animate is built upon the Wan model. To adapt it for character animation tasks, we employ a modified input paradigm to differentiate between reference conditions and regions for generation. This design unifies multiple tasks into a common symbolic representation. We use spatially-aligned skeleton signals to replicate body motion and implicit facial features extracted from source images to reenact expressions, enabling the generation of character videos with high controllability and expressiveness. Furthermore, to enhance environmental integration during character replacement, we develop an auxiliary Relighting LoRA. This module preserves the character's appearance consistency while applying the appropriate environmental lighting and color tone. Experimental results demonstrate that Wan-Animate achieves state-of-the-art performance. We are committed to open-sourcing the model weights and its source code.*
+
+The project page: https://humanaigc.github.io/wan-animate
+
+This model was mostly contributed by [M. Tolga Cangöz](https://github.com/tolgacangoz).
+
+#### Usage
+
+The Wan-Animate pipeline supports two modes of operation:
+
+1. **Animation Mode** (default): Animates a character image based on motion and expression from reference videos
+2. **Replacement Mode**: Replaces a character in a background video with a new character while preserving the scene
+
+##### Prerequisites
+
+Before using the pipeline, you need to preprocess your reference video to extract:
+- **Pose video**: Contains skeletal keypoints representing body motion
+- **Face video**: Contains facial feature representations for expression control
+
+For replacement mode, you additionally need:
+- **Background video**: The original video containing the scene
+- **Mask video**: A mask indicating where to generate content (white) vs. preserve original (black)
+
+> [!NOTE]
+> Raw videos should not be used for inputs such as `pose_video`, which the pipeline expects to be preprocessed to extract the proper information. Preprocessing scripts to prepare these inputs are available in the [original Wan-Animate repository](https://github.com/Wan-Video/Wan2.2?tab=readme-ov-file#1-preprocessing). Integration of these preprocessing steps into Diffusers is planned for a future release.
+
+The example below demonstrates how to use the Wan-Animate pipeline:
+
+<hfoptions id="Animate usage">
+<hfoption id="Animation mode">
+
+```python
+import numpy as np
+import torch
+from diffusers import AutoencoderKLWan, WanAnimatePipeline
+from diffusers.utils import export_to_video, load_image, load_video
+
+model_id = "Wan-AI/Wan2.2-Animate-14B-Diffusers"
+vae = AutoencoderKLWan.from_pretrained(model_id, subfolder="vae", torch_dtype=torch.float32)
+pipe = WanAnimatePipeline.from_pretrained(model_id, vae=vae, torch_dtype=torch.bfloat16)
+pipe.to("cuda")
+
+# Load character image and preprocessed videos
+image = load_image("path/to/character.jpg")
+pose_video = load_video("path/to/pose_video.mp4")  # Preprocessed skeletal keypoints
+face_video = load_video("path/to/face_video.mp4")  # Preprocessed facial features
+
+# Resize image to match VAE constraints
+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
+
+image, height, width = aspect_ratio_resize(image, pipe)
+
+prompt = "A person dancing energetically in a studio with dynamic lighting and professional camera work"
+negative_prompt = "blurry, low quality, distorted, deformed, static, poorly drawn"
+
+# Generate animated video
+output = pipe(
+    image=image,
+    pose_video=pose_video,
+    face_video=face_video,
+    prompt=prompt,
+    negative_prompt=negative_prompt,
+    height=height,
+    width=width,
+    segment_frame_length=77,
+    guidance_scale=1.0,
+    mode="animate",  # Animation mode (default)
+).frames[0]
+export_to_video(output, "animated_character.mp4", fps=30)
+```
+
+</hfoption>
+<hfoption id="Replacement mode">
+
+```python
+import numpy as np
+import torch
+from diffusers import AutoencoderKLWan, WanAnimatePipeline
+from diffusers.utils import export_to_video, load_image, load_video
+
+model_id = "Wan-AI/Wan2.2-Animate-14B-Diffusers"
+vae = AutoencoderKLWan.from_pretrained(model_id, subfolder="vae", torch_dtype=torch.float32)
+pipe = WanAnimatePipeline.from_pretrained(model_id, vae=vae, torch_dtype=torch.bfloat16)
+pipe.to("cuda")
+
+# Load all required inputs for replacement mode
+image = load_image("path/to/new_character.jpg")
+pose_video = load_video("path/to/pose_video.mp4")  # Preprocessed skeletal keypoints
+face_video = load_video("path/to/face_video.mp4")  # Preprocessed facial features
+background_video = load_video("path/to/background_video.mp4")  # Original scene
+mask_video = load_video("path/to/mask_video.mp4")  # Black: preserve, White: generate
+
+# Resize image to match video dimensions
+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
+
+image, height, width = aspect_ratio_resize(image, pipe)
+
+prompt = "A person seamlessly integrated into the scene with consistent lighting and environment"
+negative_prompt = "blurry, low quality, inconsistent lighting, floating, disconnected from scene"
+
+# Replace character in background video
+output = pipe(
+    image=image,
+    pose_video=pose_video,
+    face_video=face_video,
+    background_video=background_video,
+    mask_video=mask_video,
+    prompt=prompt,
+    negative_prompt=negative_prompt,
+    height=height,
+    width=width,
+    segment_frame_lengths=77,
+    guidance_scale=1.0,
+    mode="replace",  # Replacement mode
+).frames[0]
+export_to_video(output, "character_replaced.mp4", fps=30)
+```
+
+</hfoption>
+<hfoption id="Advanced options">
+
+```python
+import numpy as np
+import torch
+from diffusers import AutoencoderKLWan, WanAnimatePipeline
+from diffusers.utils import export_to_video, load_image, load_video
+
+model_id = "Wan-AI/Wan2.2-Animate-14B-Diffusers"
+vae = AutoencoderKLWan.from_pretrained(model_id, subfolder="vae", torch_dtype=torch.float32)
+pipe = WanAnimatePipeline.from_pretrained(model_id, vae=vae, torch_dtype=torch.bfloat16)
+pipe.to("cuda")
+
+image = load_image("path/to/character.jpg")
+pose_video = load_video("path/to/pose_video.mp4")
+face_video = load_video("path/to/face_video.mp4")
+
+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
+
+image, height, width = aspect_ratio_resize(image, pipe)
+
+prompt = "A person dancing energetically in a studio"
+negative_prompt = "blurry, low quality"
+
+# Advanced: Use temporal guidance and custom callback
+def callback_fn(pipe, step_index, timestep, callback_kwargs):
+    # You can modify latents or other tensors here
+    print(f"Step {step_index}, Timestep {timestep}")
+    return callback_kwargs
+
+output = pipe(
+    image=image,
+    pose_video=pose_video,
+    face_video=face_video,
+    prompt=prompt,
+    negative_prompt=negative_prompt,
+    height=height,
+    width=width,
+    segment_frame_length=77,
+    num_inference_steps=50,
+    guidance_scale=5.0,
+    prev_segment_conditioning_frames=5,  # Use 5 frames for temporal guidance (1 or 5 recommended)
+    callback_on_step_end=callback_fn,
+    callback_on_step_end_tensor_inputs=["latents"],
+).frames[0]
+export_to_video(output, "animated_advanced.mp4", fps=30)
+```
+
+</hfoption>
+</hfoptions>
+
+#### Key Parameters
+
+- **mode**: Choose between `"animate"` (default) or `"replace"`
+- **prev_segment_conditioning_frames**: Number of frames for temporal guidance (1 or 5 recommended). Using 5 provides better temporal consistency but requires more memory
+- **guidance_scale**: Controls how closely the output follows the text prompt. Higher values (5-7) produce results more aligned with the prompt. For Wan-Animate, CFG is disabled by default (`guidance_scale=1.0`) but can be enabled to support negative prompts and finer control over facial expressions. (Note that CFG will only target the text prompt and face conditioning.)
+
+
 ## Notes
 
 - Wan2.1 supports LoRAs with [`~loaders.WanLoraLoaderMixin.load_lora_weights`].
@@ -281,10 +481,10 @@ The general rule of thumb to keep in mind when preparing inputs for the VACE pip
 
   # 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 
+  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.
   """
 
@@ -359,6 +559,12 @@ The general rule of thumb to keep in mind when preparing inputs for the VACE pip
   - all
   - __call__
 
+## WanAnimatePipeline
+
+[[autodoc]] WanAnimatePipeline
+  - all
+  - __call__
+
 ## WanPipelineOutput
 
-[[autodoc]] pipelines.wan.pipeline_output.WanPipelineOutput
+[[autodoc]] pipelines.wan.pipeline_output.WanPipelineOutput

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

@@ -0,0 +1,66 @@
+<!--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.
+-->
+
+# Z-Image
+
+<div class="flex flex-wrap space-x-1">
+  <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
+</div>
+
+[Z-Image](https://huggingface.co/papers/2511.22699) is a powerful and highly efficient image generation model with 6B parameters. Currently there's only one model with two more to be released:
+
+|Model|Hugging Face|
+|---|---|
+|Z-Image-Turbo|https://huggingface.co/Tongyi-MAI/Z-Image-Turbo|
+
+## Z-Image-Turbo
+
+Z-Image-Turbo is a distilled version of Z-Image that matches or exceeds leading competitors with only 8 NFEs (Number of Function Evaluations). It offers sub-second inference latency on enterprise-grade H800 GPUs and fits comfortably within 16G VRAM consumer devices. It excels in photorealistic image generation, bilingual text rendering (English & Chinese), and robust instruction adherence.
+
+## Image-to-image
+
+Use [`ZImageImg2ImgPipeline`] to transform an existing image based on a text prompt.
+
+```python
+import torch
+from diffusers import ZImageImg2ImgPipeline
+from diffusers.utils import load_image
+
+pipe = ZImageImg2ImgPipeline.from_pretrained("Tongyi-MAI/Z-Image-Turbo", torch_dtype=torch.bfloat16)
+pipe.to("cuda")
+
+url = "https://raw.githubusercontent.com/CompVis/stable-diffusion/main/assets/stable-samples/img2img/sketch-mountains-input.jpg"
+init_image = load_image(url).resize((1024, 1024))
+
+prompt = "A fantasy landscape with mountains and a river, detailed, vibrant colors"
+image = pipe(
+    prompt,
+    image=init_image,
+    strength=0.6,
+    num_inference_steps=9,
+    guidance_scale=0.0,
+    generator=torch.Generator("cuda").manual_seed(42),
+).images[0]
+image.save("zimage_img2img.png")
+```
+
+## ZImagePipeline
+
+[[autodoc]] ZImagePipeline
+	- all
+	- __call__
+
+## ZImageImg2ImgPipeline
+
+[[autodoc]] ZImageImg2ImgPipeline
+	- all
+	- __call__

docs/source/en/hybrid_inference/api_reference.md

@@ -1,9 +1,11 @@
-# Hybrid Inference API Reference
+# Remote inference
 
-## Remote Decode
+Remote inference provides access to an [Inference Endpoint](https://huggingface.co/docs/inference-endpoints/index) to offload local generation requirements for decoding and encoding.
+
+## remote_decode
 
 [[autodoc]] utils.remote_utils.remote_decode
 
-## Remote Encode
+## remote_encode
 
 [[autodoc]] utils.remote_utils.remote_encode

docs/source/en/hybrid_inference/overview.md

@@ -10,51 +10,296 @@ an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express o
 specific language governing permissions and limitations under the License.
 -->
 
-# Hybrid Inference
-
-**Empowering local AI builders with Hybrid Inference**
-
+# Remote inference
 
