update

2024-03-12 13:08:23 +00:00 · 2024-03-12 13:04:25 +00:00 · 2024-03-12 08:52:55 +00:00 · 2024-03-12 05:41:37 +00:00
381 changed files with 4145 additions and 17980 deletions
@@ -12,345 +12,106 @@ env:
  PYTEST_TIMEOUT: 600
  RUN_SLOW: yes
  RUN_NIGHTLY: yes
-  PIPELINE_USAGE_CUTOFF: 5000
-  SLACK_API_TOKEN: ${{ secrets.SLACK_CIFEEDBACK_BOT_TOKEN }}

 jobs:
-  setup_torch_cuda_pipeline_matrix:
-    name: Setup Torch Pipelines Matrix
-    runs-on: ubuntu-latest
-    outputs:
-      pipeline_test_matrix: ${{ steps.fetch_pipeline_matrix.outputs.pipeline_test_matrix }}
-    steps:
-      - name: Checkout diffusers
-        uses: actions/checkout@v3
-        with:
-          fetch-depth: 2
-      - name: Set up Python
-        uses: actions/setup-python@v4
-        with:
-          python-version: "3.8"
-      - name: Install dependencies
-        run: |
-          pip install -e .
-          pip install huggingface_hub
-      - name: Fetch Pipeline Matrix
-        id: fetch_pipeline_matrix
-        run: |
-          matrix=$(python utils/fetch_torch_cuda_pipeline_test_matrix.py)
-          echo $matrix
-          echo "pipeline_test_matrix=$matrix" >> $GITHUB_OUTPUT
-
-      - name: Pipeline Tests Artifacts
-        if: ${{ always() }}
-        uses: actions/upload-artifact@v2
-        with:
-          name: test-pipelines.json
-          path: reports
-
-  run_nightly_tests_for_torch_pipelines:
-    name: Torch Pipelines CUDA Nightly Tests
-    needs: setup_torch_cuda_pipeline_matrix
+  run_nightly_tests:
    strategy:
      fail-fast: false
      matrix:
-        module: ${{ fromJson(needs.setup_torch_cuda_pipeline_matrix.outputs.pipeline_test_matrix) }}
-    runs-on: [single-gpu, nvidia-gpu, t4, ci]
+        config:
+          - name: Nightly PyTorch CUDA tests on Ubuntu
+            framework: pytorch
+            runner: docker-gpu
+            image: diffusers/diffusers-pytorch-cuda
+            report: torch_cuda
+          - name: Nightly Flax TPU tests on Ubuntu
+            framework: flax
+            runner: docker-tpu
+            image: diffusers/diffusers-flax-tpu
+            report: flax_tpu
+          - name: Nightly ONNXRuntime CUDA tests on Ubuntu
+            framework: onnxruntime
+            runner: docker-gpu
+            image: diffusers/diffusers-onnxruntime-cuda
+            report: onnx_cuda
+
+    name: ${{ matrix.config.name }}
+
+    runs-on: ${{ matrix.config.runner }}
+
    container:
-      image: diffusers/diffusers-pytorch-cuda
-      options: --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/ --gpus 0
+      image: ${{ matrix.config.image }}
+      options: --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/ ${{ matrix.config.runner == 'docker-tpu' && '--privileged' || '--gpus 0'}}
+
+    defaults:
+      run:
+        shell: bash
+
    steps:
      - name: Checkout diffusers
        uses: actions/checkout@v3
        with:
          fetch-depth: 2
+
      - name: NVIDIA-SMI
-        run: nvidia-smi
-      
+        if: ${{ matrix.config.runner == 'docker-gpu' }}
+        run: |
+          nvidia-smi
+
      - name: Install dependencies
        run: |
-          apt-get update && apt-get install libsndfile1-dev libgl1 -y
          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
          python -m uv pip install -e [quality,test]
-          python -m uv pip install accelerate@git+https://github.com/huggingface/accelerate.git
-          python -m uv pip install pytest-reportlog
-      
+          python -m uv pip install -U transformers@git+https://github.com/huggingface/transformers
+          python -m uv pip install accelerate@git+https://github.com/huggingface/accelerate
+
      - name: Environment
        run: |
          python utils/print_env.py
-      
-      - name: Nightly PyTorch CUDA checkpoint (pipelines) tests 
+
+      - name: Run nightly PyTorch CUDA tests
+        if: ${{ matrix.config.framework == 'pytorch' }}
        env:
          HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
-          # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
-          CUBLAS_WORKSPACE_CONFIG: :16:8
        run: |
+          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
          python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
            -s -v -k "not Flax and not Onnx" \
-            --make-reports=tests_pipeline_${{ matrix.module }}_cuda \
-            --report-log=tests_pipeline_${{ matrix.module }}_cuda.log \ 
-            tests/pipelines/${{ matrix.module }}
-      
+            --make-reports=tests_${{ matrix.config.report }} \
+            tests/
+
+      - name: Run nightly Flax TPU tests
+        if: ${{ matrix.config.framework == 'flax' }}
+        env:
+          HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
+        run: |
+          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+          python -m pytest -n 0 \
+            -s -v -k "Flax" \
+            --make-reports=tests_${{ matrix.config.report }} \
+            tests/
+
+      - name: Run nightly ONNXRuntime CUDA tests
+        if: ${{ matrix.config.framework == 'onnxruntime' }}
+        env:
+          HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
+        run: |
+          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+          python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
+            -s -v -k "Onnx" \
+            --make-reports=tests_${{ matrix.config.report }} \
+            tests/
+
      - name: Failure short reports
        if: ${{ failure() }}
-        run: |
-          cat reports/tests_pipeline_${{ matrix.module }}_cuda_stats.txt
-          cat reports/tests_pipeline_${{ matrix.module }}_cuda_failures_short.txt
+        run: cat reports/tests_${{ matrix.config.report }}_failures_short.txt