 > [!TIP]
-> Hybrid Inference is an [experimental feature](https://huggingface.co/blog/remote_vae).
-> Feedback can be provided [here](https://github.com/huggingface/diffusers/issues/new?template=remote-vae-pilot-feedback.yml).
+> This is currently an experimental feature, and if you have any feedback, please feel free to leave it [here](https://github.com/huggingface/diffusers/issues/new?template=remote-vae-pilot-feedback.yml).
+
+Remote inference offloads the decoding and encoding process to a remote endpoint to relax the memory requirements for local inference with large models. This feature is powered by [Inference Endpoints](https://huggingface.co/docs/inference-endpoints/index). Refer to the table below for the supported models and endpoint.
+
+| Model | Endpoint | Checkpoint | Support |
+|---|---|---|---|
+| Stable Diffusion v1 | https://q1bj3bpq6kzilnsu.us-east-1.aws.endpoints.huggingface.cloud | [stabilityai/sd-vae-ft-mse](https://huggingface.co/stabilityai/sd-vae-ft-mse) | encode/decode |
+| Stable Diffusion XL | https://x2dmsqunjd6k9prw.us-east-1.aws.endpoints.huggingface.cloud | [madebyollin/sdxl-vae-fp16-fix](https://huggingface.co/madebyollin/sdxl-vae-fp16-fix) | encode/decode |
+| Flux | https://whhx50ex1aryqvw6.us-east-1.aws.endpoints.huggingface.cloud | [black-forest-labs/FLUX.1-schnell](https://huggingface.co/black-forest-labs/FLUX.1-schnell) | encode/decode |
+| HunyuanVideo | https://o7ywnmrahorts457.us-east-1.aws.endpoints.huggingface.cloud | [hunyuanvideo-community/HunyuanVideo](https://huggingface.co/hunyuanvideo-community/HunyuanVideo) | decode |
+
+This guide will show you how to encode and decode latents with remote inference.
+
+## Encoding
+
+Encoding converts images and videos into latent representations. Refer to the table below for the supported VAEs.
+
+Pass an image to [`~utils.remote_encode`] to encode it. The specific `scaling_factor` and `shift_factor` values for each model can be found in the [Remote inference](../hybrid_inference/api_reference) API reference.
+
+```py
+import torch
+from diffusers import FluxPipeline
+from diffusers.utils import load_image
+from diffusers.utils.remote_utils import remote_encode
+
+pipeline = FluxPipeline.from_pretrained(
+    "black-forest-labs/FLUX.1-schnell",
+    torch_dtype=torch.float16,
+    vae=None,
+    device_map="cuda"
+)
+
+init_image = load_image(
+    "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/astronaut.jpg"
+)
+init_image = init_image.resize((768, 512))
+
+init_latent = remote_encode(
+    endpoint="https://whhx50ex1aryqvw6.us-east-1.aws.endpoints.huggingface.cloud",
+    image=init_image,
+    scaling_factor=0.3611,
+    shift_factor=0.1159
+)
+```
+
+## Decoding
+
+Decoding converts latent representations back into images or videos. Refer to the table below for the available and supported VAEs.
+
+Set the output type to `"latent"` in the pipeline and set the `vae` to `None`. Pass the latents to the [`~utils.remote_decode`] function. For Flux, the latents are packed so the `height` and `width` also need to be passed. The specific `scaling_factor` and `shift_factor` values for each model can be found in the [Remote inference](../hybrid_inference/api_reference) API reference.
+
+<hfoptions id="decode">
+<hfoption id="Flux">
+
+```py
+from diffusers import FluxPipeline
+
+pipeline = FluxPipeline.from_pretrained(
+    "black-forest-labs/FLUX.1-schnell",
+    torch_dtype=torch.bfloat16,
+    vae=None,
+    device_map="cuda"
+)
+
+prompt = """
+A photorealistic Apollo-era photograph of a cat in a small astronaut suit with a bubble helmet, standing on the Moon and holding a flagpole planted in the dusty lunar soil. The flag shows a colorful paw-print emblem. Earth glows in the black sky above the stark gray surface, with sharp shadows and high-contrast lighting like vintage NASA photos.
+"""
+
+latent = pipeline(
+    prompt=prompt,
+    guidance_scale=0.0,
+    num_inference_steps=4,
+    output_type="latent",
+).images
+image = remote_decode(
+    endpoint="https://whhx50ex1aryqvw6.us-east-1.aws.endpoints.huggingface.cloud/",
+    tensor=latent,
+    height=1024,
+    width=1024,
+    scaling_factor=0.3611,
+    shift_factor=0.1159,
+)
+image.save("image.jpg")
+```
+
+</hfoption>
+<hfoption id="HunyuanVideo">
+
+```py
+import torch
+from diffusers import HunyuanVideoPipeline, HunyuanVideoTransformer3DModel
+
+transformer = HunyuanVideoTransformer3DModel.from_pretrained(
+    "hunyuanvideo-community/HunyuanVideo", subfolder="transformer", torch_dtype=torch.bfloat16
+)
+pipeline = HunyuanVideoPipeline.from_pretrained(
+    model_id, transformer=transformer, vae=None, torch_dtype=torch.float16, device_map="cuda"
+)
+
+latent = pipeline(
+    prompt="A cat walks on the grass, realistic",
+    height=320,
+    width=512,
+    num_frames=61,
+    num_inference_steps=30,
+    output_type="latent",
+).frames
+
+video = remote_decode(
+    endpoint="https://o7ywnmrahorts457.us-east-1.aws.endpoints.huggingface.cloud/",
+    tensor=latent,
+    output_type="mp4",
+)
+
+if isinstance(video, bytes):
+    with open("video.mp4", "wb") as f:
+        f.write(video)
+```
+
+</hfoption>
+</hfoptions>
+
+## Queuing
+
+Remote inference supports queuing to process multiple generation requests. While the current latent is being decoded, you can queue the next prompt.
+
+```py
+import queue
+import threading
+from IPython.display import display
+from diffusers import StableDiffusionXLPipeline
+
+def decode_worker(q: queue.Queue):
+    while True:
+        item = q.get()
+        if item is None:
+            break
+        image = remote_decode(
+            endpoint="https://q1bj3bpq6kzilnsu.us-east-1.aws.endpoints.huggingface.cloud/",
+            tensor=item,
+            scaling_factor=0.13025,
+        )
+        display(image)
+        q.task_done()
+
+q = queue.Queue()
+thread = threading.Thread(target=decode_worker, args=(q,), daemon=True)
+thread.start()
+
+def decode(latent: torch.Tensor):
+    q.put(latent)
+
+prompts = [
+    "A grainy Apollo-era style photograph of a cat in a snug astronaut suit with a bubble helmet, standing on the lunar surface and gripping a flag with a paw-print emblem. The gray Moon landscape stretches behind it, Earth glowing vividly in the black sky, shadows crisp and high-contrast.",
+    "A vintage 1960s sci-fi pulp magazine cover illustration of a heroic cat astronaut planting a flag on the Moon. Bold, saturated colors, exaggerated space gear, playful typography floating in the background, Earth painted in bright blues and greens.",
+    "A hyper-detailed cinematic shot of a cat astronaut on the Moon holding a fluttering flag, fur visible through the helmet glass, lunar dust scattering under its feet. The vastness of space and Earth in the distance create an epic, awe-inspiring tone.",
+    "A colorful cartoon drawing of a happy cat wearing a chunky, oversized spacesuit, proudly holding a flag with a big paw print on it. The Moon’s surface is simplified with craters drawn like doodles, and Earth in the sky has a smiling face.",
+    "A monochrome 1969-style press photo of a “first cat on the Moon” moment. The cat, in a tiny astronaut suit, stands by a planted flag, with grainy textures, scratches, and a blurred Earth in the background, mimicking old archival space photos."
+]
 
 
+pipeline = StableDiffusionXLPipeline.from_pretrained(
+    "https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0",
+    torch_dtype=torch.float16,
+    vae=None,
+    device_map="cuda"
+)
 
-## Why use Hybrid Inference?
+pipeline.unet = pipeline.unet.to(memory_format=torch.channels_last)
+pipeline.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
 
-Hybrid Inference offers a fast and simple way to offload local generation requirements.
+_ = pipeline(
+    prompt=prompts[0],
+    output_type="latent",
+)
 
-- 🚀 **Reduced Requirements:** Access powerful models without expensive hardware.
-- 💎 **Without Compromise:** Achieve the highest quality without sacrificing performance.
-- 💰 **Cost Effective:** It's free! 🤑
-- 🎯 **Diverse Use Cases:** Fully compatible with Diffusers 🧨 and the wider community.
-- 🔧 **Developer-Friendly:** Simple requests, fast responses.
+for prompt in prompts:
+    latent = pipeline(
+        prompt=prompt,
+        output_type="latent",
+    ).images
+    decode(latent)
 
----
+q.put(None)
+thread.join()
+```
 
-## Available Models
+## Benchmarks
 
-* **VAE Decode 🖼️:** Quickly decode latent representations into high-quality images without compromising performance or workflow speed.
-* **VAE Encode 🔢:** Efficiently encode images into latent representations for generation and training.
-* **Text Encoders 📃 (coming soon):** Compute text embeddings for your prompts quickly and accurately, ensuring a smooth and high-quality workflow.
+The tables demonstrate the memory requirements for encoding and decoding with Stable Diffusion v1.5 and SDXL on different GPUs.
 
----
+For the majority of these GPUs, the memory usage dictates whether other models (text encoders, UNet/transformer) need to be offloaded or required tiled encoding. The latter two techniques increases inference time and impacts quality.
 
-## Integrations
+<details><summary>Encoding - Stable Diffusion v1.5</summary>
 
-* **[SD.Next](https://github.com/vladmandic/sdnext):** All-in-one UI with direct supports Hybrid Inference.
-* **[ComfyUI-HFRemoteVae](https://github.com/kijai/ComfyUI-HFRemoteVae):** ComfyUI node for Hybrid Inference.
+| GPU                           | Resolution   |   Time (seconds) |   Memory (%) |   Tiled Time (secs) |   Tiled Memory (%) |
+|:------------------------------|:-------------|-----------------:|-------------:|--------------------:|-------------------:|
+| NVIDIA GeForce RTX 4090       | 512x512      |            0.015 |      3.51901 |               0.015 |            3.51901 |
+| NVIDIA GeForce RTX 4090       | 256x256      |            0.004 |      1.3154  |               0.005 |            1.3154  |
+| NVIDIA GeForce RTX 4090       | 2048x2048    |            0.402 |     47.1852  |               0.496 |            3.51901 |
+| NVIDIA GeForce RTX 4090       | 1024x1024    |            0.078 |     12.2658  |               0.094 |            3.51901 |
+| NVIDIA GeForce RTX 4080 SUPER | 512x512      |            0.023 |      5.30105 |               0.023 |            5.30105 |
+| NVIDIA GeForce RTX 4080 SUPER | 256x256      |            0.006 |      1.98152 |               0.006 |            1.98152 |
+| NVIDIA GeForce RTX 4080 SUPER | 2048x2048    |            0.574 |     71.08    |               0.656 |            5.30105 |
+| NVIDIA GeForce RTX 4080 SUPER | 1024x1024    |            0.111 |     18.4772  |               0.14  |            5.30105 |
+| NVIDIA GeForce RTX 3090       | 512x512      |            0.032 |      3.52782 |               0.032 |            3.52782 |
+| NVIDIA GeForce RTX 3090       | 256x256      |            0.01  |      1.31869 |               0.009 |            1.31869 |
+| NVIDIA GeForce RTX 3090       | 2048x2048    |            0.742 |     47.3033  |               0.954 |            3.52782 |
+| NVIDIA GeForce RTX 3090       | 1024x1024    |            0.136 |     12.2965  |               0.207 |            3.52782 |
+| NVIDIA GeForce RTX 3080       | 512x512      |            0.036 |      8.51761 |               0.036 |            8.51761 |
+| NVIDIA GeForce RTX 3080       | 256x256      |            0.01  |      3.18387 |               0.01  |            3.18387 |
+| NVIDIA GeForce RTX 3080       | 2048x2048    |            0.863 |     86.7424  |               1.191 |            8.51761 |
+| NVIDIA GeForce RTX 3080       | 1024x1024    |            0.157 |     29.6888  |               0.227 |            8.51761 |
+| NVIDIA GeForce RTX 3070       | 512x512      |            0.051 |     10.6941  |               0.051 |           10.6941  |
+| NVIDIA GeForce RTX 3070       | 256x256      |            0.015 |      3.99743 |               0.015 |            3.99743 |
+| NVIDIA GeForce RTX 3070       | 2048x2048    |            1.217 |     96.054   |               1.482 |           10.6941  |
+| NVIDIA GeForce RTX 3070       | 1024x1024    |            0.223 |     37.2751  |               0.327 |           10.6941  |
 
-## Changelog
+</details>
 
-- March 10 2025: Added VAE encode
-- March 2 2025: Initial release with VAE decoding
+<details><summary>Encoding SDXL</summary>
 
-## Contents
+| GPU                           | Resolution   |   Time (seconds) |   Memory Consumed (%) |   Tiled Time (seconds) |   Tiled Memory (%) |
+|:------------------------------|:-------------|-----------------:|----------------------:|-----------------------:|-------------------:|
+| NVIDIA GeForce RTX 4090       | 512x512      |            0.029 |               4.95707 |                  0.029 |            4.95707 |
+| NVIDIA GeForce RTX 4090       | 256x256      |            0.007 |               2.29666 |                  0.007 |            2.29666 |
+| NVIDIA GeForce RTX 4090       | 2048x2048    |            0.873 |              66.3452  |                  0.863 |           15.5649  |
+| NVIDIA GeForce RTX 4090       | 1024x1024    |            0.142 |              15.5479  |                  0.143 |           15.5479  |
+| NVIDIA GeForce RTX 4080 SUPER | 512x512      |            0.044 |               7.46735 |                  0.044 |            7.46735 |
+| NVIDIA GeForce RTX 4080 SUPER | 256x256      |            0.01  |               3.4597  |                  0.01  |            3.4597  |
+| NVIDIA GeForce RTX 4080 SUPER | 2048x2048    |            1.317 |              87.1615  |                  1.291 |           23.447   |
+| NVIDIA GeForce RTX 4080 SUPER | 1024x1024    |            0.213 |              23.4215  |                  0.214 |           23.4215  |
+| NVIDIA GeForce RTX 3090       | 512x512      |            0.058 |               5.65638 |                  0.058 |            5.65638 |
+| NVIDIA GeForce RTX 3090       | 256x256      |            0.016 |               2.45081 |                  0.016 |            2.45081 |
+| NVIDIA GeForce RTX 3090       | 2048x2048    |            1.755 |              77.8239  |                  1.614 |           18.4193  |
+| NVIDIA GeForce RTX 3090       | 1024x1024    |            0.265 |              18.4023  |                  0.265 |           18.4023  |
+| NVIDIA GeForce RTX 3080       | 512x512      |            0.064 |              13.6568  |                  0.064 |           13.6568  |
+| NVIDIA GeForce RTX 3080       | 256x256      |            0.018 |               5.91728 |                  0.018 |            5.91728 |
+| NVIDIA GeForce RTX 3080       | 2048x2048    |          OOM     |             OOM       |                  1.866 |           44.4717  |
+| NVIDIA GeForce RTX 3080       | 1024x1024    |            0.302 |              44.4308  |                  0.302 |           44.4308  |
+| NVIDIA GeForce RTX 3070       | 512x512      |            0.093 |              17.1465  |                  0.093 |           17.1465  |
+| NVIDIA GeForce RTX 3070       | 256x256      |            0.025 |               7.42931 |                  0.026 |            7.42931 |
+| NVIDIA GeForce RTX 3070       | 2048x2048    |          OOM     |             OOM       |                  2.674 |           55.8355  |
+| NVIDIA GeForce RTX 3070       | 1024x1024    |            0.443 |              55.7841  |                  0.443 |           55.7841  |
 
-The documentation is organized into three sections:
+</details>
 
-* **VAE Decode** Learn the basics of how to use VAE Decode with Hybrid Inference.
-* **VAE Encode** Learn the basics of how to use VAE Encode with Hybrid Inference.
-* **API Reference** Dive into task-specific settings and parameters.
+<details><summary>Decoding - Stable Diffusion v1.5</summary>
+
+| GPU | Resolution | Time (seconds) | Memory (%) | Tiled Time (secs) | Tiled Memory (%) |
+| --- | --- | --- | --- | --- | --- |
+| NVIDIA GeForce RTX 4090 | 512x512 | 0.031 | 5.60% | 0.031 (0%) | 5.60% |
+| NVIDIA GeForce RTX 4090 | 1024x1024 | 0.148 | 20.00% | 0.301 (+103%) | 5.60% |
+| NVIDIA GeForce RTX 4080 | 512x512 | 0.05 | 8.40% | 0.050 (0%) | 8.40% |
+| NVIDIA GeForce RTX 4080 | 1024x1024 | 0.224 | 30.00% | 0.356 (+59%) | 8.40% |
+| NVIDIA GeForce RTX 4070 Ti | 512x512 | 0.066 | 11.30% | 0.066 (0%) | 11.30% |
+| NVIDIA GeForce RTX 4070 Ti | 1024x1024 | 0.284 | 40.50% | 0.454 (+60%) | 11.40% |
+| NVIDIA GeForce RTX 3090 | 512x512 | 0.062 | 5.20% | 0.062 (0%) | 5.20% |
+| NVIDIA GeForce RTX 3090 | 1024x1024 | 0.253 | 18.50% | 0.464 (+83%) | 5.20% |
+| NVIDIA GeForce RTX 3080 | 512x512 | 0.07 | 12.80% | 0.070 (0%) | 12.80% |
+| NVIDIA GeForce RTX 3080 | 1024x1024 | 0.286 | 45.30% | 0.466 (+63%) | 12.90% |
+| NVIDIA GeForce RTX 3070 | 512x512 | 0.102 | 15.90% | 0.102 (0%) | 15.90% |
+| NVIDIA GeForce RTX 3070 | 1024x1024 | 0.421 | 56.30% | 0.746 (+77%) | 16.00% |
+
+</details>
+
+<details><summary>Decoding SDXL</summary>
+
+| GPU | Resolution | Time (seconds) | Memory Consumed (%) | Tiled Time (seconds) | Tiled Memory (%) |
+| --- | --- | --- | --- | --- | --- |
+| NVIDIA GeForce RTX 4090 | 512x512 | 0.057 | 10.00% | 0.057 (0%) | 10.00% |
+| NVIDIA GeForce RTX 4090 | 1024x1024 | 0.256 | 35.50% | 0.257 (+0.4%) | 35.50% |
+| NVIDIA GeForce RTX 4080 | 512x512 | 0.092 | 15.00% | 0.092 (0%) | 15.00% |
+| NVIDIA GeForce RTX 4080 | 1024x1024 | 0.406 | 53.30% | 0.406 (0%) | 53.30% |
+| NVIDIA GeForce RTX 4070 Ti | 512x512 | 0.121 | 20.20% | 0.120 (-0.8%) | 20.20% |
+| NVIDIA GeForce RTX 4070 Ti | 1024x1024 | 0.519 | 72.00% | 0.519 (0%) | 72.00% |
+| NVIDIA GeForce RTX 3090 | 512x512 | 0.107 | 10.50% | 0.107 (0%) | 10.50% |
+| NVIDIA GeForce RTX 3090 | 1024x1024 | 0.459 | 38.00% | 0.460 (+0.2%) | 38.00% |
+| NVIDIA GeForce RTX 3080 | 512x512 | 0.121 | 25.60% | 0.121 (0%) | 25.60% |
+| NVIDIA GeForce RTX 3080 | 1024x1024 | 0.524 | 93.00% | 0.524 (0%) | 93.00% |
+| NVIDIA GeForce RTX 3070 | 512x512 | 0.183 | 31.80% | 0.183 (0%) | 31.80% |
+| NVIDIA GeForce RTX 3070 | 1024x1024 | 0.794 | 96.40% | 0.794 (0%) | 96.40% |
+
+</details>
+
+
+## Resources
+
+- Remote inference is also supported in [SD.Next](https://github.com/vladmandic/sdnext) and [ComfyUI-HFRemoteVae](https://github.com/kijai/ComfyUI-HFRemoteVae).
+- Refer to the [Remote VAEs for decoding with Inference Endpoints](https://huggingface.co/blog/remote_vae) blog post to learn more.

docs/source/en/hybrid_inference/vae_decode.md

@@ -1,345 +0,0 @@
-# Getting Started: VAE Decode with Hybrid Inference
-
-VAE decode is an essential component of diffusion models - turning latent representations into images or videos.
-
-## Memory
-
-These tables demonstrate the VRAM requirements for VAE decode with SD v1 and SD XL on different GPUs.
-
-For the majority of these GPUs the memory usage % dictates other models (text encoders, UNet/Transformer) must be offloaded, or tiled decoding has to be used which increases time taken and impacts quality.
-
-<details><summary>SD v1.5</summary>
-
-| GPU | Resolution | Time (seconds) | Memory (%) | Tiled Time (secs) | Tiled Memory (%) |
-| --- | --- | --- | --- | --- | --- |
-| NVIDIA GeForce RTX 4090 | 512x512 | 0.031 | 5.60% | 0.031 (0%) | 5.60% |
-| NVIDIA GeForce RTX 4090 | 1024x1024 | 0.148 | 20.00% | 0.301 (+103%) | 5.60% |
-| NVIDIA GeForce RTX 4080 | 512x512 | 0.05 | 8.40% | 0.050 (0%) | 8.40% |
-| NVIDIA GeForce RTX 4080 | 1024x1024 | 0.224 | 30.00% | 0.356 (+59%) | 8.40% |
-| NVIDIA GeForce RTX 4070 Ti | 512x512 | 0.066 | 11.30% | 0.066 (0%) | 11.30% |
-| NVIDIA GeForce RTX 4070 Ti | 1024x1024 | 0.284 | 40.50% | 0.454 (+60%) | 11.40% |
-| NVIDIA GeForce RTX 3090 | 512x512 | 0.062 | 5.20% | 0.062 (0%) | 5.20% |
-| NVIDIA GeForce RTX 3090 | 1024x1024 | 0.253 | 18.50% | 0.464 (+83%) | 5.20% |
-| NVIDIA GeForce RTX 3080 | 512x512 | 0.07 | 12.80% | 0.070 (0%) | 12.80% |
-| NVIDIA GeForce RTX 3080 | 1024x1024 | 0.286 | 45.30% | 0.466 (+63%) | 12.90% |
-| NVIDIA GeForce RTX 3070 | 512x512 | 0.102 | 15.90% | 0.102 (0%) | 15.90% |
-| NVIDIA GeForce RTX 3070 | 1024x1024 | 0.421 | 56.30% | 0.746 (+77%) | 16.00% |
-
-</details>
-
-<details><summary>SDXL</summary>
-
-| GPU | Resolution | Time (seconds) | Memory Consumed (%) | Tiled Time (seconds) | Tiled Memory (%) |
-| --- | --- | --- | --- | --- | --- |
-| NVIDIA GeForce RTX 4090 | 512x512 | 0.057 | 10.00% | 0.057 (0%) | 10.00% |
-| NVIDIA GeForce RTX 4090 | 1024x1024 | 0.256 | 35.50% | 0.257 (+0.4%) | 35.50% |
-| NVIDIA GeForce RTX 4080 | 512x512 | 0.092 | 15.00% | 0.092 (0%) | 15.00% |
-| NVIDIA GeForce RTX 4080 | 1024x1024 | 0.406 | 53.30% | 0.406 (0%) | 53.30% |
-| NVIDIA GeForce RTX 4070 Ti | 512x512 | 0.121 | 20.20% | 0.120 (-0.8%) | 20.20% |
-| NVIDIA GeForce RTX 4070 Ti | 1024x1024 | 0.519 | 72.00% | 0.519 (0%) | 72.00% |
-| NVIDIA GeForce RTX 3090 | 512x512 | 0.107 | 10.50% | 0.107 (0%) | 10.50% |
-| NVIDIA GeForce RTX 3090 | 1024x1024 | 0.459 | 38.00% | 0.460 (+0.2%) | 38.00% |
-| NVIDIA GeForce RTX 3080 | 512x512 | 0.121 | 25.60% | 0.121 (0%) | 25.60% |
-| NVIDIA GeForce RTX 3080 | 1024x1024 | 0.524 | 93.00% | 0.524 (0%) | 93.00% |
-| NVIDIA GeForce RTX 3070 | 512x512 | 0.183 | 31.80% | 0.183 (0%) | 31.80% |
-| NVIDIA GeForce RTX 3070 | 1024x1024 | 0.794 | 96.40% | 0.794 (0%) | 96.40% |
-
-</details>
-
-## Available VAEs
-
-|   | **Endpoint** | **Model** |
-|:-:|:-----------:|:--------:|
-| **Stable Diffusion v1** | [https://q1bj3bpq6kzilnsu.us-east-1.aws.endpoints.huggingface.cloud](https://q1bj3bpq6kzilnsu.us-east-1.aws.endpoints.huggingface.cloud) | [`stabilityai/sd-vae-ft-mse`](https://hf.co/stabilityai/sd-vae-ft-mse) |
-| **Stable Diffusion XL** | [https://x2dmsqunjd6k9prw.us-east-1.aws.endpoints.huggingface.cloud](https://x2dmsqunjd6k9prw.us-east-1.aws.endpoints.huggingface.cloud) | [`madebyollin/sdxl-vae-fp16-fix`](https://hf.co/madebyollin/sdxl-vae-fp16-fix) |
-| **Flux** | [https://whhx50ex1aryqvw6.us-east-1.aws.endpoints.huggingface.cloud](https://whhx50ex1aryqvw6.us-east-1.aws.endpoints.huggingface.cloud) | [`black-forest-labs/FLUX.1-schnell`](https://hf.co/black-forest-labs/FLUX.1-schnell) |
-| **HunyuanVideo** | [https://o7ywnmrahorts457.us-east-1.aws.endpoints.huggingface.cloud](https://o7ywnmrahorts457.us-east-1.aws.endpoints.huggingface.cloud) | [`hunyuanvideo-community/HunyuanVideo`](https://hf.co/hunyuanvideo-community/HunyuanVideo) |
-
-
-> [!TIP]
-> Model support can be requested [here](https://github.com/huggingface/diffusers/issues/new?template=remote-vae-pilot-feedback.yml).
-
-
-## Code
-
-> [!TIP]
-> Install `diffusers` from `main` to run the code: `pip install git+https://github.com/huggingface/diffusers@main`
-
-
-A helper method simplifies interacting with Hybrid Inference.
-
-```python
-from diffusers.utils.remote_utils import remote_decode
-```
-
-### Basic example
-
-Here, we show how to use the remote VAE on random tensors.
-
-<details><summary>Code</summary>
-
-```python
-image = remote_decode(
-    endpoint="https://q1bj3bpq6kzilnsu.us-east-1.aws.endpoints.huggingface.cloud/",
-    tensor=torch.randn([1, 4, 64, 64], dtype=torch.float16),
-    scaling_factor=0.18215,
-)
-```
-
-</details>
-
-<figure class="image flex flex-col items-center justify-center text-center m-0 w-full">
-<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/blog/remote_vae/output.png"/>
-</figure>
-
-Usage for Flux is slightly different. Flux latents are packed so we need to send the `height` and `width`.
-
-<details><summary>Code</summary>
-
-```python
-image = remote_decode(
-    endpoint="https://whhx50ex1aryqvw6.us-east-1.aws.endpoints.huggingface.cloud/",
-    tensor=torch.randn([1, 4096, 64], dtype=torch.float16),
-    height=1024,
-    width=1024,
-    scaling_factor=0.3611,
-    shift_factor=0.1159,
-)
-```
-
-</details>
-
-<figure class="image flex flex-col items-center justify-center text-center m-0 w-full">
-<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/blog/remote_vae/flux_random_latent.png"/>
-</figure>
-
-Finally, an example for HunyuanVideo.
-
-<details><summary>Code</summary>
-
-```python
-video = remote_decode(
-    endpoint="https://o7ywnmrahorts457.us-east-1.aws.endpoints.huggingface.cloud/",
-    tensor=torch.randn([1, 16, 3, 40, 64], dtype=torch.float16),
-    output_type="mp4",
-)
-with open("video.mp4", "wb") as f:
-    f.write(video)
-```
-
-</details>
-
-<figure class="image flex flex-col items-center justify-center text-center m-0 w-full">
-   <video
-      alt="queue.mp4"
-      autoplay loop autobuffer muted playsinline
-    >
-    <source src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/blog/remote_vae/video_1.mp4" type="video/mp4">
-  </video>
-</figure>
-
-
-### Generation
-
-But we want to use the VAE on an actual pipeline to get an actual image, not random noise. The example below shows how to do it with SD v1.5. 
-
-<details><summary>Code</summary>
-
-```python
-from diffusers import StableDiffusionPipeline
-
-pipe = StableDiffusionPipeline.from_pretrained(
-    "stable-diffusion-v1-5/stable-diffusion-v1-5",
-    torch_dtype=torch.float16,
-    variant="fp16",
-    vae=None,
-).to("cuda")
-
-prompt = "Strawberry ice cream, in a stylish modern glass, coconut, splashing milk cream and honey, in a gradient purple background, fluid motion, dynamic movement, cinematic lighting, Mysterious"
-
-latent = pipe(
-    prompt=prompt,
-    output_type="latent",
-).images
-image = remote_decode(
-    endpoint="https://q1bj3bpq6kzilnsu.us-east-1.aws.endpoints.huggingface.cloud/",
-    tensor=latent,
-    scaling_factor=0.18215,
-)
-image.save("test.jpg")
-```
-
-</details>
-
-<figure class="image flex flex-col items-center justify-center text-center m-0 w-full">
-<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/blog/remote_vae/test.jpg"/>
-</figure>
-
-Here’s another example with Flux.
-
-<details><summary>Code</summary>
-
-```python
-from diffusers import FluxPipeline
-
-pipe = FluxPipeline.from_pretrained(
-    "black-forest-labs/FLUX.1-schnell",
-    torch_dtype=torch.bfloat16,
-    vae=None,
-).to("cuda")
-
-prompt = "Strawberry ice cream, in a stylish modern glass, coconut, splashing milk cream and honey, in a gradient purple background, fluid motion, dynamic movement, cinematic lighting, Mysterious"
-
-latent = pipe(
-    prompt=prompt,
-    guidance_scale=0.0,
-    num_inference_steps=4,
-    output_type="latent",
-).images
-image = remote_decode(
-    endpoint="https://whhx50ex1aryqvw6.us-east-1.aws.endpoints.huggingface.cloud/",
-    tensor=latent,
-    height=1024,
-    width=1024,
-    scaling_factor=0.3611,
-    shift_factor=0.1159,
-)
-image.save("test.jpg")
-```
-
-</details>
-
-<figure class="image flex flex-col items-center justify-center text-center m-0 w-full">
-<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/blog/remote_vae/test_1.jpg"/>
-</figure>
-
-Here’s an example with HunyuanVideo.
-
-<details><summary>Code</summary>
-
-```python
-from diffusers import HunyuanVideoPipeline, HunyuanVideoTransformer3DModel
-
-model_id = "hunyuanvideo-community/HunyuanVideo"
-transformer = HunyuanVideoTransformer3DModel.from_pretrained(
-    model_id, subfolder="transformer", torch_dtype=torch.bfloat16
-)
-pipe = HunyuanVideoPipeline.from_pretrained(
-    model_id, transformer=transformer, vae=None, torch_dtype=torch.float16
-).to("cuda")
-
-latent = pipe(
-    prompt="A cat walks on the grass, realistic",
-    height=320,
-    width=512,
-    num_frames=61,
-    num_inference_steps=30,
-    output_type="latent",
-).frames
-
-video = remote_decode(
-    endpoint="https://o7ywnmrahorts457.us-east-1.aws.endpoints.huggingface.cloud/",
-    tensor=latent,
-    output_type="mp4",
-)
-
-if isinstance(video, bytes):
-    with open("video.mp4", "wb") as f:
-        f.write(video)
-```
-
-</details>
-
-<figure class="image flex flex-col items-center justify-center text-center m-0 w-full">
-   <video
-      alt="queue.mp4"
-      autoplay loop autobuffer muted playsinline
-    >
-    <source src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/blog/remote_vae/video.mp4" type="video/mp4">
-  </video>
-</figure>
-
-
-### Queueing
-
-One of the great benefits of using a remote VAE is that we can queue multiple generation requests. While the current latent is being processed for decoding, we can already queue another one. This helps improve concurrency. 
-
-
-<details><summary>Code</summary>
-
-```python
-import queue
-import threading
-from IPython.display import display
-from diffusers import StableDiffusionPipeline
-
-def decode_worker(q: queue.Queue):
-    while True:
-        item = q.get()
-        if item is None:
-            break
-        image = remote_decode(
-            endpoint="https://q1bj3bpq6kzilnsu.us-east-1.aws.endpoints.huggingface.cloud/",
-            tensor=item,
-            scaling_factor=0.18215,
-        )
-        display(image)
-        q.task_done()
-
-q = queue.Queue()
-thread = threading.Thread(target=decode_worker, args=(q,), daemon=True)
-thread.start()
-
-def decode(latent: torch.Tensor):
-    q.put(latent)
-
-prompts = [
-    "Blueberry ice cream, in a stylish modern glass , ice cubes, nuts, mint leaves, splashing milk cream, in a gradient purple background, fluid motion, dynamic movement, cinematic lighting, Mysterious",
-    "Lemonade in a glass, mint leaves, in an aqua and white background, flowers, ice cubes, halo, fluid motion, dynamic movement, soft lighting, digital painting, rule of thirds composition, Art by Greg rutkowski, Coby whitmore",
-    "Comic book art, beautiful, vintage, pastel neon colors, extremely detailed pupils, delicate features, light on face, slight smile, Artgerm, Mary Blair, Edmund Dulac, long dark locks, bangs, glowing, fashionable style, fairytale ambience, hot pink.",
-    "Masterpiece, vanilla cone ice cream garnished with chocolate syrup, crushed nuts, choco flakes, in a brown background, gold, cinematic lighting, Art by WLOP",
-    "A bowl of milk, falling cornflakes, berries, blueberries, in a white background, soft lighting, intricate details, rule of thirds, octane render, volumetric lighting",
-    "Cold Coffee with cream, crushed almonds, in a glass, choco flakes, ice cubes, wet, in a wooden background, cinematic lighting, hyper realistic painting, art by Carne Griffiths, octane render, volumetric lighting, fluid motion, dynamic movement, muted colors,",
-]
-
-pipe = StableDiffusionPipeline.from_pretrained(
-    "Lykon/dreamshaper-8",
-    torch_dtype=torch.float16,
-    vae=None,
-).to("cuda")
-
-pipe.unet = pipe.unet.to(memory_format=torch.channels_last)
-pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
-
-_ = pipe(
-    prompt=prompts[0],
-    output_type="latent",
-)
-
-for prompt in prompts:
-    latent = pipe(
-        prompt=prompt,
-        output_type="latent",
-    ).images
-    decode(latent)
-
-q.put(None)
-thread.join()
-```
-
-</details>
-
-
-<figure class="image flex flex-col items-center justify-center text-center m-0 w-full">
-   <video
-      alt="queue.mp4"
-      autoplay loop autobuffer muted playsinline
-    >
-    <source src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/blog/remote_vae/queue.mp4" type="video/mp4">
-  </video>
-</figure>
-
-## Integrations
-
-* **[SD.Next](https://github.com/vladmandic/sdnext):** All-in-one UI with direct supports Hybrid Inference.
-* **[ComfyUI-HFRemoteVae](https://github.com/kijai/ComfyUI-HFRemoteVae):** ComfyUI node for Hybrid Inference.