      - name: Test suite reports artifacts
        if: ${{ always() }}
        uses: actions/upload-artifact@v2
        with:
-          name: pipeline_${{ matrix.module }}_test_reports
+          name: ${{ matrix.config.report }}_test_reports
          path: reports
-      
-      - name: Generate Report and Notify Channel
-        if: always()
-        run: |
-          pip install slack_sdk tabulate
-          python scripts/log_reports.py >> $GITHUB_STEP_SUMMARY
-
-  run_nightly_tests_for_other_torch_modules:
-    name: Torch Non-Pipelines CUDA Nightly Tests
-    runs-on: docker-gpu
-    container:
-      image: diffusers/diffusers-pytorch-cuda
-      options: --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/ --gpus 0
-    defaults:
-      run:
-        shell: bash
-    strategy:
-      matrix:
-        module: [models, schedulers, others, examples]
-    steps:
-    - name: Checkout diffusers
-      uses: actions/checkout@v3
-      with:
-        fetch-depth: 2
-
-    - name: Install dependencies
-      run: |
-        apt-get update && apt-get install libsndfile1-dev libgl1 -y
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m uv pip install -e [quality,test]
-        python -m uv pip install accelerate@git+https://github.com/huggingface/accelerate.git
-        python -m uv pip install pytest-reportlog
-
-    - name: Environment
-      run: python utils/print_env.py
-
-    - name: Run nightly PyTorch CUDA tests for non-pipeline modules
-      if: ${{ matrix.module != 'examples'}} 
-      env:
-        HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
-        # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
-        CUBLAS_WORKSPACE_CONFIG: :16:8
-      run: |
-        python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-          -s -v -k "not Flax and not Onnx" \
-          --make-reports=tests_torch_${{ matrix.module }}_cuda \
-          --report-log=tests_torch_${{ matrix.module }}_cuda.log \ 
-          tests/${{ matrix.module }}
-
-    - name: Run nightly example tests with Torch
-      if: ${{ matrix.module == 'examples' }}
-      env:
-        HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
-        # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
-        CUBLAS_WORKSPACE_CONFIG: :16:8
-      run: |
-        python -m uv pip install peft@git+https://github.com/huggingface/peft.git
-        python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-          -s -v --make-reports=examples_torch_cuda \
-          --report-log=examples_torch_cuda.log \ 
-          examples/
-
-    - name: Failure short reports
-      if: ${{ failure() }}
-      run: |
-        cat reports/tests_torch_${{ matrix.module }}_cuda_stats.txt 
-        cat reports/tests_torch_${{ matrix.module }}_cuda_failures_short.txt
-
-    - name: Test suite reports artifacts
-      if: ${{ always() }}
-      uses: actions/upload-artifact@v2
-      with:
-        name: torch_${{ matrix.module }}_cuda_test_reports
-        path: reports
-
-    - name: Generate Report and Notify Channel
-      if: always()
-      run: |
-        pip install slack_sdk tabulate
-        python scripts/log_reports.py >> $GITHUB_STEP_SUMMARY
-
-  run_lora_nightly_tests:
-    name: Nightly LoRA Tests with PEFT and TORCH
-    runs-on: docker-gpu
-    container:
-      image: diffusers/diffusers-pytorch-cuda
-      options: --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/ --gpus 0
-    defaults:
-      run:
-        shell: bash
-    steps:
-    - name: Checkout diffusers
-      uses: actions/checkout@v3
-      with:
-        fetch-depth: 2
-
-    - name: Install dependencies
-      run: |
-        apt-get update && apt-get install libsndfile1-dev libgl1 -y
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m uv pip install -e [quality,test]
-        python -m uv pip install accelerate@git+https://github.com/huggingface/accelerate.git
-        python -m uv pip install peft@git+https://github.com/huggingface/peft.git
-        python -m uv pip install pytest-reportlog
-
-    - name: Environment
-      run: python utils/print_env.py
-
-    - name: Run nightly LoRA tests with PEFT and Torch
-      env:
-        HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
-        # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
-        CUBLAS_WORKSPACE_CONFIG: :16:8
-      run: |
-        python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-          -s -v -k "not Flax and not Onnx" \
-          --make-reports=tests_torch_lora_cuda \
-          --report-log=tests_torch_lora_cuda.log \ 
-          tests/lora
-    
-    - name: Failure short reports
-      if: ${{ failure() }}
-      run: |
-        cat reports/tests_torch_lora_cuda_stats.txt 
-        cat reports/tests_torch_lora_cuda_failures_short.txt
-
-    - name: Test suite reports artifacts
-      if: ${{ always() }}
-      uses: actions/upload-artifact@v2
-      with:
-        name: torch_lora_cuda_test_reports
-        path: reports
-
-    - name: Generate Report and Notify Channel
-      if: always()
-      run: |
-        pip install slack_sdk tabulate
-        python scripts/log_reports.py >> $GITHUB_STEP_SUMMARY
-  
-  run_flax_tpu_tests:
-    name: Nightly Flax TPU Tests
-    runs-on: docker-tpu
-    container:
-      image: diffusers/diffusers-flax-tpu
-      options: --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/ --privileged
-    defaults:
-      run:
-        shell: bash
-    steps:
-    - name: Checkout diffusers
-      uses: actions/checkout@v3
-      with:
-        fetch-depth: 2
-
-    - name: Install dependencies
-      run: |
-        apt-get update && apt-get install libsndfile1-dev libgl1 -y
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m uv pip install -e [quality,test]
-        python -m uv pip install accelerate@git+https://github.com/huggingface/accelerate.git
-        python -m uv pip install pytest-reportlog
-
-    - name: Environment
-      run: python utils/print_env.py
-
-    - name: Run nightly Flax TPU tests
-      env:
-        HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
-      run: |
-        python -m pytest -n 0 \
-          -s -v -k "Flax" \
-          --make-reports=tests_flax_tpu \
-          --report-log=tests_flax_tpu.log \ 
-          tests/
-
-    - name: Failure short reports
-      if: ${{ failure() }}
-      run: |
-        cat reports/tests_flax_tpu_stats.txt
-        cat reports/tests_flax_tpu_failures_short.txt
-
-    - name: Test suite reports artifacts
-      if: ${{ always() }}
-      uses: actions/upload-artifact@v2
-      with:
-        name: flax_tpu_test_reports
-        path: reports
-
-    - name: Generate Report and Notify Channel
-      if: always()
-      run: |
-        pip install slack_sdk tabulate
-        python scripts/log_reports.py >> $GITHUB_STEP_SUMMARY
-
-  run_nightly_onnx_tests:
-    name: Nightly ONNXRuntime CUDA tests on Ubuntu
-    runs-on: docker-gpu
-    container:
-      image: diffusers/diffusers-onnxruntime-cuda
-      options: --gpus 0 --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/
-    
-    steps:
-    - name: Checkout diffusers
-      uses: actions/checkout@v3
-      with:
-        fetch-depth: 2
-
-    - name: NVIDIA-SMI
-      run: nvidia-smi
-
-    - name: Install dependencies
-      run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m uv pip install -e [quality,test]
-        python -m uv pip install accelerate@git+https://github.com/huggingface/accelerate.git
-        python -m uv pip install pytest-reportlog
-
-    - name: Environment
-      run: python utils/print_env.py
-    
-    - name: Run nightly ONNXRuntime CUDA tests
-      env:
-        HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
-      run: |
-        python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-          -s -v -k "Onnx" \
-          --make-reports=tests_onnx_cuda \
-          --report-log=tests_onnx_cuda.log \ 
-          tests/
-
-    - name: Failure short reports
-      if: ${{ failure() }}
-      run: |
-        cat reports/tests_onnx_cuda_stats.txt
-        cat reports/tests_onnx_cuda_failures_short.txt
-
-    - name: Test suite reports artifacts
-      if: ${{ always() }}
-      uses: actions/upload-artifact@v2
-      with:
-        name: ${{ matrix.config.report }}_test_reports
-        path: reports
-    
-    - name: Generate Report and Notify Channel
-      if: always()
-      run: |
-        pip install slack_sdk tabulate
-        python scripts/log_reports.py >> $GITHUB_STEP_SUMMARY

  run_nightly_tests_apple_m1:
    name: Nightly PyTorch MPS tests on MacOS
@@ -379,7 +140,6 @@ jobs:
          ${CONDA_RUN} python -m uv pip install -e [quality,test]
          ${CONDA_RUN} python -m uv pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cpu
          ${CONDA_RUN} python -m uv pip install accelerate@git+https://github.com/huggingface/accelerate
-          ${CONDA_RUN} python -m uv pip install pytest-reportlog

      - name: Environment
        shell: arch -arch arm64 bash {0}
@@ -392,9 +152,7 @@ jobs:
          HF_HOME: /System/Volumes/Data/mnt/cache
          HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
        run: |
-          ${CONDA_RUN} python -m pytest -n 1 -s -v --make-reports=tests_torch_mps \
-            --report-log=tests_torch_mps.log \
-            tests/
+          ${CONDA_RUN} python -m pytest -n 1 -s -v --make-reports=tests_torch_mps tests/

      - name: Failure short reports
        if: ${{ failure() }}
@@ -406,9 +164,3 @@ jobs:
        with:
          name: torch_mps_test_reports
          path: reports
-
-      - name: Generate Report and Notify Channel
-        if: always()
-        run: |
-          pip install slack_sdk tabulate
-          python scripts/log_reports.py >> $GITHUB_STEP_SUMMARY
@@ -1,23 +0,0 @@
-name: Notify Slack about a release
-
-on:
-  workflow_dispatch:
-  release:
-    types: [published]
-
-jobs:
-  build:
-    runs-on: ubuntu-latest
-
-    steps:
-    - uses: actions/checkout@v3
-    
-    - name: Setup Python
-      uses: actions/setup-python@v4
-      with:
-        python-version: '3.8'
-    
-    - name: Notify Slack about the release
-      env:
-        SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL }}
-      run: pip install requests && python utils/notify_slack_about_release.py
@@ -35,10 +35,6 @@ jobs:
        run: |
          ruff check examples tests src utils scripts
          ruff format examples tests src utils scripts --check
-      - name: Check if failure
-        if: ${{ failure() }}
-        run: |
-          echo "Quality check failed. Please ensure the right dependency versions are installed with 'pip install -e .[quality]' and run 'make style && make quality'" >> $GITHUB_STEP_SUMMARY

  check_repository_consistency:
    needs: check_code_quality
@@ -58,10 +54,6 @@ jobs:
          python utils/check_copies.py
          python utils/check_dummies.py
          make deps_table_check_updated
-      - name: Check if failure
-        if: ${{ failure() }}
-        run: |
-          echo "Repo consistency check failed. Please ensure the right dependency versions are installed with 'pip install -e .[quality]' and run 'make fix-copies'" >> $GITHUB_STEP_SUMMARY

  run_fast_tests:
    needs: [check_code_quality, check_repository_consistency]
@@ -113,4 +105,4 @@ jobs:
        python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
          -s -v \
          --make-reports=tests_${{ matrix.config.report }} \
-          tests/lora/
+          tests/lora/test_lora_layers_peft.py
@@ -43,10 +43,6 @@ jobs:
        run: |
          ruff check examples tests src utils scripts
          ruff format examples tests src utils scripts --check
-      - name: Check if failure
-        if: ${{ failure() }}
-        run: |
-          echo "Quality check failed. Please ensure the right dependency versions are installed with 'pip install -e .[quality]' and run 'make style && make quality'" >> $GITHUB_STEP_SUMMARY

  check_repository_consistency:
    needs: check_code_quality
@@ -66,10 +62,6 @@ jobs:
          python utils/check_copies.py
          python utils/check_dummies.py
          make deps_table_check_updated
-      - name: Check if failure
-        if: ${{ failure() }}
-        run: |
-          echo "Repo consistency check failed. Please ensure the right dependency versions are installed with 'pip install -e .[quality]' and run 'make fix-copies'" >> $GITHUB_STEP_SUMMARY

  run_fast_tests:
    needs: [check_code_quality, check_repository_consistency]
@@ -21,7 +21,10 @@ env:
 jobs:
  setup_torch_cuda_pipeline_matrix:
    name: Setup Torch Pipelines CUDA Slow Tests Matrix
-    runs-on: ubuntu-latest
+    runs-on: [single-gpu, nvidia-gpu, t4, ci]
+    container:
+      image: diffusers/diffusers-pytorch-cpu # this is a CPU image, but we need it to fetch the matrix
+      options: --shm-size "16gb" --ipc host
    outputs:
      pipeline_test_matrix: ${{ steps.fetch_pipeline_matrix.outputs.pipeline_test_matrix }}
    steps:
@@ -29,20 +32,24 @@ jobs:
        uses: actions/checkout@v3
        with:
          fetch-depth: 2
-      - name: Set up Python
-        uses: actions/setup-python@v4
-        with:
-          python-version: "3.8"
      - name: Install dependencies
        run: |
-          pip install -e .
-          pip install huggingface_hub
+          apt-get update && apt-get install libsndfile1-dev libgl1 -y
+          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+          python -m uv pip install -e [quality,test]
+          python -m uv pip install accelerate@git+https://github.com/huggingface/accelerate.git
+
+      - name: Environment
+        run: |
+          python utils/print_env.py
+
      - name: Fetch Pipeline Matrix
        id: fetch_pipeline_matrix
        run: |
          matrix=$(python utils/fetch_torch_cuda_pipeline_test_matrix.py)
          echo $matrix
          echo "pipeline_test_matrix=$matrix" >> $GITHUB_OUTPUT
+
      - name: Pipeline Tests Artifacts
        if: ${{ always() }}
        uses: actions/upload-artifact@v2
@@ -1,81 +0,0 @@
-# Adapted from https://blog.deepjyoti30.dev/pypi-release-github-action
-
-name: PyPI release
-
-on:
-  workflow_dispatch:
-  push:
-    tags:
-      - "*"
-
-jobs:
-  find-and-checkout-latest-branch:
-    runs-on: ubuntu-latest
-    outputs:
-      latest_branch: ${{ steps.set_latest_branch.outputs.latest_branch }}
-    steps:
-      - name: Checkout Repo
-        uses: actions/checkout@v3
-
-      - name: Set up Python
-        uses: actions/setup-python@v4
-        with:
-          python-version: '3.8'
-
-      - name: Fetch latest branch
-        id: fetch_latest_branch
-        run: |
-          pip install -U requests packaging
-          LATEST_BRANCH=$(python utils/fetch_latest_release_branch.py)
-          echo "Latest branch: $LATEST_BRANCH"
-          echo "latest_branch=$LATEST_BRANCH" >> $GITHUB_ENV
-          
-      - name: Set latest branch output
-        id: set_latest_branch
-        run: echo "::set-output name=latest_branch::${{ env.latest_branch }}"
-
-  release:
-    needs: find-and-checkout-latest-branch
-    runs-on: ubuntu-latest
-
-    steps:
-      - name: Checkout Repo
-        uses: actions/checkout@v3
-        with:
-          ref: ${{ needs.find-and-checkout-latest-branch.outputs.latest_branch }}
-          
-      - name: Setup Python
-        uses: actions/setup-python@v4
-        with:
-          python-version: "3.8"
-      
-      - name: Install dependencies
-        run: |
-          python -m pip install --upgrade pip
-          pip install -U setuptools wheel twine
-          pip install -U torch --index-url https://download.pytorch.org/whl/cpu
-          pip install -U transformers
-      
-      - name: Build the dist files
-        run: python setup.py bdist_wheel && python setup.py sdist
-      
-      - name: Publish to the test PyPI
-        env:
-          TWINE_USERNAME: ${{ secrets.TEST_PYPI_USERNAME }}
-          TWINE_PASSWORD: ${{ secrets.TEST_PYPI_PASSWORD }}
-        run: twine upload dist/* -r pypitest --repository-url=https://test.pypi.org/legacy/    
-
-      - name: Test installing diffusers and importing
-        run: |
-          pip install diffusers && pip uninstall diffusers -y
-          pip install -i https://testpypi.python.org/pypi diffusers
-          python -c "from diffusers import __version__; print(__version__)"
-          python -c "from diffusers import DiffusionPipeline; pipe = DiffusionPipeline.from_pretrained('fusing/unet-ldm-dummy-update'); pipe()"
-          python -c "from diffusers import DiffusionPipeline; pipe = DiffusionPipeline.from_pretrained('hf-internal-testing/tiny-stable-diffusion-pipe', safety_checker=None); pipe('ah suh du')"
-          python -c "from diffusers import *"
-
-      - name: Publish to PyPI
-        env:
-          TWINE_USERNAME: ${{ secrets.PYPI_USERNAME }}
-          TWINE_PASSWORD: ${{ secrets.PYPI_PASSWORD }}
-        run: twine upload dist/* -r pypi
@@ -19,16 +19,6 @@ authors:
    family-names: Rasul
  - given-names: Mishig
    family-names: Davaadorj
-  - given-names: Dhruv
-    family-names: Nair
-  - given-names: Sayak
-    family-names: Paul
-  - given-names: Steven
-    family-names: Liu
-  - given-names: William
-    family-names: Berman
-  - given-names: Yiyi
-    family-names: Xu
  - given-names: Thomas
    family-names: Wolf
 repository-code: 'https://github.com/huggingface/diffusers'
@@ -77,7 +77,7 @@ Please refer to the [How to use Stable Diffusion in Apple Silicon](https://huggi

 ## Quickstart

-Generating outputs is super easy with 🤗 Diffusers. To generate an image from text, use the `from_pretrained` method to load any pretrained diffusion model (browse the [Hub](https://huggingface.co/models?library=diffusers&sort=downloads) for 22000+ checkpoints):
+Generating outputs is super easy with 🤗 Diffusers. To generate an image from text, use the `from_pretrained` method to load any pretrained diffusion model (browse the [Hub](https://huggingface.co/models?library=diffusers&sort=downloads) for 19000+ checkpoints):

 ```python
 from diffusers import DiffusionPipeline
@@ -219,7 +219,7 @@ Also, say 👋 in our public Discord channel <a href="https://discord.gg/G7tWnz9
 - https://github.com/deep-floyd/IF
 - https://github.com/bentoml/BentoML
 - https://github.com/bmaltais/kohya_ss
- +9000 other amazing GitHub repositories 💪
+- +8000 other amazing GitHub repositories 💪

 Thank you for using us ❤️.

@@ -238,7 +238,7 @@ We also want to thank @heejkoo for the very helpful overview of papers, code and

 ```bibtex
@misc{von-platen-etal-2022-diffusers,
-  author = {Patrick von Platen and Suraj Patil and Anton Lozhkov and Pedro Cuenca and Nathan Lambert and Kashif Rasul and Mishig Davaadorj and Dhruv Nair and Sayak Paul and William Berman and Yiyi Xu and Steven Liu and Thomas Wolf},
+  author = {Patrick von Platen and Suraj Patil and Anton Lozhkov and Pedro Cuenca and Nathan Lambert and Kashif Rasul and Mishig Davaadorj and Thomas Wolf},
  title = {Diffusers: State-of-the-art diffusion models},
  year = {2022},
  publisher = {GitHub},
@@ -104,8 +104,6 @@
      title: Latent Consistency Model-LoRA
    - local: using-diffusers/inference_with_lcm
      title: Latent Consistency Model
-    - local: using-diffusers/inference_with_tcd_lora
-      title: Trajectory Consistency Distillation-LoRA
    - local: using-diffusers/svd
      title: Stable Video Diffusion
    title: Specific pipeline examples
@@ -306,8 +304,6 @@
      title: Latent Consistency Models
    - local: api/pipelines/latent_diffusion
      title: Latent Diffusion
-    - local: api/pipelines/ledits_pp
-      title: LEDITS++
    - local: api/pipelines/panorama
      title: MultiDiffusion
    - local: api/pipelines/musicldm
@@ -400,10 +396,6 @@
      title: DPMSolverSDEScheduler
    - local: api/schedulers/singlestep_dpm_solver
      title: DPMSolverSinglestepScheduler
-    - local: api/schedulers/edm_multistep_dpm_solver
-      title: EDMDPMSolverMultistepScheduler
-    - local: api/schedulers/edm_euler
-      title: EDMEulerScheduler
    - local: api/schedulers/euler_ancestral
      title: EulerAncestralDiscreteScheduler
    - local: api/schedulers/euler
@@ -408,29 +408,6 @@ Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers)

 </Tip>

-<table>
-    <tr>
-      <th align=center>Without FreeInit enabled</th>
-      <th align=center>With FreeInit enabled</th>
-    </tr>
-    <tr>
-        <td align=center>
-          panda playing a guitar
-          <br />
-          <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/animatediff-no-freeinit.gif"
-              alt="panda playing a guitar"
-              style="width: 300px;" />
-        </td>
-        <td align=center>
-          panda playing a guitar
-          <br/>
-          <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/animatediff-freeinit.gif"
-              alt="panda playing a guitar"
-              style="width: 300px;" />
-        </td>
-    </tr>
-</table>
-
 ## Using AnimateLCM