docs/source/en/hybrid_inference/vae_encode.md

@@ -1,183 +0,0 @@
-# Getting Started: VAE Encode with Hybrid Inference
-
-VAE encode is used for training, image-to-image and image-to-video - turning into images or videos into latent representations.
-
-## Memory
-
-These tables demonstrate the VRAM requirements for VAE encode with SD v1 and SD XL on different GPUs.
-
-For the majority of these GPUs the memory usage % dictates other models (text encoders, UNet/Transformer) must be offloaded, or tiled encoding has to be used which increases time taken and impacts quality.
-
-<details><summary>SD v1.5</summary>
-
-| GPU                           | Resolution   |   Time (seconds) |   Memory (%) |   Tiled Time (secs) |   Tiled Memory (%) |
-|:------------------------------|:-------------|-----------------:|-------------:|--------------------:|-------------------:|
-| NVIDIA GeForce RTX 4090       | 512x512      |            0.015 |      3.51901 |               0.015 |            3.51901 |
-| NVIDIA GeForce RTX 4090       | 256x256      |            0.004 |      1.3154  |               0.005 |            1.3154  |
-| NVIDIA GeForce RTX 4090       | 2048x2048    |            0.402 |     47.1852  |               0.496 |            3.51901 |
-| NVIDIA GeForce RTX 4090       | 1024x1024    |            0.078 |     12.2658  |               0.094 |            3.51901 |
-| NVIDIA GeForce RTX 4080 SUPER | 512x512      |            0.023 |      5.30105 |               0.023 |            5.30105 |
-| NVIDIA GeForce RTX 4080 SUPER | 256x256      |            0.006 |      1.98152 |               0.006 |            1.98152 |
-| NVIDIA GeForce RTX 4080 SUPER | 2048x2048    |            0.574 |     71.08    |               0.656 |            5.30105 |
-| NVIDIA GeForce RTX 4080 SUPER | 1024x1024    |            0.111 |     18.4772  |               0.14  |            5.30105 |
-| NVIDIA GeForce RTX 3090       | 512x512      |            0.032 |      3.52782 |               0.032 |            3.52782 |
-| NVIDIA GeForce RTX 3090       | 256x256      |            0.01  |      1.31869 |               0.009 |            1.31869 |
-| NVIDIA GeForce RTX 3090       | 2048x2048    |            0.742 |     47.3033  |               0.954 |            3.52782 |
-| NVIDIA GeForce RTX 3090       | 1024x1024    |            0.136 |     12.2965  |               0.207 |            3.52782 |
-| NVIDIA GeForce RTX 3080       | 512x512      |            0.036 |      8.51761 |               0.036 |            8.51761 |
-| NVIDIA GeForce RTX 3080       | 256x256      |            0.01  |      3.18387 |               0.01  |            3.18387 |
-| NVIDIA GeForce RTX 3080       | 2048x2048    |            0.863 |     86.7424  |               1.191 |            8.51761 |
-| NVIDIA GeForce RTX 3080       | 1024x1024    |            0.157 |     29.6888  |               0.227 |            8.51761 |
-| NVIDIA GeForce RTX 3070       | 512x512      |            0.051 |     10.6941  |               0.051 |           10.6941  |
-| NVIDIA GeForce RTX 3070       | 256x256      |            0.015 |      3.99743 |               0.015 |            3.99743 |
-| NVIDIA GeForce RTX 3070       | 2048x2048    |            1.217 |     96.054   |               1.482 |           10.6941  |
-| NVIDIA GeForce RTX 3070       | 1024x1024    |            0.223 |     37.2751  |               0.327 |           10.6941  |
-
-
-</details>
-
-<details><summary>SDXL</summary>
-
-| GPU                           | Resolution   |   Time (seconds) |   Memory Consumed (%) |   Tiled Time (seconds) |   Tiled Memory (%) |
-|:------------------------------|:-------------|-----------------:|----------------------:|-----------------------:|-------------------:|
-| NVIDIA GeForce RTX 4090       | 512x512      |            0.029 |               4.95707 |                  0.029 |            4.95707 |
-| NVIDIA GeForce RTX 4090       | 256x256      |            0.007 |               2.29666 |                  0.007 |            2.29666 |
-| NVIDIA GeForce RTX 4090       | 2048x2048    |            0.873 |              66.3452  |                  0.863 |           15.5649  |
-| NVIDIA GeForce RTX 4090       | 1024x1024    |            0.142 |              15.5479  |                  0.143 |           15.5479  |
-| NVIDIA GeForce RTX 4080 SUPER | 512x512      |            0.044 |               7.46735 |                  0.044 |            7.46735 |
-| NVIDIA GeForce RTX 4080 SUPER | 256x256      |            0.01  |               3.4597  |                  0.01  |            3.4597  |
-| NVIDIA GeForce RTX 4080 SUPER | 2048x2048    |            1.317 |              87.1615  |                  1.291 |           23.447   |
-| NVIDIA GeForce RTX 4080 SUPER | 1024x1024    |            0.213 |              23.4215  |                  0.214 |           23.4215  |
-| NVIDIA GeForce RTX 3090       | 512x512      |            0.058 |               5.65638 |                  0.058 |            5.65638 |
-| NVIDIA GeForce RTX 3090       | 256x256      |            0.016 |               2.45081 |                  0.016 |            2.45081 |
-| NVIDIA GeForce RTX 3090       | 2048x2048    |            1.755 |              77.8239  |                  1.614 |           18.4193  |
-| NVIDIA GeForce RTX 3090       | 1024x1024    |            0.265 |              18.4023  |                  0.265 |           18.4023  |
-| NVIDIA GeForce RTX 3080       | 512x512      |            0.064 |              13.6568  |                  0.064 |           13.6568  |
-| NVIDIA GeForce RTX 3080       | 256x256      |            0.018 |               5.91728 |                  0.018 |            5.91728 |
-| NVIDIA GeForce RTX 3080       | 2048x2048    |          OOM     |             OOM       |                  1.866 |           44.4717  |
-| NVIDIA GeForce RTX 3080       | 1024x1024    |            0.302 |              44.4308  |                  0.302 |           44.4308  |
-| NVIDIA GeForce RTX 3070       | 512x512      |            0.093 |              17.1465  |                  0.093 |           17.1465  |
-| NVIDIA GeForce RTX 3070       | 256x256      |            0.025 |               7.42931 |                  0.026 |            7.42931 |
-| NVIDIA GeForce RTX 3070       | 2048x2048    |          OOM     |             OOM       |                  2.674 |           55.8355  |
-| NVIDIA GeForce RTX 3070       | 1024x1024    |            0.443 |              55.7841  |                  0.443 |           55.7841  |
-
-</details>
-
-## Available VAEs
-
-|   | **Endpoint** | **Model** |
-|:-:|:-----------:|:--------:|
-| **Stable Diffusion v1** | [https://qc6479g0aac6qwy9.us-east-1.aws.endpoints.huggingface.cloud](https://qc6479g0aac6qwy9.us-east-1.aws.endpoints.huggingface.cloud) | [`stabilityai/sd-vae-ft-mse`](https://hf.co/stabilityai/sd-vae-ft-mse) |
-| **Stable Diffusion XL** | [https://xjqqhmyn62rog84g.us-east-1.aws.endpoints.huggingface.cloud](https://xjqqhmyn62rog84g.us-east-1.aws.endpoints.huggingface.cloud) | [`madebyollin/sdxl-vae-fp16-fix`](https://hf.co/madebyollin/sdxl-vae-fp16-fix) |
-| **Flux** | [https://ptccx55jz97f9zgo.us-east-1.aws.endpoints.huggingface.cloud](https://ptccx55jz97f9zgo.us-east-1.aws.endpoints.huggingface.cloud) | [`black-forest-labs/FLUX.1-schnell`](https://hf.co/black-forest-labs/FLUX.1-schnell) |
-
-
-> [!TIP]
-> Model support can be requested [here](https://github.com/huggingface/diffusers/issues/new?template=remote-vae-pilot-feedback.yml).
-
-
-## Code
-
-> [!TIP]
-> Install `diffusers` from `main` to run the code: `pip install git+https://github.com/huggingface/diffusers@main`
-
-
-A helper method simplifies interacting with Hybrid Inference.
-
-```python
-from diffusers.utils.remote_utils import remote_encode
-```
-
-### Basic example
-
-Let's encode an image, then decode it to demonstrate.
-
-<figure class="image flex flex-col items-center justify-center text-center m-0 w-full">
-<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/astronaut.jpg"/>
-</figure>
-
-<details><summary>Code</summary>
-
-```python
-from diffusers.utils import load_image
-from diffusers.utils.remote_utils import remote_decode
-
-image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/astronaut.jpg?download=true")
-
-latent = remote_encode(
-    endpoint="https://ptccx55jz97f9zgo.us-east-1.aws.endpoints.huggingface.cloud/",
-    scaling_factor=0.3611,
-    shift_factor=0.1159,
-)
-
-decoded = remote_decode(
-    endpoint="https://whhx50ex1aryqvw6.us-east-1.aws.endpoints.huggingface.cloud/",
-    tensor=latent,
-    scaling_factor=0.3611,
-    shift_factor=0.1159,
-)
-```
-
-</details>
-
-<figure class="image flex flex-col items-center justify-center text-center m-0 w-full">
-<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/blog/remote_vae/decoded.png"/>
-</figure>
-
-
-### Generation
-
-Now let's look at a generation example, we'll encode the image, generate then remotely decode too!
-
-<details><summary>Code</summary>
-
-```python
-import torch
-from diffusers import StableDiffusionImg2ImgPipeline
-from diffusers.utils import load_image
-from diffusers.utils.remote_utils import remote_decode, remote_encode
-
-pipe = StableDiffusionImg2ImgPipeline.from_pretrained(
-    "stable-diffusion-v1-5/stable-diffusion-v1-5",
-    torch_dtype=torch.float16,
-    variant="fp16",
-    vae=None,
-).to("cuda")
-
-init_image = load_image(
-    "https://raw.githubusercontent.com/CompVis/stable-diffusion/main/assets/stable-samples/img2img/sketch-mountains-input.jpg"
-)
-init_image = init_image.resize((768, 512))
-
-init_latent = remote_encode(
-    endpoint="https://qc6479g0aac6qwy9.us-east-1.aws.endpoints.huggingface.cloud/",
-    image=init_image,
-    scaling_factor=0.18215,
-)
-
-prompt = "A fantasy landscape, trending on artstation"
-latent = pipe(
-    prompt=prompt,
-    image=init_latent,
-    strength=0.75,
-    output_type="latent",
-).images
-
-image = remote_decode(
-    endpoint="https://q1bj3bpq6kzilnsu.us-east-1.aws.endpoints.huggingface.cloud/",
-    tensor=latent,
-    scaling_factor=0.18215,
-)
-image.save("fantasy_landscape.jpg")
-```
-
-</details>
-
-<figure class="image flex flex-col items-center justify-center text-center m-0 w-full">
-<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/blog/remote_vae/fantasy_landscape.png"/>
-</figure>
-
-## Integrations
-
-* **[SD.Next](https://github.com/vladmandic/sdnext):** All-in-one UI with direct supports Hybrid Inference.
-* **[ComfyUI-HFRemoteVae](https://github.com/kijai/ComfyUI-HFRemoteVae):** ComfyUI node for Hybrid Inference.