 [AnimateLCM](https://animatelcm.github.io/) is a motion module checkpoint and an [LCM LoRA](https://huggingface.co/docs/diffusers/using-diffusers/inference_with_lcm_lora) that have been created using a consistency learning strategy that decouples the distillation of the image generation priors and the motion generation priors.
@@ -1,54 +0,0 @@
-<!--Copyright 2023 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.
-->
-
-# LEDITS++
-
-LEDITS++ was proposed in [LEDITS++: Limitless Image Editing using Text-to-Image Models](https://huggingface.co/papers/2311.16711) by Manuel Brack, Felix Friedrich, Katharina Kornmeier, Linoy Tsaban, Patrick Schramowski, Kristian Kersting, Apolinário Passos.
-
-The abstract from the paper is:
-
-*Text-to-image diffusion models have recently received increasing interest for their astonishing ability to produce high-fidelity images from solely text inputs. Subsequent research efforts aim to exploit and apply their capabilities to real image editing. However, existing image-to-image methods are often inefficient, imprecise, and of limited versatility. They either require time-consuming fine-tuning, deviate unnecessarily strongly from the input image, and/or lack support for multiple, simultaneous edits. To address these issues, we introduce LEDITS++, an efficient yet versatile and precise textual image manipulation technique. LEDITS++'s novel inversion approach requires no tuning nor optimization and produces high-fidelity results with a few diffusion steps. Second, our methodology supports multiple simultaneous edits and is architecture-agnostic. Third, we use a novel implicit masking technique that limits changes to relevant image regions. We propose the novel TEdBench++ benchmark as part of our exhaustive evaluation. Our results demonstrate the capabilities of LEDITS++ and its improvements over previous methods. The project page is available at https://leditsplusplus-project.static.hf.space .*
-
-<Tip>
-
-You can find additional information about LEDITS++ on the [project page](https://leditsplusplus-project.static.hf.space/index.html) and try it out in a [demo](https://huggingface.co/spaces/editing-images/leditsplusplus).
-
-</Tip>
-
-<Tip warning={true}>
-Due to some backward compatability issues with the current diffusers implementation of [`~schedulers.DPMSolverMultistepScheduler`] this implementation of LEdits++ can no longer guarantee perfect inversion. 
-This issue is unlikely to have any noticeable effects on applied use-cases. However, we provide an alternative implementation that guarantees perfect inversion in a dedicated [GitHub repo](https://github.com/ml-research/ledits_pp). 
-</Tip>
-
-We provide two distinct pipelines based on different pre-trained models. 
-
-## LEditsPPPipelineStableDiffusion
-[[autodoc]] pipelines.ledits_pp.LEditsPPPipelineStableDiffusion
-	- all
-	- __call__
-	- invert
-
-## LEditsPPPipelineStableDiffusionXL
-[[autodoc]] pipelines.ledits_pp.LEditsPPPipelineStableDiffusionXL
-	- all
-	- __call__
-	- invert
-
-
-
-## LEditsPPDiffusionPipelineOutput
-[[autodoc]] pipelines.ledits_pp.pipeline_output.LEditsPPDiffusionPipelineOutput
-	- all
-
-## LEditsPPInversionPipelineOutput
-[[autodoc]] pipelines.ledits_pp.pipeline_output.LEditsPPInversionPipelineOutput
-	- all
@@ -57,7 +57,6 @@ The table below lists all the pipelines currently available in 🤗 Diffusers an
 | [Latent Consistency Models](latent_consistency_models) | text2image |
 | [Latent Diffusion](latent_diffusion) | text2image, super-resolution |
 | [LDM3D](stable_diffusion/ldm3d_diffusion) | text2image, text-to-3D, text-to-pano, upscaling |
-| [LEDITS++](ledits_pp) | image editing |
 | [MultiDiffusion](panorama) | text2image |
 | [MusicLDM](musicldm) | text2audio |
 | [Paint by Example](paint_by_example) | inpainting |
@@ -30,6 +30,6 @@ Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers)
 	- all
 	- __call__

-## SemanticStableDiffusionPipelineOutput
+## StableDiffusionSafePipelineOutput
 [[autodoc]] pipelines.semantic_stable_diffusion.pipeline_output.SemanticStableDiffusionPipelineOutput
 	- all
@@ -12,13 +12,13 @@ specific language governing permissions and limitations under the License.

 # Stable Cascade

-This model is built upon the [Würstchen](https://openreview.net/forum?id=gU58d5QeGv) architecture and its main
-difference to other models like Stable Diffusion is that it is working at a much smaller latent space. Why is this
-important? The smaller the latent space, the **faster** you can run inference and the **cheaper** the training becomes.
-How small is the latent space? Stable Diffusion uses a compression factor of 8, resulting in a 1024x1024 image being
-encoded to 128x128. Stable Cascade achieves a compression factor of 42, meaning that it is possible to encode a
-1024x1024 image to 24x24, while maintaining crisp reconstructions. The text-conditional model is then trained in the
-highly compressed latent space. Previous versions of this architecture, achieved a 16x cost reduction over Stable
+This model is built upon the [Würstchen](https://openreview.net/forum?id=gU58d5QeGv) architecture and its main 
+difference to other models like Stable Diffusion is that it is working at a much smaller latent space. Why is this 
+important? The smaller the latent space, the **faster** you can run inference and the **cheaper** the training becomes. 
+How small is the latent space? Stable Diffusion uses a compression factor of 8, resulting in a 1024x1024 image being 
+encoded to 128x128. Stable Cascade achieves a compression factor of 42, meaning that it is possible to encode a 
+1024x1024 image to 24x24, while maintaining crisp reconstructions. The text-conditional model is then trained in the 
+highly compressed latent space. Previous versions of this architecture, achieved a 16x cost reduction over Stable 
 Diffusion 1.5.

 Therefore, this kind of model is well suited for usages where efficiency is important. Furthermore, all known extensions
@@ -30,154 +30,13 @@ The original codebase can be found at [Stability-AI/StableCascade](https://githu
 Stable Cascade consists of three models: Stage A, Stage B and Stage C, representing a cascade to generate images,
 hence the name "Stable Cascade".

-Stage A & B are used to compress images, similar to what the job of the VAE is in Stable Diffusion.
-However, with this setup, a much higher compression of images can be achieved. While the Stable Diffusion models use a
-spatial compression factor of 8, encoding an image with resolution of 1024 x 1024 to 128 x 128, Stable Cascade achieves
-a compression factor of 42. This encodes a 1024 x 1024 image to 24 x 24, while being able to accurately decode the
-image. This comes with the great benefit of cheaper training and inference. Furthermore, Stage C is responsible
+Stage A & B are used to compress images, similar to what the job of the VAE is in Stable Diffusion. 
+However, with this setup, a much higher compression of images can be achieved. While the Stable Diffusion models use a 
+spatial compression factor of 8, encoding an image with resolution of 1024 x 1024 to 128 x 128, Stable Cascade achieves 
+a compression factor of 42. This encodes a 1024 x 1024 image to 24 x 24, while being able to accurately decode the 
+image. This comes with the great benefit of cheaper training and inference. Furthermore, Stage C is responsible 
 for generating the small 24 x 24 latents given a text prompt.

-The Stage C model operates on the small 24 x 24 latents and denoises the latents conditioned on text prompts. The model is also the largest component in the Cascade pipeline and is meant to be used with the `StableCascadePriorPipeline`
-
-The Stage B and Stage A models are used with the `StableCascadeDecoderPipeline` and are responsible for generating the final image given the small 24 x 24 latents.
-
-<Tip warning={true}>
-
-There are some restrictions on data types that can be used with the Stable Cascade models. The official checkpoints for the  `StableCascadePriorPipeline` do not support the `torch.float16` data type. Please use `torch.bfloat16` instead.
-
-In order to use the `torch.bfloat16` data type with the `StableCascadeDecoderPipeline` you need to have PyTorch 2.2.0 or higher installed. This also means that using the `StableCascadeCombinedPipeline` with `torch.bfloat16` requires PyTorch 2.2.0 or higher, since it calls the `StableCascadeDecoderPipeline` internally.
-
-If it is not possible to install PyTorch 2.2.0 or higher in your environment, the `StableCascadeDecoderPipeline` can be used on its own with the `torch.float16` data type. You can download the full precision or `bf16` variant weights for the pipeline and cast the weights to `torch.float16`.
-
-</Tip>
-
-## Usage example
-
-```python
-import torch
-from diffusers import StableCascadeDecoderPipeline, StableCascadePriorPipeline
-
-prompt = "an image of a shiba inu, donning a spacesuit and helmet"
-negative_prompt = ""
-
-prior = StableCascadePriorPipeline.from_pretrained("stabilityai/stable-cascade-prior", variant="bf16", torch_dtype=torch.bfloat16)
-decoder = StableCascadeDecoderPipeline.from_pretrained("stabilityai/stable-cascade", variant="bf16", torch_dtype=torch.float16)
-
-prior.enable_model_cpu_offload()
-prior_output = prior(
-    prompt=prompt,
-    height=1024,
-    width=1024,
-    negative_prompt=negative_prompt,
-    guidance_scale=4.0,
-    num_images_per_prompt=1,
-    num_inference_steps=20
-)
-
-decoder.enable_model_cpu_offload()
-decoder_output = decoder(
-    image_embeddings=prior_output.image_embeddings.to(torch.float16),
-    prompt=prompt,
-    negative_prompt=negative_prompt,
-    guidance_scale=0.0,
-    output_type="pil",
-    num_inference_steps=10
-).images[0]
-decoder_output.save("cascade.png")
-```
-
-## Using the Lite Versions of the Stage B and Stage C models
-
-```python
-import torch
-from diffusers import (
-    StableCascadeDecoderPipeline,
-    StableCascadePriorPipeline,
-    StableCascadeUNet,
-)
-
-prompt = "an image of a shiba inu, donning a spacesuit and helmet"
-negative_prompt = ""
-
-prior_unet = StableCascadeUNet.from_pretrained("stabilityai/stable-cascade-prior", subfolder="prior_lite")
-decoder_unet = StableCascadeUNet.from_pretrained("stabilityai/stable-cascade", subfolder="decoder_lite")
-
-prior = StableCascadePriorPipeline.from_pretrained("stabilityai/stable-cascade-prior", prior=prior_unet)
-decoder = StableCascadeDecoderPipeline.from_pretrained("stabilityai/stable-cascade", decoder=decoder_unet)
-
-prior.enable_model_cpu_offload()
-prior_output = prior(
-    prompt=prompt,
-    height=1024,
-    width=1024,
-    negative_prompt=negative_prompt,
-    guidance_scale=4.0,
-    num_images_per_prompt=1,
-    num_inference_steps=20
-)
-
-decoder.enable_model_cpu_offload()
-decoder_output = decoder(
-    image_embeddings=prior_output.image_embeddings,
-    prompt=prompt,
-    negative_prompt=negative_prompt,
-    guidance_scale=0.0,
-    output_type="pil",
-    num_inference_steps=10
-).images[0]
-decoder_output.save("cascade.png")
-```
-
-## Loading original checkpoints with `from_single_file`
-
-Loading the original format checkpoints is supported via `from_single_file` method in the StableCascadeUNet.
-
-```python
-import torch
-from diffusers import (
-    StableCascadeDecoderPipeline,
-    StableCascadePriorPipeline,
-    StableCascadeUNet,
-)
-
-prompt = "an image of a shiba inu, donning a spacesuit and helmet"
-negative_prompt = ""
-
-prior_unet = StableCascadeUNet.from_single_file(
-    "https://huggingface.co/stabilityai/stable-cascade/resolve/main/stage_c_bf16.safetensors",
-    torch_dtype=torch.bfloat16
-)
-decoder_unet = StableCascadeUNet.from_single_file(
-    "https://huggingface.co/stabilityai/stable-cascade/blob/main/stage_b_bf16.safetensors",
-    torch_dtype=torch.bfloat16
-)
-
-prior = StableCascadePriorPipeline.from_pretrained("stabilityai/stable-cascade-prior", prior=prior_unet, torch_dtype=torch.bfloat16)
-decoder = StableCascadeDecoderPipeline.from_pretrained("stabilityai/stable-cascade", decoder=decoder_unet, torch_dtype=torch.bfloat16)
-
-prior.enable_model_cpu_offload()
-prior_output = prior(
-    prompt=prompt,
-    height=1024,
-    width=1024,
-    negative_prompt=negative_prompt,
-    guidance_scale=4.0,
-    num_images_per_prompt=1,
-    num_inference_steps=20
-)
-
-decoder.enable_model_cpu_offload()
-decoder_output = decoder(
-    image_embeddings=prior_output.image_embeddings,
-    prompt=prompt,
-    negative_prompt=negative_prompt,
-    guidance_scale=0.0,
-    output_type="pil",
-    num_inference_steps=10
-).images[0]
-decoder_output.save("cascade-single-file.png")
-```
-
 ## Uses

 ### Direct Use
@@ -194,7 +53,7 @@ Excluded uses are described below.

 ### Out-of-Scope Use

-The model was not trained to be factual or true representations of people or events,
+The model was not trained to be factual or true representations of people or events, 
 and therefore using the model to generate such content is out-of-scope for the abilities of this model.
 The model should not be used in any way that violates Stability AI's [Acceptable Use Policy](https://stability.ai/use-policy).

@@ -172,41 +172,3 @@ inpaint = StableDiffusionInpaintPipeline(**text2img.components)

 # now you can use text2img(...), img2img(...), inpaint(...) just like the call methods of each respective pipeline
 ```
-
-### Create web demos using `gradio`
-
-The Stable Diffusion pipelines are automatically supported in [Gradio](https://github.com/gradio-app/gradio/), a library that makes creating beautiful and user-friendly machine learning apps on the web a breeze. First, make sure you have Gradio installed:
-
-```
-pip install -U gradio
-```
-
-Then, create a web demo around any Stable Diffusion-based pipeline. For example, you can create an image generation pipeline in a single line of code with Gradio's [`Interface.from_pipeline`](https://www.gradio.app/docs/interface#interface-from-pipeline) function:
-
-```py
-from diffusers import StableDiffusionPipeline
-import gradio as gr
-
-pipe = StableDiffusionPipeline.from_pretrained("CompVis/stable-diffusion-v1-4")
-
-gr.Interface.from_pipeline(pipe).launch()
-```
-
-which opens an intuitive drag-and-drop interface in your browser:
-
-![](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/gradio-panda.png)
-
-Similarly, you could create a demo for an image-to-image pipeline with:
-
-```py
-from diffusers import StableDiffusionImg2ImgPipeline
-import gradio as gr
-
-
-pipe = StableDiffusionImg2ImgPipeline.from_pretrained("runwayml/stable-diffusion-v1-5")
-
-gr.Interface.from_pipeline(pipe).launch()
-```
-
-By default, the web demo runs on a local server. If you'd like to share it with others, you can generate a temporary public
-link by setting `share=True` in `launch()`. Or, you can host your demo on [Hugging Face Spaces](https://huggingface.co/spaces)https://huggingface.co/spaces for a permanent link. 
@@ -1,22 +0,0 @@
-<!--Copyright 2024 The HuggingFace Team. All rights reserved.
-
-Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
-the License. You may obtain a copy of the License at
-
-http://www.apache.org/licenses/LICENSE-2.0
-
-Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
-an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
-specific language governing permissions and limitations under the License.
-->
-
-# EDMEulerScheduler
-
-The Karras formulation of the Euler scheduler (Algorithm 2) from the [Elucidating the Design Space of Diffusion-Based Generative Models](https://huggingface.co/papers/2206.00364) paper by Karras et al. This is a fast scheduler which can often generate good outputs in 20-30 steps. The scheduler is based on the original [k-diffusion](https://github.com/crowsonkb/k-diffusion/blob/481677d114f6ea445aa009cf5bd7a9cdee909e47/k_diffusion/sampling.py#L51) implementation by [Katherine Crowson](https://github.com/crowsonkb/).
-
-
-## EDMEulerScheduler
-[[autodoc]] EDMEulerScheduler
-
-## EDMEulerSchedulerOutput
-[[autodoc]] schedulers.scheduling_edm_euler.EDMEulerSchedulerOutput
@@ -1,24 +0,0 @@
-<!--Copyright 2024 The HuggingFace Team. All rights reserved.
-
-Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
-the License. You may obtain a copy of the License at
-
-http://www.apache.org/licenses/LICENSE-2.0
-
-Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
-an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
-specific language governing permissions and limitations under the License.
-->
-
-# EDMDPMSolverMultistepScheduler
-
-`EDMDPMSolverMultistepScheduler` is a [Karras formulation](https://huggingface.co/papers/2206.00364) of `DPMSolverMultistep`, a multistep scheduler from [DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps](https://huggingface.co/papers/2206.00927) and [DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models](https://huggingface.co/papers/2211.01095) by Cheng Lu, Yuhao Zhou, Fan Bao, Jianfei Chen, Chongxuan Li, and Jun Zhu.
-
-DPMSolver (and the improved version DPMSolver++) is a fast dedicated high-order solver for diffusion ODEs with convergence order guarantee. Empirically, DPMSolver sampling with only 20 steps can generate high-quality
-samples, and it can generate quite good samples even in 10 steps.
-
-## EDMDPMSolverMultistepScheduler
-[[autodoc]] EDMDPMSolverMultistepScheduler
-
-## SchedulerOutput
-[[autodoc]] schedulers.scheduling_utils.SchedulerOutput
@@ -88,7 +88,7 @@ accelerate config default

 Or if your environment doesn't support an interactive shell, like a notebook, you can use:

-```py
+```bash
 from accelerate.utils import write_basic_config

 write_basic_config()
@@ -54,7 +54,7 @@ accelerate config default

 Or if your environment doesn't support an interactive shell, like a notebook, you can use:

-```py
+```bash
 from accelerate.utils import write_basic_config

 write_basic_config()
@@ -84,7 +84,7 @@ Many of the basic parameters are described in the [DreamBooth](dreambooth#script
 - `--freeze_model`: freezes the key and value parameters in the cross-attention layer; the default is `crossattn_kv`, but you can set it to `crossattn` to train all the parameters in the cross-attention layer
 - `--concepts_list`: to learn multiple concepts, provide a path to a JSON file containing the concepts
 - `--modifier_token`: a special word used to represent the learned concept
- `--initializer_token`: a special word used to initialize the embeddings of the `modifier_token`
+- `--initializer_token`:

 ### Prior preservation loss

@@ -67,7 +67,7 @@ accelerate config default

 Or if your environment doesn't support an interactive shell, like a notebook, you can use:

-```py
+```bash
 from accelerate.utils import write_basic_config

 write_basic_config()
@@ -180,7 +180,7 @@ elif args.pretrained_model_name_or_path:
        revision=args.revision,
        use_fast=False,
    )
-
+    
 # Load scheduler and models
 noise_scheduler = DDPMScheduler.from_pretrained(args.pretrained_model_name_or_path, subfolder="scheduler")
 text_encoder = text_encoder_cls.from_pretrained(
@@ -51,7 +51,7 @@ accelerate config default

 Or if your environment doesn't support an interactive shell, like a notebook, you can use:

-```py
+```bash
 from accelerate.utils import write_basic_config

 write_basic_config()
@@ -89,7 +89,7 @@ The dataset preprocessing code and training loop are found in the [`main()`](htt

 As with the script parameters, a walkthrough of the training script is provided in the [Text-to-image](text2image#training-script) training guide. Instead, this guide takes a look at the InstructPix2Pix relevant parts of the script.

-The script begins by modifying the [number of input channels](https://github.com/huggingface/diffusers/blob/64603389da01082055a901f2883c4810d1144edb/examples/instruct_pix2pix/train_instruct_pix2pix.py#L445) in the first convolutional layer of the UNet to account for InstructPix2Pix's additional conditioning image:
+The script begins by modifing the [number of input channels](https://github.com/huggingface/diffusers/blob/64603389da01082055a901f2883c4810d1144edb/examples/instruct_pix2pix/train_instruct_pix2pix.py#L445) in the first convolutional layer of the UNet to account for InstructPix2Pix's additional conditioning image:

 ```py
 in_channels = 8
@@ -59,7 +59,7 @@ accelerate config default

 Or if your environment doesn't support an interactive shell, like a notebook, you can use:

-```py
+```bash
 from accelerate.utils import write_basic_config

 write_basic_config()
@@ -235,7 +235,7 @@ accelerate launch --mixed_precision="fp16"  train_text_to_image_prior.py \
  --validation_prompts="A robot pokemon, 4k photo" \
  --report_to="wandb" \
  --push_to_hub \
-  --output_dir="kandi2-prior-pokemon-model"
+  --output_dir="kandi2-prior-pokemon-model" 
 ```

 </hfoption>
@@ -259,7 +259,7 @@ accelerate launch --mixed_precision="fp16"  train_text_to_image_decoder.py \
  --validation_prompts="A robot pokemon, 4k photo" \
  --report_to="wandb" \
  --push_to_hub \
-  --output_dir="kandi2-decoder-pokemon-model"
+  --output_dir="kandi2-decoder-pokemon-model" 
 ```