docs/source/en/modular_diffusers/custom_blocks.md

@@ -0,0 +1,492 @@
+<!--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.
+-->
+
+
+# Building Custom Blocks
+
+[ModularPipelineBlocks](./pipeline_block) are the fundamental building blocks of a [`ModularPipeline`]. You can create custom blocks by defining their inputs, outputs, and computation logic. This guide demonstrates how to create and use a custom block.
+
+> [!TIP]
+> Explore the [Modular Diffusers Custom Blocks](https://huggingface.co/collections/diffusers/modular-diffusers-custom-blocks) collection for official custom modular blocks like Nano Banana.
+
+## Project Structure
+
+Your custom block project should use the following structure:
+
+```shell
+.
+├── block.py
+└── modular_config.json
+```
+
+- `block.py` contains the custom block implementation
+- `modular_config.json` contains the metadata needed to load the block
+
+## Example: Florence 2 Inpainting Block
+
+In this example we will create a custom block that uses the [Florence 2](https://huggingface.co/docs/transformers/model_doc/florence2) model to process an input image and generate a mask for inpainting.
+
+The first step is to define the components that the block will use. In this case, we will need to use the `Florence2ForConditionalGeneration` model and its corresponding processor `AutoProcessor`. When defining components, we must specify the name of the component within our pipeline, model class via `type_hint`, and provide a `pretrained_model_name_or_path` for the component if we intend to load the model weights from a specific repository on the Hub.
+
+```py
+# Inside block.py
+from diffusers.modular_pipelines import (
+    ModularPipelineBlocks,
+    ComponentSpec,
+)
+from transformers import AutoProcessor, Florence2ForConditionalGeneration
+
+
+class Florence2ImageAnnotatorBlock(ModularPipelineBlocks):
+
+    @property
+    def expected_components(self):
+        return [
+            ComponentSpec(
+                name="image_annotator",
+                type_hint=Florence2ForConditionalGeneration,
+                pretrained_model_name_or_path="florence-community/Florence-2-base-ft",
+            ),
+            ComponentSpec(
+                name="image_annotator_processor",
+                type_hint=AutoProcessor,
+                pretrained_model_name_or_path="florence-community/Florence-2-base-ft",
+            ),
+        ]
+```
+
+Next, we define the inputs and outputs of the block. The inputs include the image to be annotated, the annotation task, and the annotation prompt. The outputs include the generated mask image and annotations.
+
+```py
+from typing import List, Union
+from PIL import Image, ImageDraw
+import torch
+import numpy as np
+
+from diffusers.modular_pipelines import (
+    PipelineState,
+    ModularPipelineBlocks,
+    InputParam,
+    ComponentSpec,
+    OutputParam,
+)
+from transformers import AutoProcessor, Florence2ForConditionalGeneration
+
+
+class Florence2ImageAnnotatorBlock(ModularPipelineBlocks):
+
+    @property
+    def expected_components(self):
+        return [
+            ComponentSpec(
+                name="image_annotator",
+                type_hint=Florence2ForConditionalGeneration,
+                pretrained_model_name_or_path="florence-community/Florence-2-base-ft",
+            ),
+            ComponentSpec(
+                name="image_annotator_processor",
+                type_hint=AutoProcessor,
+                pretrained_model_name_or_path="florence-community/Florence-2-base-ft",
+            ),
+        ]
+
+    @property
+    def inputs(self) -> List[InputParam]:
+        return [
+            InputParam(
+                "image",
+                type_hint=Union[Image.Image, List[Image.Image]],
+                required=True,
+                description="Image(s) to annotate",
+            ),
+            InputParam(
+                "annotation_task",
+                type_hint=Union[str, List[str]],
+                required=True,
+                default="<REFERRING_EXPRESSION_SEGMENTATION>",
+                description="""Annotation Task to perform on the image.
+                Supported Tasks:
+
+                <OD>
+                <REFERRING_EXPRESSION_SEGMENTATION>
+                <CAPTION>
+                <DETAILED_CAPTION>
+                <MORE_DETAILED_CAPTION>
+                <DENSE_REGION_CAPTION>
+                <CAPTION_TO_PHRASE_GROUNDING>
+                <OPEN_VOCABULARY_DETECTION>
+
+                """,
+            ),
+            InputParam(
+                "annotation_prompt",
+                type_hint=Union[str, List[str]],
+                required=True,
+                description="""Annotation Prompt to provide more context to the task.
+                Can be used to detect or segment out specific elements in the image
+                """,
+            ),
+            InputParam(
+                "annotation_output_type",
+                type_hint=str,
+                required=True,
+                default="mask_image",
+                description="""Output type from annotation predictions. Availabe options are
+                mask_image:
+                    -black and white mask image for the given image based on the task type
+                mask_overlay:
+                    - mask overlayed on the original image
+                bounding_box:
+                    - bounding boxes drawn on the original image
+                """,
+            ),
+            InputParam(
+                "annotation_overlay",
+                type_hint=bool,
+                required=True,
+                default=False,
+                description="",
+            ),
+        ]
+
+    @property
+    def intermediate_outputs(self) -> List[OutputParam]:
+        return [
+            OutputParam(
+                "mask_image",
+                type_hint=Image,
+                description="Inpainting Mask for input Image(s)",
+            ),
+            OutputParam(
+                "annotations",
+                type_hint=dict,
+                description="Annotations Predictions for input Image(s)",
+            ),
+            OutputParam(
+                "image",
+                type_hint=Image,
+                description="Annotated input Image(s)",
+            ),
+        ]
+
+```
+
+Now we implement the `__call__` method, which contains the logic for processing the input image and generating the mask.
+
+```py
+from typing import List, Union
+from PIL import Image, ImageDraw
+import torch
+import numpy as np
+
+from diffusers.modular_pipelines import (
+    PipelineState,
+    ModularPipelineBlocks,
+    InputParam,
+    ComponentSpec,
+    OutputParam,
+)
+from transformers import AutoProcessor, Florence2ForConditionalGeneration
+
+
+class Florence2ImageAnnotatorBlock(ModularPipelineBlocks):
+
+    @property
+    def expected_components(self):
+        return [
+            ComponentSpec(
+                name="image_annotator",
+                type_hint=Florence2ForConditionalGeneration,
+                pretrained_model_name_or_path="florence-community/Florence-2-base-ft",
+            ),
+            ComponentSpec(
+                name="image_annotator_processor",
+                type_hint=AutoProcessor,
+                pretrained_model_name_or_path="florence-community/Florence-2-base-ft",
+            ),
+        ]
+
+    @property
+    def inputs(self) -> List[InputParam]:
+        return [
+            InputParam(
+                "image",
+                type_hint=Union[Image.Image, List[Image.Image]],
+                required=True,
+                description="Image(s) to annotate",
+            ),
+            InputParam(
+                "annotation_task",
+                type_hint=Union[str, List[str]],
+                required=True,
+                default="<REFERRING_EXPRESSION_SEGMENTATION>",
+                description="""Annotation Task to perform on the image.
+                Supported Tasks:
+
+                <OD>
+                <REFERRING_EXPRESSION_SEGMENTATION>
+                <CAPTION>
+                <DETAILED_CAPTION>
+                <MORE_DETAILED_CAPTION>
+                <DENSE_REGION_CAPTION>
+                <CAPTION_TO_PHRASE_GROUNDING>
+                <OPEN_VOCABULARY_DETECTION>
+
+                """,
+            ),
+            InputParam(
+                "annotation_prompt",
+                type_hint=Union[str, List[str]],
+                required=True,
+                description="""Annotation Prompt to provide more context to the task.
+                Can be used to detect or segment out specific elements in the image
+                """,
+            ),
+            InputParam(
+                "annotation_output_type",
+                type_hint=str,
+                required=True,
+                default="mask_image",
+                description="""Output type from annotation predictions. Availabe options are
+                mask_image:
+                    -black and white mask image for the given image based on the task type
+                mask_overlay:
+                    - mask overlayed on the original image
+                bounding_box:
+                    - bounding boxes drawn on the original image
+                """,
+            ),
+            InputParam(
+                "annotation_overlay",
+                type_hint=bool,
+                required=True,
+                default=False,
+                description="",
+            ),
+        ]
+
+    @property
+    def intermediate_outputs(self) -> List[OutputParam]:
+        return [
+            OutputParam(
+                "mask_image",
+                type_hint=Image,
+                description="Inpainting Mask for input Image(s)",
+            ),
+            OutputParam(
+                "annotations",
+                type_hint=dict,
+                description="Annotations Predictions for input Image(s)",
+            ),
+            OutputParam(
+                "image",
+                type_hint=Image,
+                description="Annotated input Image(s)",
+            ),
+        ]
+
+    def get_annotations(self, components, images, prompts, task):
+        task_prompts = [task + prompt for prompt in prompts]
+
+        inputs = components.image_annotator_processor(
+            text=task_prompts, images=images, return_tensors="pt"
+        ).to(components.image_annotator.device, components.image_annotator.dtype)
+
+        generated_ids = components.image_annotator.generate(
+            input_ids=inputs["input_ids"],
+            pixel_values=inputs["pixel_values"],
+            max_new_tokens=1024,
+            early_stopping=False,
+            do_sample=False,
+            num_beams=3,
+        )
+        annotations = components.image_annotator_processor.batch_decode(
+            generated_ids, skip_special_tokens=False
+        )
+        outputs = []
+        for image, annotation in zip(images, annotations):
+            outputs.append(
+                components.image_annotator_processor.post_process_generation(
+                    annotation, task=task, image_size=(image.width, image.height)
+                )
+            )
+        return outputs
+
+    def prepare_mask(self, images, annotations, overlay=False, fill="white"):
+        masks = []
+        for image, annotation in zip(images, annotations):
+            mask_image = image.copy() if overlay else Image.new("L", image.size, 0)
+            draw = ImageDraw.Draw(mask_image)
+
+            for _, _annotation in annotation.items():
+                if "polygons" in _annotation:
+                    for polygon in _annotation["polygons"]:
+                        polygon = np.array(polygon).reshape(-1, 2)
+                        if len(polygon) < 3:
+                            continue
+                        polygon = polygon.reshape(-1).tolist()
+                        draw.polygon(polygon, fill=fill)
+
+                elif "bbox" in _annotation:
+                    bbox = _annotation["bbox"]
+                    draw.rectangle(bbox, fill="white")
+
+            masks.append(mask_image)
+
+        return masks
+
+    def prepare_bounding_boxes(self, images, annotations):
+        outputs = []
+        for image, annotation in zip(images, annotations):
+            image_copy = image.copy()
+            draw = ImageDraw.Draw(image_copy)
+            for _, _annotation in annotation.items():
+                bbox = _annotation["bbox"]
+                label = _annotation["label"]
+
+                draw.rectangle(bbox, outline="red", width=3)
+                draw.text((bbox[0], bbox[1] - 20), label, fill="red")
+
+            outputs.append(image_copy)
+
+        return outputs
+
+    def prepare_inputs(self, images, prompts):
+        prompts = prompts or ""
+
+        if isinstance(images, Image.Image):
+            images = [images]
+        if isinstance(prompts, str):
+            prompts = [prompts]
+
+        if len(images) != len(prompts):
+            raise ValueError("Number of images and annotation prompts must match.")
+
+        return images, prompts
+
+    @torch.no_grad()
+    def __call__(self, components, state: PipelineState) -> PipelineState:
+        block_state = self.get_block_state(state)
+        images, annotation_task_prompt = self.prepare_inputs(
+            block_state.image, block_state.annotation_prompt
+        )
+        task = block_state.annotation_task
+        fill = block_state.fill
+
+        annotations = self.get_annotations(
+            components, images, annotation_task_prompt, task
+        )
+        block_state.annotations = annotations
+        if block_state.annotation_output_type == "mask_image":
+            block_state.mask_image = self.prepare_mask(images, annotations)
+        else:
+            block_state.mask_image = None
+
+        if block_state.annotation_output_type == "mask_overlay":
+            block_state.image = self.prepare_mask(images, annotations, overlay=True, fill=fill)
+
+        elif block_state.annotation_output_type == "bounding_box":
+            block_state.image = self.prepare_bounding_boxes(images, annotations)
+
+        self.set_block_state(state, block_state)
+
+        return components, state
+
+```
+
+Once we have defined our custom block, we can save it to the Hub, using either the CLI or the [`push_to_hub`] method. This will make it easy to share and reuse our custom block with other pipelines.
+
+<hfoptions id="share">
+<hfoption id="hf CLI">
+
+```shell
+# In the folder with the `block.py` file, run:
+diffusers-cli custom_block
+```
+
+Then upload the block to the Hub:
+
+```shell
+hf upload <your repo id> . .
+```
+</hfoption>
+<hfoption id="push_to_hub">
+
+```py
+from block import Florence2ImageAnnotatorBlock
+block = Florence2ImageAnnotatorBlock()
+block.push_to_hub("<your repo id>")
+```
+
+</hfoption>
+</hfoptions>
+
+## Using Custom Blocks
+
+Load the custom block with [`~ModularPipelineBlocks.from_pretrained`] and set `trust_remote_code=True`.
+
+```py
+import torch
+from diffusers.modular_pipelines import ModularPipelineBlocks, SequentialPipelineBlocks
+from diffusers.modular_pipelines.stable_diffusion_xl import INPAINT_BLOCKS
+from diffusers.utils import load_image
+
+# Fetch the Florence2 image annotator block that will create our mask
+image_annotator_block = ModularPipelineBlocks.from_pretrained("diffusers/florence-2-custom-block", trust_remote_code=True)
+
+my_blocks = INPAINT_BLOCKS.copy()
+# insert the annotation block before the image encoding step
+my_blocks.insert("image_annotator", image_annotator_block, 1)
+
+# Create our initial set of inpainting blocks
+blocks = SequentialPipelineBlocks.from_blocks_dict(my_blocks)
+
+repo_id = "diffusers/modular-stable-diffusion-xl-base-1.0"
+pipe = blocks.init_pipeline(repo_id)
+pipe.load_components(torch_dtype=torch.float16, device_map="cuda", trust_remote_code=True)
+
+image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg?download=true")
+image = image.resize((1024, 1024))
+
+prompt = ["A red car"]
+annotation_task = "<REFERRING_EXPRESSION_SEGMENTATION>"
+annotation_prompt = ["the car"]
+
+output = pipe(
+    prompt=prompt,
+    image=image,
+    annotation_task=annotation_task,
+    annotation_prompt=annotation_prompt,
+    annotation_output_type="mask_image",
+    num_inference_steps=35,
+    guidance_scale=7.5,
+    strength=0.95,
+    output="images"
+)
+output[0].save("florence-inpainting.png")
+```
+
+## Editing Custom Blocks
+
+By default, custom blocks are saved in your cache directory. Use the `local_dir` argument to download and edit a custom block in a specific folder.
+
+```py
+import torch
+from diffusers.modular_pipelines import ModularPipelineBlocks, SequentialPipelineBlocks
+from diffusers.modular_pipelines.stable_diffusion_xl import INPAINT_BLOCKS
+from diffusers.utils import load_image
+
+# Fetch the Florence2 image annotator block that will create our mask
+image_annotator_block = ModularPipelineBlocks.from_pretrained("diffusers/florence-2-custom-block", trust_remote_code=True, local_dir="/my-local-folder")
+```
+
+Any changes made to the block files in this folder will be reflected when you load the block again.