 </hfoption>
@@ -53,7 +53,7 @@ accelerate config default

 Or if your environment doesn't support an interactive shell, like a notebook, you can use:

-```py
+```bash
 from accelerate.utils import write_basic_config

 write_basic_config()
@@ -252,4 +252,4 @@ The SDXL training script is discussed in more detail in the [SDXL training](sdxl
 Congratulations on distilling a LCM model! To learn more about LCM, the following may be helpful:

 - Learn how to use [LCMs for inference](../using-diffusers/lcm) for text-to-image, image-to-image, and with LoRA checkpoints.
- Read the [SDXL in 4 steps with Latent Consistency LoRAs](https://huggingface.co/blog/lcm_lora) blog post to learn more about SDXL LCM-LoRA's for super fast inference, quality comparisons, benchmarks, and more.
+- Read the [SDXL in 4 steps with Latent Consistency LoRAs](https://huggingface.co/blog/lcm_lora) blog post to learn more about SDXL LCM-LoRA's for super fast inference, quality comparisons, benchmarks, and more.
@@ -59,7 +59,7 @@ accelerate config default

 Or if your environment doesn't support an interactive shell, like a notebook, you can use:

-```py
+```bash
 from accelerate.utils import write_basic_config

 write_basic_config()
@@ -53,7 +53,7 @@ accelerate config default

 Or if your environment doesn't support an interactive shell, like a notebook, you can use:

-```py
+```bash
 from accelerate.utils import write_basic_config

 write_basic_config()
@@ -69,7 +69,7 @@ accelerate config default

 Or if your environment doesn't support an interactive shell, like a notebook, you can use:

-```py
+```bash
 from accelerate.utils import write_basic_config

 write_basic_config()
@@ -67,7 +67,7 @@ accelerate config default

 Or if your environment doesn't support an interactive shell, like a notebook, you can use:

-```py
+```bash
 from accelerate.utils import write_basic_config

 write_basic_config()
@@ -51,7 +51,7 @@ accelerate config default

 Or if your environment doesn't support an interactive shell like a notebook, you can use:

-```py
+```bash
 from accelerate.utils import write_basic_config

 write_basic_config()
@@ -53,7 +53,7 @@ accelerate config default

 Or if your environment doesn't support an interactive shell, like a notebook, you can use:

-```py
+```bash
 from accelerate.utils import write_basic_config

 write_basic_config()
@@ -173,7 +173,7 @@ pipeline = AutoPipelineForText2Image.from_pretrained("path/to/saved/model", torc

 caption = "A cute bird pokemon holding a shield"
 images = pipeline(
-    caption,
+    caption, 
    width=1024,
    height=1536,
    prior_timesteps=DEFAULT_STAGE_C_TIMESTEPS,
@@ -45,7 +45,7 @@ Make sure to include the token `toy_face` in the prompt and then you can perform
 ```python
 prompt = "toy_face of a hacker with a hoodie"

-lora_scale = 0.9
+lora_scale= 0.9
 image = pipe(
    prompt, num_inference_steps=30, cross_attention_kwargs={"scale": lora_scale}, generator=torch.manual_seed(0)
 ).images[0]
@@ -114,7 +114,7 @@ To return to only using one adapter, use the [`~diffusers.loaders.UNet2DConditio
 pipe.set_adapters("toy")

 prompt = "toy_face of a hacker with a hoodie"
-lora_scale = 0.9
+lora_scale= 0.9
 image = pipe(
    prompt, num_inference_steps=30, cross_attention_kwargs={"scale": lora_scale}, generator=torch.manual_seed(0)
 ).images[0]
@@ -127,68 +127,11 @@ Or to disable all adapters entirely, use the [`~diffusers.loaders.UNet2DConditio
 pipe.disable_lora()

 prompt = "toy_face of a hacker with a hoodie"
+lora_scale= 0.9
 image = pipe(prompt, num_inference_steps=30, generator=torch.manual_seed(0)).images[0]
 image
 ```

-![no-lora](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/peft_integration/diffusers_peft_lora_inference_20_1.png)
-
-### Customize adapters strength
-For even more customization, you can control how strongly the adapter affects each part of the pipeline. For this, pass a dictionary with the control strengths (called "scales") to [`~diffusers.loaders.UNet2DConditionLoadersMixin.set_adapters`].
-
-For example, here's how you can turn on the adapter for the `down` parts, but turn it off for the `mid` and `up` parts:
-```python
-pipe.enable_lora()  # enable lora again, after we disabled it above
-prompt = "toy_face of a hacker with a hoodie, pixel art"
-adapter_weight_scales = { "unet": { "down": 1, "mid": 0, "up": 0} }
-pipe.set_adapters("pixel", adapter_weight_scales)
-image = pipe(prompt, num_inference_steps=30, generator=torch.manual_seed(0)).images[0]
-image
-```
-
-![block-lora-text-and-down](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/peft_integration/diffusers_peft_lora_inference_block_down.png)
-
-Let's see how turning off the `down` part and turning on the `mid` and `up` part respectively changes the image.
-```python
-adapter_weight_scales = { "unet": { "down": 0, "mid": 1, "up": 0} }
-pipe.set_adapters("pixel", adapter_weight_scales)
-image = pipe(prompt, num_inference_steps=30, generator=torch.manual_seed(0)).images[0]
-image
-```
-
-![block-lora-text-and-mid](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/peft_integration/diffusers_peft_lora_inference_block_mid.png)
-
-```python
-adapter_weight_scales = { "unet": { "down": 0, "mid": 0, "up": 1} }
-pipe.set_adapters("pixel", adapter_weight_scales)
-image = pipe(prompt, num_inference_steps=30, generator=torch.manual_seed(0)).images[0]
-image
-```
-
-![block-lora-text-and-up](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/peft_integration/diffusers_peft_lora_inference_block_up.png)
-
-Looks cool!
-
-This is a really powerful feature. You can use it to control the adapter strengths down to per-transformer level. And you can even use it for multiple adapters.
-```python
-adapter_weight_scales_toy = 0.5
-adapter_weight_scales_pixel = {
-    "unet": {
-        "down": 0.9,  # all transformers in the down-part will use scale 0.9
-        # "mid"  # because, in this example, "mid" is not given, all transformers in the mid part will use the default scale 1.0
-        "up": {
-            "block_0": 0.6,  # all 3 transformers in the 0th block in the up-part will use scale 0.6
-            "block_1": [0.4, 0.8, 1.0],  # the 3 transformers in the 1st block in the up-part will use scales 0.4, 0.8 and 1.0 respectively
-        }
-    }
-}
-pipe.set_adapters(["toy", "pixel"], [adapter_weight_scales_toy, adapter_weight_scales_pixel])
-image = pipe(prompt, num_inference_steps=30, generator=torch.manual_seed(0)).images[0]
-image
-```
-
-![block-lora-mixed](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/peft_integration/diffusers_peft_lora_inference_block_mixed.png)
-
 ## Manage active adapters

 You have attached multiple adapters in this tutorial, and if you're feeling a bit lost on what adapters have been attached to the pipeline's components, use the [`~diffusers.loaders.LoraLoaderMixin.get_active_adapters`] method to check the list of active adapters:
@@ -239,7 +239,5 @@ pipeline.to("cuda")
 prompt = "柴犬、カラフルアート"

 image = pipeline(prompt=prompt).images[0]
-```

-> [!TIP]
-> When using `trust_remote_code=True`, it is also strongly encouraged to pass a commit hash as a `revision` to make sure the author of the models did not update the code with some malicious new lines (unless you fully trust the authors of the models).
+```
@@ -1,438 +0,0 @@
-<!--Copyright 2024 The HuggingFace Team. All rights reserved.
-
-Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
-the License. You may obtain a copy of the License at
-
-http://www.apache.org/licenses/LICENSE-2.0
-
-Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
-an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
-specific language governing permissions and limitations under the License.
-->
-
-[[open-in-colab]]
-
-# Trajectory Consistency Distillation-LoRA
-
-Trajectory Consistency Distillation (TCD) enables a model to generate higher quality and more detailed images with fewer steps. Moreover, owing to the effective error mitigation during the distillation process, TCD demonstrates superior performance even under conditions of large inference steps.
-
-The major advantages of TCD are:
-
- Better than Teacher: TCD demonstrates superior generative quality at both small and large inference steps and exceeds the performance of [DPM-Solver++(2S)](../../api/schedulers/multistep_dpm_solver) with Stable Diffusion XL (SDXL). There is no additional discriminator or LPIPS supervision included during TCD training.
-
- Flexible Inference Steps: The inference steps for TCD sampling can be freely adjusted without adversely affecting the image quality.
-
- Freely change detail level: During inference, the level of detail in the image can be adjusted with a single hyperparameter, *gamma*.
-
-> [!TIP]
-> For more technical details of TCD, please refer to the [paper](https://arxiv.org/abs/2402.19159) or official [project page](https://mhh0318.github.io/tcd/)).
-
-For large models like SDXL, TCD is trained with [LoRA](https://huggingface.co/docs/peft/conceptual_guides/adapter#low-rank-adaptation-lora) to reduce memory usage. This is also useful because you can reuse LoRAs between different finetuned models, as long as they share the same base model, without further training.
-
-
-
-This guide will show you how to perform inference with TCD-LoRAs for a variety of tasks like text-to-image and inpainting, as well as how you can easily combine TCD-LoRAs with other adapters. Choose one of the supported base model and it's corresponding TCD-LoRA checkpoint from the table below to get started.
-
-| Base model                                                                                      | TCD-LoRA checkpoint                                            |
-|-------------------------------------------------------------------------------------------------|----------------------------------------------------------------|
-| [stable-diffusion-v1-5](https://huggingface.co/runwayml/stable-diffusion-v1-5)                  | [TCD-SD15](https://huggingface.co/h1t/TCD-SD15-LoRA)           |
-| [stable-diffusion-2-1-base](https://huggingface.co/stabilityai/stable-diffusion-2-1-base)       | [TCD-SD21-base](https://huggingface.co/h1t/TCD-SD21-base-LoRA) |
-| [stable-diffusion-xl-base-1.0](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0) | [TCD-SDXL](https://huggingface.co/h1t/TCD-SDXL-LoRA)           |
-
-
-Make sure you have [PEFT](https://github.com/huggingface/peft) installed for better LoRA support.
-
-```bash
-pip install -U peft
-```
-
-## General tasks
-
-In this guide, let's use the [`StableDiffusionXLPipeline`] and the [`TCDScheduler`]. Use the [`~StableDiffusionPipeline.load_lora_weights`] method to load the SDXL-compatible TCD-LoRA weights.
-
-A few tips to keep in mind for TCD-LoRA inference are to:
-
- Keep the `num_inference_steps` between 4 and 50
- Set `eta` (used to control stochasticity at each step) between 0 and 1. You should use a higher `eta` when increasing the number of inference steps, but the downside is that a larger `eta` in [`TCDScheduler`] leads to blurrier images. A value of 0.3 is recommended to produce good results.
-
-<hfoptions id="tasks">
-<hfoption id="text-to-image">
-
-```python
-import torch
-from diffusers import StableDiffusionXLPipeline, TCDScheduler
-
-device = "cuda"
-base_model_id = "stabilityai/stable-diffusion-xl-base-1.0"
-tcd_lora_id = "h1t/TCD-SDXL-LoRA"
-
-pipe = StableDiffusionXLPipeline.from_pretrained(base_model_id, torch_dtype=torch.float16, variant="fp16").to(device)
-pipe.scheduler = TCDScheduler.from_config(pipe.scheduler.config)
-
-pipe.load_lora_weights(tcd_lora_id)
-pipe.fuse_lora()
-
-prompt = "Painting of the orange cat Otto von Garfield, Count of Bismarck-Schönhausen, Duke of Lauenburg, Minister-President of Prussia. Depicted wearing a Prussian Pickelhaube and eating his favorite meal - lasagna."
-
-image = pipe(
-    prompt=prompt,
-    num_inference_steps=4,
-    guidance_scale=0,
-    eta=0.3, 
-    generator=torch.Generator(device=device).manual_seed(0),
-).images[0]
-```
-
-![](https://github.com/jabir-zheng/TCD/raw/main/assets/demo_image.png)
-
-</hfoption>
-
-<hfoption id="inpainting">
-
-```python
-import torch
-from diffusers import AutoPipelineForInpainting, TCDScheduler
-from diffusers.utils import load_image, make_image_grid
-
-device = "cuda"
-base_model_id = "diffusers/stable-diffusion-xl-1.0-inpainting-0.1"
-tcd_lora_id = "h1t/TCD-SDXL-LoRA"
-
-pipe = AutoPipelineForInpainting.from_pretrained(base_model_id, torch_dtype=torch.float16, variant="fp16").to(device)
-pipe.scheduler = TCDScheduler.from_config(pipe.scheduler.config)
-
-pipe.load_lora_weights(tcd_lora_id)
-pipe.fuse_lora()
-
-img_url = "https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo.png"
-mask_url = "https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo_mask.png"
-
-init_image = load_image(img_url).resize((1024, 1024))
-mask_image = load_image(mask_url).resize((1024, 1024))
-
-prompt = "a tiger sitting on a park bench"
-
-image = pipe(
-  prompt=prompt,
-  image=init_image,
-  mask_image=mask_image,
-  num_inference_steps=8,
-  guidance_scale=0,
-  eta=0.3,
-  strength=0.99,  # make sure to use `strength` below 1.0
-  generator=torch.Generator(device=device).manual_seed(0),
-).images[0]
-
-grid_image = make_image_grid([init_image, mask_image, image], rows=1, cols=3)
-```
-
-![](https://github.com/jabir-zheng/TCD/raw/main/assets/inpainting_tcd.png)
-
-
-</hfoption>
-</hfoptions>
-
-## Community models
-
-TCD-LoRA also works with many community finetuned models and plugins. For example, load the [animagine-xl-3.0](https://huggingface.co/cagliostrolab/animagine-xl-3.0) checkpoint which is a community finetuned version of SDXL for generating anime images.
-
-```python
-import torch
-from diffusers import StableDiffusionXLPipeline, TCDScheduler
-
-device = "cuda"
-base_model_id = "cagliostrolab/animagine-xl-3.0"
-tcd_lora_id = "h1t/TCD-SDXL-LoRA"
-
-pipe = StableDiffusionXLPipeline.from_pretrained(base_model_id, torch_dtype=torch.float16, variant="fp16").to(device)
-pipe.scheduler = TCDScheduler.from_config(pipe.scheduler.config)
-
-pipe.load_lora_weights(tcd_lora_id)
-pipe.fuse_lora()
-
-prompt = "A man, clad in a meticulously tailored military uniform, stands with unwavering resolve. The uniform boasts intricate details, and his eyes gleam with determination. Strands of vibrant, windswept hair peek out from beneath the brim of his cap."
-
-image = pipe(
-    prompt=prompt,
-    num_inference_steps=8,
-    guidance_scale=0,
-    eta=0.3, 
-    generator=torch.Generator(device=device).manual_seed(0),
-).images[0]
-```
-
-![](https://github.com/jabir-zheng/TCD/raw/main/assets/animagine_xl.png)
-
-TCD-LoRA also supports other LoRAs trained on different styles. For example, let's load the [TheLastBen/Papercut_SDXL](https://huggingface.co/TheLastBen/Papercut_SDXL) LoRA and fuse it with the TCD-LoRA with the [`~loaders.UNet2DConditionLoadersMixin.set_adapters`] method. 
-
-> [!TIP]
-> Check out the [Merge LoRAs](merge_loras) guide to learn more about efficient merging methods.
-
-```python
-import torch
-from diffusers import StableDiffusionXLPipeline
-from scheduling_tcd import TCDScheduler 
-
-device = "cuda"
-base_model_id = "stabilityai/stable-diffusion-xl-base-1.0"
-tcd_lora_id = "h1t/TCD-SDXL-LoRA"
-styled_lora_id = "TheLastBen/Papercut_SDXL"
-
-pipe = StableDiffusionXLPipeline.from_pretrained(base_model_id, torch_dtype=torch.float16, variant="fp16").to(device)
-pipe.scheduler = TCDScheduler.from_config(pipe.scheduler.config)
-
-pipe.load_lora_weights(tcd_lora_id, adapter_name="tcd")
-pipe.load_lora_weights(styled_lora_id, adapter_name="style")
-pipe.set_adapters(["tcd", "style"], adapter_weights=[1.0, 1.0])
-
-prompt = "papercut of a winter mountain, snow"
-
-image = pipe(
-    prompt=prompt,
-    num_inference_steps=4,
-    guidance_scale=0,
-    eta=0.3, 
-    generator=torch.Generator(device=device).manual_seed(0),
-).images[0]
-```
-
-![](https://github.com/jabir-zheng/TCD/raw/main/assets/styled_lora.png)
-
-
-## Adapters
-
-TCD-LoRA is very versatile, and it can be combined with other adapter types like ControlNets, IP-Adapter, and AnimateDiff.
-
-<hfoptions id="adapters">
-<hfoption id="ControlNet">
-
-### Depth ControlNet
-
-```python
-import torch
-import numpy as np
-from PIL import Image
-from transformers import DPTFeatureExtractor, DPTForDepthEstimation
-from diffusers import ControlNetModel, StableDiffusionXLControlNetPipeline
-from diffusers.utils import load_image, make_image_grid
-from scheduling_tcd import TCDScheduler 
-