docs/source/en/modular_diffusers/guiders.md

@@ -159,7 +159,7 @@ Change the [`~ComponentSpec.default_creation_method`] to `from_pretrained` and u
 ```py
 guider_spec = t2i_pipeline.get_component_spec("guider")
 guider_spec.default_creation_method="from_pretrained"
-guider_spec.repo="YiYiXu/modular-loader-t2i-guider"
+guider_spec.pretrained_model_name_or_path="YiYiXu/modular-loader-t2i-guider"
 guider_spec.subfolder="pag_guider"
 pag_guider = guider_spec.load()
 t2i_pipeline.update_components(guider=pag_guider)

docs/source/en/modular_diffusers/loop_sequential_pipeline_blocks.md

@@ -12,7 +12,7 @@ specific language governing permissions and limitations under the License.
 
 # LoopSequentialPipelineBlocks
 
-[`~modular_pipelines.LoopSequentialPipelineBlocks`] are a multi-block type that composes other [`~modular_pipelines.ModularPipelineBlocks`] together in a loop. Data flows circularly, using `intermediate_inputs` and `intermediate_outputs`, and each block is run iteratively. This is typically used to create a denoising loop which is iterative by default.
+[`~modular_pipelines.LoopSequentialPipelineBlocks`] are a multi-block type that composes other [`~modular_pipelines.ModularPipelineBlocks`] together in a loop. Data flows circularly, using `inputs` and `intermediate_outputs`, and each block is run iteratively. This is typically used to create a denoising loop which is iterative by default.
 
 This guide shows you how to create [`~modular_pipelines.LoopSequentialPipelineBlocks`].
 
@@ -21,7 +21,6 @@ This guide shows you how to create [`~modular_pipelines.LoopSequentialPipelineBl
 [`~modular_pipelines.LoopSequentialPipelineBlocks`], is also known as the *loop wrapper* because it defines the loop structure, iteration variables, and configuration. Within the loop wrapper, you need the following variables.
 
 - `loop_inputs` are user provided values and equivalent to [`~modular_pipelines.ModularPipelineBlocks.inputs`].
-- `loop_intermediate_inputs` are intermediate variables from the [`~modular_pipelines.PipelineState`] and equivalent to [`~modular_pipelines.ModularPipelineBlocks.intermediate_inputs`].
 - `loop_intermediate_outputs` are new intermediate variables created by the block and added to the [`~modular_pipelines.PipelineState`]. It is equivalent to [`~modular_pipelines.ModularPipelineBlocks.intermediate_outputs`].
 - `__call__` method defines the loop structure and iteration logic.
 
@@ -90,4 +89,4 @@ Add more loop blocks to run within each iteration with [`~modular_pipelines.Loop
 
 ```py
 loop = LoopWrapper.from_blocks_dict({"block1": LoopBlock(), "block2": LoopBlock})
-```
+```

docs/source/en/modular_diffusers/modular_pipeline.md

@@ -313,14 +313,14 @@ unet_spec
 ComponentSpec(
     name='unet',
     type_hint=<class 'diffusers.models.unets.unet_2d_condition.UNet2DConditionModel'>,
-    repo='RunDiffusion/Juggernaut-XL-v9',
+    pretrained_model_name_or_path='RunDiffusion/Juggernaut-XL-v9',
     subfolder='unet',
     variant='fp16',
     default_creation_method='from_pretrained'
 )
 
 # modify to load from a different repository
-unet_spec.repo = "stabilityai/stable-diffusion-xl-base-1.0"
+unet_spec.pretrained_model_name_or_path = "stabilityai/stable-diffusion-xl-base-1.0"
 
 # load component with modified spec
 unet = unet_spec.load(torch_dtype=torch.float16)

docs/source/en/modular_diffusers/pipeline_block.md

@@ -37,17 +37,7 @@ A [`~modular_pipelines.ModularPipelineBlocks`] requires `inputs`, and `intermedi
     ]
     ```
 
-- `intermediate_inputs` are values typically created from a previous block but it can also be directly provided if no preceding block generates them. Unlike `inputs`, `intermediate_inputs` can be modified.
-
-    Use `InputParam` to define `intermediate_inputs`.
-
-    ```py
-    user_intermediate_inputs = [
-        InputParam(name="processed_image", type_hint="torch.Tensor", description="image that has been preprocessed and normalized"),
-    ]
-    ```
-
-- `intermediate_outputs` are new values created by a block and added to the [`~modular_pipelines.PipelineState`]. The `intermediate_outputs` are available as `intermediate_inputs` for subsequent blocks or available as the final output from running the pipeline.
+- `intermediate_outputs` are new values created by a block and added to the [`~modular_pipelines.PipelineState`]. The `intermediate_outputs` are available as `inputs` for subsequent blocks or available as the final output from running the pipeline.
 
     Use `OutputParam` to define `intermediate_outputs`.
 
@@ -65,8 +55,8 @@ The intermediate inputs and outputs share data to connect blocks. They are acces
 
 The computation a block performs is defined in the `__call__` method and it follows a specific structure.
 
-1. Retrieve the [`~modular_pipelines.BlockState`] to get a local view of the `inputs` and `intermediate_inputs`.
-2. Implement the computation logic on the `inputs` and `intermediate_inputs`.
+1. Retrieve the [`~modular_pipelines.BlockState`] to get a local view of the `inputs`
+2. Implement the computation logic on the `inputs`.
 3. Update [`~modular_pipelines.PipelineState`] to push changes from the local [`~modular_pipelines.BlockState`] back to the global [`~modular_pipelines.PipelineState`].
 4. Return the components and state which becomes available to the next block.
 
@@ -76,7 +66,7 @@ def __call__(self, components, state):
     block_state = self.get_block_state(state)
 
     # Your computation logic here
-    # block_state contains all your inputs and intermediate_inputs
+    # block_state contains all your inputs
     # Access them like: block_state.image, block_state.processed_image
 
     # Update the pipeline state with your updated block_states
@@ -112,4 +102,4 @@ def __call__(self, components, state):
     unet = components.unet
     vae = components.vae
     scheduler = components.scheduler
-```
+```

docs/source/en/modular_diffusers/quickstart.md

@@ -183,7 +183,7 @@ from diffusers.modular_pipelines import ComponentsManager
 components = ComponentManager()
 
 dd_pipeline = dd_blocks.init_pipeline("YiYiXu/modular-demo-auto", components_manager=components, collection="diffdiff")
-dd_pipeline.load_default_componenets(torch_dtype=torch.float16)
+dd_pipeline.load_componenets(torch_dtype=torch.float16)
 dd_pipeline.to("cuda")
 ```
 

docs/source/en/modular_diffusers/sequential_pipeline_blocks.md

@@ -12,11 +12,11 @@ specific language governing permissions and limitations under the License.
 
 # SequentialPipelineBlocks
 
-[`~modular_pipelines.SequentialPipelineBlocks`] are a multi-block type that composes other [`~modular_pipelines.ModularPipelineBlocks`] together in a sequence. Data flows linearly from one block to the next using `intermediate_inputs` and `intermediate_outputs`. Each block in [`~modular_pipelines.SequentialPipelineBlocks`] usually represents a step in the pipeline, and by combining them, you gradually build a pipeline.
+[`~modular_pipelines.SequentialPipelineBlocks`] are a multi-block type that composes other [`~modular_pipelines.ModularPipelineBlocks`] together in a sequence. Data flows linearly from one block to the next using `inputs` and `intermediate_outputs`. Each block in [`~modular_pipelines.SequentialPipelineBlocks`] usually represents a step in the pipeline, and by combining them, you gradually build a pipeline.
 
 This guide shows you how to connect two blocks into a [`~modular_pipelines.SequentialPipelineBlocks`].
 
-Create two [`~modular_pipelines.ModularPipelineBlocks`]. The first block, `InputBlock`, outputs a `batch_size` value and the second block, `ImageEncoderBlock` uses `batch_size` as `intermediate_inputs`.
+Create two [`~modular_pipelines.ModularPipelineBlocks`]. The first block, `InputBlock`, outputs a `batch_size` value and the second block, `ImageEncoderBlock` uses `batch_size` as `inputs`.
 
 <hfoptions id="sequential">
 <hfoption id="InputBlock">
@@ -110,4 +110,4 @@ Inspect the sub-blocks in [`~modular_pipelines.SequentialPipelineBlocks`] by cal
 ```py
 print(blocks)
 print(blocks.doc)
-```
+```

docs/source/en/optimization/attention_backends.md

@@ -21,6 +21,7 @@ Refer to the table below for an overview of the available attention families and
 | attention family | main feature |
 |---|---|
 | FlashAttention | minimizes memory reads/writes through tiling and recomputation |
+| AI Tensor Engine for ROCm | FlashAttention implementation optimized for AMD ROCm accelerators |
 | SageAttention | quantizes attention to int8 |
 | PyTorch native | built-in PyTorch implementation using [scaled_dot_product_attention](./fp16#scaled-dot-product-attention) |
 | xFormers | memory-efficient attention with support for various attention kernels |
@@ -31,7 +32,7 @@ This guide will show you how to set and use the different attention backends.
 
 The [`~ModelMixin.set_attention_backend`] method iterates through all the modules in the model and sets the appropriate attention backend to use. The attention backend setting persists until [`~ModelMixin.reset_attention_backend`] is called.
 
-The example below demonstrates how to enable the `_flash_3_hub` implementation for FlashAttention-3 from the [kernel](https://github.com/huggingface/kernels) library, which allows you to instantly use optimized compute kernels from the Hub without requiring any setup.
+The example below demonstrates how to enable the `_flash_3_hub` implementation for FlashAttention-3 from the [`kernels`](https://github.com/huggingface/kernels) library, which allows you to instantly use optimized compute kernels from the Hub without requiring any setup.
 
 > [!NOTE]
 > FlashAttention-3 is not supported for non-Hopper architectures, in which case, use FlashAttention with `set_attention_backend("flash")`.
@@ -138,11 +139,16 @@ Refer to the table below for a complete list of available attention backends and
 | `_native_npu` | [PyTorch native](https://docs.pytorch.org/docs/stable/generated/torch.nn.attention.SDPBackend.html#torch.nn.attention.SDPBackend) | NPU-optimized attention |
 | `_native_xla` | [PyTorch native](https://docs.pytorch.org/docs/stable/generated/torch.nn.attention.SDPBackend.html#torch.nn.attention.SDPBackend) | XLA-optimized attention |
 | `flash` | [FlashAttention](https://github.com/Dao-AILab/flash-attention) | FlashAttention-2 |
+| `flash_hub` | [FlashAttention](https://github.com/Dao-AILab/flash-attention) | FlashAttention-2 from kernels |
 | `flash_varlen` | [FlashAttention](https://github.com/Dao-AILab/flash-attention) | Variable length FlashAttention |
+| `flash_varlen_hub` | [FlashAttention](https://github.com/Dao-AILab/flash-attention) | Variable length FlashAttention from kernels |
+| `aiter` | [AI Tensor Engine for ROCm](https://github.com/ROCm/aiter) | FlashAttention for AMD ROCm |
 | `_flash_3` | [FlashAttention](https://github.com/Dao-AILab/flash-attention) | FlashAttention-3 |
 | `_flash_varlen_3` | [FlashAttention](https://github.com/Dao-AILab/flash-attention) | Variable length FlashAttention-3 |
 | `_flash_3_hub` | [FlashAttention](https://github.com/Dao-AILab/flash-attention) | FlashAttention-3 from kernels |
+| `_flash_3_varlen_hub` | [FlashAttention](https://github.com/Dao-AILab/flash-attention) | Variable length FlashAttention-3 from kernels |
 | `sage` | [SageAttention](https://github.com/thu-ml/SageAttention) | Quantized attention (INT8 QK) |
+| `sage_hub` | [SageAttention](https://github.com/thu-ml/SageAttention) | Quantized attention (INT8 QK) from kernels |
 | `sage_varlen` | [SageAttention](https://github.com/thu-ml/SageAttention) | Variable length SageAttention |
 | `_sage_qk_int8_pv_fp8_cuda` | [SageAttention](https://github.com/thu-ml/SageAttention) | INT8 QK + FP8 PV (CUDA) |
 | `_sage_qk_int8_pv_fp8_cuda_sm90` | [SageAttention](https://github.com/thu-ml/SageAttention) | INT8 QK + FP8 PV (SM90) |
@@ -150,4 +156,4 @@ Refer to the table below for a complete list of available attention backends and
 | `_sage_qk_int8_pv_fp16_triton` | [SageAttention](https://github.com/thu-ml/SageAttention) | INT8 QK + FP16 PV (Triton) |
 | `xformers` | [xFormers](https://github.com/facebookresearch/xformers) | Memory-efficient attention |
 
-</details>
+</details>

docs/source/en/optimization/cache.md

@@ -66,4 +66,35 @@ config = FasterCacheConfig(
     tensor_format="BFCHW",
 )
 pipeline.transformer.enable_cache(config)
+```
+
+## TaylorSeer Cache
+
+[TaylorSeer Cache](https://huggingface.co/papers/2403.06923) accelerates diffusion inference by using Taylor series expansions to approximate and cache intermediate activations across denoising steps. The method predicts future outputs based on past computations, reusing them at specified intervals to reduce redundant calculations.
+
+This caching mechanism delivers strong results with minimal additional memory overhead. For detailed performance analysis, see [our findings here](https://github.com/huggingface/diffusers/pull/12648#issuecomment-3610615080).
+
+To enable TaylorSeer Cache, create a [`TaylorSeerCacheConfig`] and pass it to your pipeline's transformer:
+
+- `cache_interval`: Number of steps to reuse cached outputs before performing a full forward pass
+- `disable_cache_before_step`: Initial steps that use full computations to gather data for approximations
+- `max_order`: Approximation accuracy (in theory, higher values improve quality but increase memory usage but we recommend it should be set to `1`)
+
+```python
+import torch
+from diffusers import FluxPipeline, TaylorSeerCacheConfig
+
+pipe = FluxPipeline.from_pretrained(
+    "black-forest-labs/FLUX.1-dev",
+    torch_dtype=torch.bfloat16,
+)
+pipe.to("cuda")
+
+config = TaylorSeerCacheConfig(
+    cache_interval=5,
+    max_order=1,
+    disable_cache_before_step=10,
+    taylor_factors_dtype=torch.bfloat16,
+)
+pipe.transformer.enable_cache(config)
 ```

docs/source/en/quantization/modelopt.md

@@ -11,7 +11,7 @@ specific language governing permissions and limitations under the License. -->
 
 # NVIDIA ModelOpt
 
-[NVIDIA-ModelOpt](https://github.com/NVIDIA/TensorRT-Model-Optimizer) is a unified library of state-of-the-art model optimization techniques like quantization, pruning, distillation, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM or TensorRT to optimize inference speed.
+[NVIDIA-ModelOpt](https://github.com/NVIDIA/Model-Optimizer) is a unified library of state-of-the-art model optimization techniques like quantization, pruning, distillation, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM or TensorRT to optimize inference speed.
 
 Before you begin, make sure you have nvidia_modelopt installed.
 
@@ -57,7 +57,7 @@ image.save("output.png")
 >
 > The quantization methods in NVIDIA-ModelOpt are designed to reduce the memory footprint of model weights using various QAT (Quantization-Aware Training) and PTQ (Post-Training Quantization) techniques while maintaining model performance. However, the actual performance gain during inference depends on the deployment framework (e.g., TRT-LLM, TensorRT) and the specific hardware configuration.  
 > 
-> More details can be found [here](https://github.com/NVIDIA/TensorRT-Model-Optimizer/tree/main/examples).
+> More details can be found [here](https://github.com/NVIDIA/Model-Optimizer/tree/main/examples).
 
 ## NVIDIAModelOptConfig
 
@@ -86,7 +86,7 @@ The quantization methods supported are as follows:
 | **NVFP4** | `nvfp4 weight only`, `nvfp4 block quantization` | `quant_type`, `quant_type + channel_quantize + block_quantize` | `channel_quantize = -1 is only supported for now`|
 
 
-Refer to the [official modelopt documentation](https://nvidia.github.io/TensorRT-Model-Optimizer/) for a better understanding of the available quantization methods and the exhaustive list of configuration options available.
+Refer to the [official modelopt documentation](https://nvidia.github.io/Model-Optimizer/) for a better understanding of the available quantization methods and the exhaustive list of configuration options available.
 
 ## Serializing and Deserializing quantized models
 

docs/source/en/quantization/torchao.md

@@ -33,7 +33,7 @@ pipeline_quant_config = PipelineQuantizationConfig(
 )
 pipeline = DiffusionPipeline.from_pretrained(
     "black-forest-labs/FLUX.1-dev",
-    quantzation_config=pipeline_quant_config,
+    quantization_config=pipeline_quant_config,
     torch_dtype=torch.bfloat16,
     device_map="cuda"
 )
@@ -50,7 +50,7 @@ pipeline_quant_config = PipelineQuantizationConfig(
 )
 pipeline = DiffusionPipeline.from_pretrained(
     "black-forest-labs/FLUX.1-dev",
-    quantzation_config=pipeline_quant_config,
+    quantization_config=pipeline_quant_config,
     torch_dtype=torch.bfloat16,
     device_map="cuda"
 )
@@ -70,7 +70,7 @@ pipeline_quant_config = PipelineQuantizationConfig(
 )
 pipeline = DiffusionPipeline.from_pretrained(
     "black-forest-labs/FLUX.1-dev",
-    quantzation_config=pipeline_quant_config,
+    quantization_config=pipeline_quant_config,
     torch_dtype=torch.bfloat16,
     device_map="cuda"
 )

docs/source/en/training/distributed_inference.md

@@ -237,6 +237,8 @@ By selectively loading and unloading the models you need at a given stage and sh
 
 Use [`~ModelMixin.set_attention_backend`] to switch to a more optimized attention backend. Refer to this [table](../optimization/attention_backends#available-backends) for a complete list of available backends.
 
+Most attention backends are compatible with context parallelism. Open an [issue](https://github.com/huggingface/diffusers/issues/new) if a backend is not compatible.
+
 ### Ring Attention
 
 Key (K) and value (V) representations communicate between devices using [Ring Attention](https://huggingface.co/papers/2310.01889). This ensures each split sees every other token's K/V. Each GPU computes attention for its local K/V and passes it to the next GPU in the ring. No single GPU holds the full sequence, which reduces communication latency.
@@ -245,38 +247,58 @@ Pass a [`ContextParallelConfig`] to the `parallel_config` argument of the transf
 
 ```py
 import torch
-from diffusers import AutoModel, QwenImagePipeline, ContextParallelConfig
+from torch import distributed as dist
+from diffusers import DiffusionPipeline, ContextParallelConfig
 
-try:
-    torch.distributed.init_process_group("nccl")
-    rank = torch.distributed.get_rank()
-    device = torch.device("cuda", rank % torch.cuda.device_count())
+def setup_distributed():
+    if not dist.is_initialized():
+        dist.init_process_group(backend="nccl")
+    rank = dist.get_rank()
+    device = torch.device(f"cuda:{rank}")
     torch.cuda.set_device(device)
-    
-    transformer = AutoModel.from_pretrained("Qwen/Qwen-Image", subfolder="transformer", torch_dtype=torch.bfloat16, parallel_config=ContextParallelConfig(ring_degree=2))
-    pipeline = QwenImagePipeline.from_pretrained("Qwen/Qwen-Image", transformer=transformer, torch_dtype=torch.bfloat16, device_map="cuda")
-    pipeline.transformer.set_attention_backend("flash")
+    return device
+
+def main():
+    device = setup_distributed()
+    world_size = dist.get_world_size()
+
+    pipeline = DiffusionPipeline.from_pretrained(
+        "black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16
+    ).to(device)
+    pipeline.transformer.set_attention_backend("_native_cudnn")
+
+    cp_config = ContextParallelConfig(ring_degree=world_size)
+    pipeline.transformer.enable_parallelism(config=cp_config)
 
     prompt = """
     cinematic film still of a cat sipping a margarita in a pool in Palm Springs, California
     highly detailed, high budget hollywood movie, cinemascope, moody, epic, gorgeous, film grain
     """
-    
+
     # Must specify generator so all ranks start with same latents (or pass your own)
     generator = torch.Generator().manual_seed(42)
-    image = pipeline(prompt, num_inference_steps=50, generator=generator).images[0]
-    
-    if rank == 0:
-        image.save("output.png")
+    image = pipeline(
+        prompt,
+        guidance_scale=3.5,
+        num_inference_steps=50,
+        generator=generator,
+    ).images[0]
 
-except Exception as e:
-    print(f"An error occurred: {e}")
-    torch.distributed.breakpoint()
-    raise
+    if dist.get_rank() == 0:
+        image.save(f"output.png")
 
-finally:
-    if torch.distributed.is_initialized():
-        torch.distributed.destroy_process_group()
+    if dist.is_initialized():
+        dist.destroy_process_group()
+
+
+if __name__ == "__main__":
+    main()
+```
+
+The script above needs to be run with a distributed launcher, such as [torchrun](https://docs.pytorch.org/docs/stable/elastic/run.html), that is compatible with PyTorch. `--nproc-per-node` is set to the number of GPUs available.
+
+```shell
+torchrun --nproc-per-node 2 above_script.py
 ```
 
 ### Ulysses Attention
@@ -288,5 +310,26 @@ finally:
 Pass the [`ContextParallelConfig`] to [`~ModelMixin.enable_parallelism`].
 
 ```py
+# Depending on the number of GPUs available.
 pipeline.transformer.enable_parallelism(config=ContextParallelConfig(ulysses_degree=2))
-```
+```
+
+### parallel_config
+
+Pass `parallel_config` during model initialization to enable context parallelism.
+
+```py
+CKPT_ID = "black-forest-labs/FLUX.1-dev"
+
+cp_config = ContextParallelConfig(ring_degree=2)
+transformer = AutoModel.from_pretrained(
+    CKPT_ID, 
+    subfolder="transformer", 
+    torch_dtype=torch.bfloat16, 
+    parallel_config=cp_config
+)
+
+pipeline = DiffusionPipeline.from_pretrained(
+    CKPT_ID, transformer=transformer, torch_dtype=torch.bfloat16,
+).to(device)
+```

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

@@ -0,0 +1,46 @@
+<!--Copyright 2025 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License.
+-->
+
+# AutoModel
+
+The [`AutoModel`] class automatically detects and loads the correct model class (UNet, transformer, VAE) from a `config.json` file. You don't need to know the specific model class name ahead of time. It supports data types and device placement, and works across model types and libraries.
+
+The example below loads a transformer from Diffusers and a text encoder from Transformers. Use the `subfolder` parameter to specify where to load the `config.json` file from.
+
+```py
+import torch
+from diffusers import AutoModel, DiffusionPipeline
+
+transformer = AutoModel.from_pretrained(
+    "Qwen/Qwen-Image", subfolder="transformer", torch_dtype=torch.bfloat16, device_map="cuda"
+)
+
+text_encoder = AutoModel.from_pretrained(
+    "Qwen/Qwen-Image", subfolder="text_encoder", torch_dtype=torch.bfloat16, device_map="cuda"
+)
+```
+
+[`AutoModel`] also loads models from the [Hub](https://huggingface.co/models) that aren't included in Diffusers. Set `trust_remote_code=True` in [`AutoModel.from_pretrained`] to load custom models.
+
+```py
+import torch
+from diffusers import AutoModel
+
+transformer = AutoModel.from_pretrained(
+    "custom/custom-transformer-model", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map="cuda"
+)
+```
+
+If the custom model inherits from the [`ModelMixin`] class, it gets access to the same features as Diffusers model classes, like [regional compilation](../optimization/fp16#regional-compilation) and [group offloading](../optimization/memory#group-offloading).
+
+> [!NOTE]
+> Learn more about implementing custom models in the [Community components](../using-diffusers/custom_pipeline_overview#community-components) guide.

docs/source/pt/_toctree.yml

@@ -1,8 +1,10 @@
 - sections:
-    - local: index
-      title: 🧨 Diffusers
-    - local: quicktour
-      title: Tour rápido
-    - local: installation
-      title: Instalação
+  - local: index
+    title: Diffusers
+  - local: installation
+    title: Instalação
+  - local: quicktour
+    title: Tour rápido
+  - local: stable_diffusion
+    title: Desempenho básico
   title: Primeiros passos

docs/source/pt/index.md

@@ -18,11 +18,11 @@ specific language governing permissions and limitations under the License.
 
 # Diffusers
 
-🤗 Diffusers é uma biblioteca de modelos de difusão de última geração para geração de imagens, áudio e até mesmo estruturas 3D de moléculas. Se você está procurando uma solução de geração simples ou queira treinar seu próprio modelo de difusão, 🤗 Diffusers é uma modular caixa de ferramentas que suporta ambos. Nossa biblioteca é desenhada com foco em [usabilidade em vez de desempenho](conceptual/philosophy#usability-over-performance), [simples em vez de fácil](conceptual/philosophy#simple-over-easy) e [customizável em vez de abstrações](conceptual/philosophy#tweakable-contributorfriendly-over-abstraction).
+🤗 Diffusers é uma biblioteca de modelos de difusão de última geração para geração de imagens, áudio e até mesmo estruturas 3D de moléculas. Se você está procurando uma solução de geração simples ou quer treinar seu próprio modelo de difusão, 🤗 Diffusers é uma caixa de ferramentas modular que suporta ambos. Nossa biblioteca é desenhada com foco em [usabilidade em vez de desempenho](conceptual/philosophy#usability-over-performance), [simples em vez de fácil](conceptual/philosophy#simple-over-easy) e [customizável em vez de abstrações](conceptual/philosophy#tweakable-contributorfriendly-over-abstraction).
 
 A Biblioteca tem três componentes principais:
 
-- Pipelines de última geração para a geração em poucas linhas de código. Têm muitos pipelines no 🤗 Diffusers, veja a tabela no pipeline [Visão geral](api/pipelines/overview) para uma lista completa de pipelines disponíveis e as tarefas que eles resolvem.
+- Pipelines de última geração para a geração em poucas linhas de código. Há muitos pipelines no 🤗 Diffusers, veja a tabela no pipeline [Visão geral](api/pipelines/overview) para uma lista completa de pipelines disponíveis e as tarefas que eles resolvem.
 - Intercambiáveis [agendadores de ruído](api/schedulers/overview) para balancear as compensações entre velocidade e qualidade de geração.
 - [Modelos](api/models) pré-treinados que podem ser usados como se fossem blocos de construção, e combinados com agendadores, para criar seu próprio sistema de difusão de ponta a ponta.
 

docs/source/pt/installation.md

@@ -21,7 +21,7 @@ specific language governing permissions and limitations under the License.
 
 Recomenda-se instalar 🤗 Diffusers em um [ambiente virtual](https://docs.python.org/3/library/venv.html).
 Se você não está familiarizado com ambiente virtuals, veja o [guia](https://packaging.python.org/guides/installing-using-pip-and-virtual-environments/).
-Um ambiente virtual deixa mais fácil gerenciar diferentes projetos e evitar problemas de compatibilidade entre dependências.
+Um ambiente virtual facilita gerenciar diferentes projetos e evitar problemas de compatibilidade entre dependências.
 
 Comece criando um ambiente virtual no diretório do projeto:
 
@@ -100,12 +100,12 @@ pip install -e ".[flax]"
 </jax>
 </frameworkcontent>
 
-Esses comandos irá linkar a pasta que você clonou o repositório e os caminhos das suas bibliotecas Python.
+Esses comandos irão vincular a pasta que você clonou o repositório e os caminhos das suas bibliotecas Python.
 Python então irá procurar dentro da pasta que você clonou além dos caminhos normais das bibliotecas.
 Por exemplo, se o pacote python for tipicamente instalado no `~/anaconda3/envs/main/lib/python3.10/site-packages/`, o Python também irá procurar na pasta `~/diffusers/` que você clonou.
 
 > [!WARNING]
-> Você deve deixar a pasta `diffusers` se você quiser continuar usando a biblioteca.
+> Você deve manter a pasta `diffusers` se quiser continuar usando a biblioteca.
 
 Agora você pode facilmente atualizar seu clone para a última versão do 🤗 Diffusers com o seguinte comando:
 

docs/source/pt/stable_diffusion.md

@@ -0,0 +1,132 @@
+<!--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.
+-->
+
+[[open-in-colab]]
+
+# Desempenho básico
+
+Difusão é um processo aleatório que demanda muito processamento. Você pode precisar executar o [`DiffusionPipeline`] várias vezes antes de obter o resultado desejado. Por isso é importante equilibrar cuidadosamente a velocidade de geração e o uso de memória para iterar mais rápido.
+
+Este guia recomenda algumas dicas básicas de desempenho para usar o [`DiffusionPipeline`]. Consulte a seção de documentação sobre Otimização de Inferência, como [Acelerar inferência](./optimization/fp16) ou [Reduzir uso de memória](./optimization/memory) para guias de desempenho mais detalhados.
+
+## Uso de memória
+
+Reduzir a quantidade de memória usada indiretamente acelera a geração e pode ajudar um modelo a caber no dispositivo.
+
+O método [`~DiffusionPipeline.enable_model_cpu_offload`] move um modelo para a CPU quando não está em uso para economizar memória da GPU.
+
+```py
+import torch
+from diffusers import DiffusionPipeline
+
+pipeline = DiffusionPipeline.from_pretrained(
+  "stabilityai/stable-diffusion-xl-base-1.0",
+  torch_dtype=torch.bfloat16,
+  device_map="cuda"
+)
+pipeline.enable_model_cpu_offload()
+
+prompt = """
+cinematic film still of a cat sipping a margarita in a pool in Palm Springs, California
+highly detailed, high budget hollywood movie, cinemascope, moody, epic, gorgeous, film grain
+"""
+pipeline(prompt).images[0]
+print(f"Memória máxima reservada: {torch.cuda.max_memory_allocated() / 1024**3:.2f} GB")
+```
+
+## Velocidade de inferência
+
+O processo de remoção de ruído é o mais exigente computacionalmente durante a difusão. Métodos que otimizam este processo aceleram a velocidade de inferência. Experimente os seguintes métodos para acelerar.
+
+- Adicione `device_map="cuda"` para colocar o pipeline em uma GPU. Colocar um modelo em um acelerador, como uma GPU, aumenta a velocidade porque realiza computações em paralelo.
+- Defina `torch_dtype=torch.bfloat16` para executar o pipeline em meia-precisão. Reduzir a precisão do tipo de dado aumenta a velocidade porque leva menos tempo para realizar computações em precisão mais baixa.
+
+```py
+import torch
+import time
+from diffusers import DiffusionPipeline, DPMSolverMultistepScheduler
+
+pipeline = DiffusionPipeline.from_pretrained(
+  "stabilityai/stable-diffusion-xl-base-1.0",
+  torch_dtype=torch.bfloat16,
+  device_map="cuda"
+)
+```
+
+- Use um agendador mais rápido, como [`DPMSolverMultistepScheduler`], que requer apenas ~20-25 passos.
+- Defina `num_inference_steps` para um valor menor. Reduzir o número de passos de inferência reduz o número total de computações. No entanto, isso pode resultar em menor qualidade de geração.
+
+```py
+pipeline.scheduler = DPMSolverMultistepScheduler.from_config(pipeline.scheduler.config)
+
+prompt = """
+cinematic film still of a cat sipping a margarita in a pool in Palm Springs, California
+highly detailed, high budget hollywood movie, cinemascope, moody, epic, gorgeous, film grain
+"""
+
+start_time = time.perf_counter()
+image = pipeline(prompt).images[0]
+end_time = time.perf_counter()
+
+print(f"Geração de imagem levou {end_time - start_time:.3f} segundos")
+```
+
+## Qualidade de geração
+
+Muitos modelos de difusão modernos entregam imagens de alta qualidade imediatamente. No entanto, você ainda pode melhorar a qualidade de geração experimentando o seguinte.
+
+- Experimente um prompt mais detalhado e descritivo. Inclua detalhes como o meio da imagem, assunto, estilo e estética. Um prompt negativo também pode ajudar, guiando um modelo para longe de características indesejáveis usando palavras como baixa qualidade ou desfocado.
+
+    ```py
+    import torch
+    from diffusers import DiffusionPipeline
+
+    pipeline = DiffusionPipeline.from_pretrained(
+        "stabilityai/stable-diffusion-xl-base-1.0",
+        torch_dtype=torch.bfloat16,
+        device_map="cuda"
+    )
+
+    prompt = """
+    cinematic film still of a cat sipping a margarita in a pool in Palm Springs, California
+    highly detailed, high budget hollywood movie, cinemascope, moody, epic, gorgeous, film grain
+    """
+    negative_prompt = "low quality, blurry, ugly, poor details"
+    pipeline(prompt, negative_prompt=negative_prompt).images[0]
+    ```
+
+    Para mais detalhes sobre como criar prompts melhores, consulte a documentação sobre [Técnicas de prompt](./using-diffusers/weighted_prompts).
+
+- Experimente um agendador diferente, como [`HeunDiscreteScheduler`] ou [`LMSDiscreteScheduler`], que sacrifica velocidade de geração por qualidade.
+
+    ```py
+    import torch
+    from diffusers import DiffusionPipeline, HeunDiscreteScheduler
+
+    pipeline = DiffusionPipeline.from_pretrained(
+        "stabilityai/stable-diffusion-xl-base-1.0",
+        torch_dtype=torch.bfloat16,
+        device_map="cuda"
+    )
+    pipeline.scheduler = HeunDiscreteScheduler.from_config(pipeline.scheduler.config)
+
+    prompt = """
+    cinematic film still of a cat sipping a margarita in a pool in Palm Springs, California
+    highly detailed, high budget hollywood movie, cinemascope, moody, epic, gorgeous, film grain
+    """
+    negative_prompt = "low quality, blurry, ugly, poor details"
+    pipeline(prompt, negative_prompt=negative_prompt).images[0]
+    ```
+
+## Próximos passos
+
+Diffusers oferece otimizações mais avançadas e poderosas, como [group-offloading](./optimization/memory#group-offloading) e [compilação regional](./optimization/fp16#regional-compilation). Para saber mais sobre como maximizar o desempenho, consulte a seção sobre Otimização de Inferência.

docs/source/zh/modular_diffusers/guiders.md

@@ -157,7 +157,7 @@ guider.push_to_hub("YiYiXu/modular-loader-t2i-guider", subfolder="pag_guider")
 ```py
 guider_spec = t2i_pipeline.get_component_spec("guider")
 guider_spec.default_creation_method="from_pretrained"
-guider_spec.repo="YiYiXu/modular-loader-t2i-guider"
+guider_spec.pretrained_model_name_or_path="YiYiXu/modular-loader-t2i-guider"
 guider_spec.subfolder="pag_guider"
 pag_guider = guider_spec.load()
 t2i_pipeline.update_components(guider=pag_guider)

docs/source/zh/modular_diffusers/modular_pipeline.md

@@ -313,14 +313,14 @@ unet_spec
 ComponentSpec(
     name='unet',
     type_hint=<class 'diffusers.models.unets.unet_2d_condition.UNet2DConditionModel'>,
-    repo='RunDiffusion/Juggernaut-XL-v9',
+    pretrained_model_name_or_path='RunDiffusion/Juggernaut-XL-v9',
     subfolder='unet',
     variant='fp16',
     default_creation_method='from_pretrained'
 )
 
 # 修改以从不同的仓库加载
-unet_spec.repo = "stabilityai/stable-diffusion-xl-base-1.0"
+unet_spec.pretrained_model_name_or_path = "stabilityai/stable-diffusion-xl-base-1.0"
 
 # 使用修改后的规范加载组件
 unet = unet_spec.load(torch_dtype=torch.float16)

examples/advanced_diffusion_training/train_dreambooth_lora_flux_advanced.py

@@ -94,7 +94,7 @@ if is_wandb_available():
     import wandb
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.36.0.dev0")
+check_min_version("0.37.0.dev0")
 
 logger = get_logger(__name__)