-device = "cuda"
-depth_estimator = DPTForDepthEstimation.from_pretrained("Intel/dpt-hybrid-midas").to(device)
-feature_extractor = DPTFeatureExtractor.from_pretrained("Intel/dpt-hybrid-midas")
-
-def get_depth_map(image):
-    image = feature_extractor(images=image, return_tensors="pt").pixel_values.to(device)
-    with torch.no_grad(), torch.autocast(device):
-        depth_map = depth_estimator(image).predicted_depth
-
-    depth_map = torch.nn.functional.interpolate(
-        depth_map.unsqueeze(1),
-        size=(1024, 1024),
-        mode="bicubic",
-        align_corners=False,
-    )
-    depth_min = torch.amin(depth_map, dim=[1, 2, 3], keepdim=True)
-    depth_max = torch.amax(depth_map, dim=[1, 2, 3], keepdim=True)
-    depth_map = (depth_map - depth_min) / (depth_max - depth_min)
-    image = torch.cat([depth_map] * 3, dim=1)
-
-    image = image.permute(0, 2, 3, 1).cpu().numpy()[0]
-    image = Image.fromarray((image * 255.0).clip(0, 255).astype(np.uint8))
-    return image
-
-base_model_id = "stabilityai/stable-diffusion-xl-base-1.0"
-controlnet_id = "diffusers/controlnet-depth-sdxl-1.0"
-tcd_lora_id = "h1t/TCD-SDXL-LoRA"
-
-controlnet = ControlNetModel.from_pretrained(
-    controlnet_id,
-    torch_dtype=torch.float16,
-    variant="fp16",
-).to(device)
-pipe = StableDiffusionXLControlNetPipeline.from_pretrained(
-    base_model_id,
-    controlnet=controlnet,
-    torch_dtype=torch.float16,
-    variant="fp16",
-).to(device)
-pipe.enable_model_cpu_offload()
-
-pipe.scheduler = TCDScheduler.from_config(pipe.scheduler.config)
-
-pipe.load_lora_weights(tcd_lora_id)
-pipe.fuse_lora()
-
-prompt = "stormtrooper lecture, photorealistic"
-
-image = load_image("https://huggingface.co/lllyasviel/sd-controlnet-depth/resolve/main/images/stormtrooper.png")
-depth_image = get_depth_map(image)
-
-controlnet_conditioning_scale = 0.5  # recommended for good generalization
-
-image = pipe(
-    prompt, 
-    image=depth_image, 
-    num_inference_steps=4, 
-    guidance_scale=0,
-    eta=0.3,
-    controlnet_conditioning_scale=controlnet_conditioning_scale,
-    generator=torch.Generator(device=device).manual_seed(0),
-).images[0]
-
-grid_image = make_image_grid([depth_image, image], rows=1, cols=2)
-```
-
-![](https://github.com/jabir-zheng/TCD/raw/main/assets/controlnet_depth_tcd.png)
-
-### Canny ControlNet
-```python
-import torch
-from diffusers import ControlNetModel, StableDiffusionXLControlNetPipeline
-from diffusers.utils import load_image, make_image_grid
-from scheduling_tcd import TCDScheduler 
-
-device = "cuda"
-base_model_id = "stabilityai/stable-diffusion-xl-base-1.0"
-controlnet_id = "diffusers/controlnet-canny-sdxl-1.0"
-tcd_lora_id = "h1t/TCD-SDXL-LoRA"
-
-controlnet = ControlNetModel.from_pretrained(
-    controlnet_id,
-    torch_dtype=torch.float16,
-    variant="fp16",
-).to(device)
-pipe = StableDiffusionXLControlNetPipeline.from_pretrained(
-    base_model_id,
-    controlnet=controlnet,
-    torch_dtype=torch.float16,
-    variant="fp16",
-).to(device)
-pipe.enable_model_cpu_offload()
-
-pipe.scheduler = TCDScheduler.from_config(pipe.scheduler.config)
-
-pipe.load_lora_weights(tcd_lora_id)
-pipe.fuse_lora()
-
-prompt = "ultrarealistic shot of a furry blue bird"
-
-canny_image = load_image("https://huggingface.co/datasets/hf-internal-testing/diffusers-images/resolve/main/sd_controlnet/bird_canny.png")
-
-controlnet_conditioning_scale = 0.5  # recommended for good generalization
-
-image = pipe(
-    prompt, 
-    image=canny_image, 
-    num_inference_steps=4, 
-    guidance_scale=0,
-    eta=0.3,
-    controlnet_conditioning_scale=controlnet_conditioning_scale,
-    generator=torch.Generator(device=device).manual_seed(0),
-).images[0]
-
-grid_image = make_image_grid([canny_image, image], rows=1, cols=2)
-```
-![](https://github.com/jabir-zheng/TCD/raw/main/assets/controlnet_canny_tcd.png)
-
-<Tip>
-The inference parameters in this example might not work for all examples, so we recommend you to try different values for `num_inference_steps`, `guidance_scale`, `controlnet_conditioning_scale` and `cross_attention_kwargs` parameters and choose the best one. 
-</Tip>
-
-</hfoption>
-<hfoption id="IP-Adapter">
-
-This example shows how to use the TCD-LoRA with the [IP-Adapter](https://github.com/tencent-ailab/IP-Adapter/tree/main) and SDXL.
-
-```python
-import torch
-from diffusers import StableDiffusionXLPipeline
-from diffusers.utils import load_image, make_image_grid
-
-from ip_adapter import IPAdapterXL
-from scheduling_tcd import TCDScheduler 
-
-device = "cuda"
-base_model_path = "stabilityai/stable-diffusion-xl-base-1.0"
-image_encoder_path = "sdxl_models/image_encoder"
-ip_ckpt = "sdxl_models/ip-adapter_sdxl.bin"
-tcd_lora_id = "h1t/TCD-SDXL-LoRA"
-
-pipe = StableDiffusionXLPipeline.from_pretrained(
-    base_model_path, 
-    torch_dtype=torch.float16, 
-    variant="fp16"
-)
-pipe.scheduler = TCDScheduler.from_config(pipe.scheduler.config)
-
-pipe.load_lora_weights(tcd_lora_id)
-pipe.fuse_lora()
-
-ip_model = IPAdapterXL(pipe, image_encoder_path, ip_ckpt, device)
-
-ref_image = load_image("https://raw.githubusercontent.com/tencent-ailab/IP-Adapter/main/assets/images/woman.png").resize((512, 512))
-
-prompt = "best quality, high quality, wearing sunglasses"
-
-image = ip_model.generate(
-    pil_image=ref_image, 
-    prompt=prompt,
-    scale=0.5,
-    num_samples=1, 
-    num_inference_steps=4, 
-    guidance_scale=0,
-    eta=0.3, 
-    seed=0,
-)[0]
-
-grid_image = make_image_grid([ref_image, image], rows=1, cols=2)
-```
-
-![](https://github.com/jabir-zheng/TCD/raw/main/assets/ip_adapter.png)
-
-
-
-</hfoption>
-<hfoption id="AnimateDiff">
-
-[`AnimateDiff`] allows animating images using Stable Diffusion models. TCD-LoRA can substantially accelerate the process without degrading image quality. The quality of animation with TCD-LoRA and AnimateDiff has a more lucid outcome.
-
-```python
-import torch
-from diffusers import MotionAdapter, AnimateDiffPipeline, DDIMScheduler
-from scheduling_tcd import TCDScheduler
-from diffusers.utils import export_to_gif
-
-adapter = MotionAdapter.from_pretrained("guoyww/animatediff-motion-adapter-v1-5")
-pipe = AnimateDiffPipeline.from_pretrained(
-    "frankjoshua/toonyou_beta6",
-    motion_adapter=adapter,
-).to("cuda")
-
-# set TCDScheduler
-pipe.scheduler = TCDScheduler.from_config(pipe.scheduler.config)
-
-# load TCD LoRA
-pipe.load_lora_weights("h1t/TCD-SD15-LoRA", adapter_name="tcd")
-pipe.load_lora_weights("guoyww/animatediff-motion-lora-zoom-in", weight_name="diffusion_pytorch_model.safetensors", adapter_name="motion-lora")
-
-pipe.set_adapters(["tcd", "motion-lora"], adapter_weights=[1.0, 1.2])
-
-prompt = "best quality, masterpiece, 1girl, looking at viewer, blurry background, upper body, contemporary, dress"
-generator = torch.manual_seed(0)
-frames = pipe(
-    prompt=prompt,
-    num_inference_steps=5,
-    guidance_scale=0,
-    cross_attention_kwargs={"scale": 1},
-    num_frames=24,
-    eta=0.3,
-    generator=generator
-).frames[0]
-export_to_gif(frames, "animation.gif")
-```
-
-![](https://github.com/jabir-zheng/TCD/raw/main/assets/animation_example.gif)
-
-</hfoption>
-</hfoptions>
@@ -60,23 +60,6 @@ repo_id = "runwayml/stable-diffusion-v1-5"
 pipe = StableDiffusionImg2ImgPipeline.from_pretrained(repo_id)
 ```

-You can use the Space below to gauge the memory requirements of a pipeline you want to load beforehand without downloading the pipeline checkpoints:
-
-<div class="block dark:hidden">
-	<iframe 
-        src="https://diffusers-compute-pipeline-size.hf.space?__theme=light"
-        width="850"
-        height="1600"
-    ></iframe>
-</div>
-<div class="hidden dark:block">
-    <iframe 
-        src="https://diffusers-compute-pipeline-size.hf.space?__theme=dark"
-        width="850"
-        height="1600"
-    ></iframe>
-</div>
-
 ### Local pipeline

 To load a diffusion pipeline locally, use [`git-lfs`](https://git-lfs.github.com/) to manually download the checkpoint (in this case, [`runwayml/stable-diffusion-v1-5`](https://huggingface.co/runwayml/stable-diffusion-v1-5)) to your local disk. This creates a local folder, `./stable-diffusion-v1-5`, on your disk:
@@ -153,43 +153,18 @@ image
    <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/load_attn_proc.png" />
 </div>

+<Tip>
+
+For both [`~loaders.LoraLoaderMixin.load_lora_weights`] and [`~loaders.UNet2DConditionLoadersMixin.load_attn_procs`], you can pass the `cross_attention_kwargs={"scale": 0.5}` parameter to adjust how much of the LoRA weights to use. A value of `0` is the same as only using the base model weights, and a value of `1` is equivalent to using the fully finetuned LoRA.
+
+</Tip>
+
 To unload the LoRA weights, use the [`~loaders.LoraLoaderMixin.unload_lora_weights`] method to discard the LoRA weights and restore the model to its original weights:

 ```py
 pipeline.unload_lora_weights()
 ```

-### Adjust LoRA weight scale
-
-For both [`~loaders.LoraLoaderMixin.load_lora_weights`] and [`~loaders.UNet2DConditionLoadersMixin.load_attn_procs`], you can pass the `cross_attention_kwargs={"scale": 0.5}` parameter to adjust how much of the LoRA weights to use. A value of `0` is the same as only using the base model weights, and a value of `1` is equivalent to using the fully finetuned LoRA.
-
-For more granular control on the amount of LoRA weights used per layer, you can use [`~loaders.LoraLoaderMixin.set_adapters`] and pass a dictionary specifying by how much to scale the weights in each layer by.
-```python
-pipe = ... # create pipeline
-pipe.load_lora_weights(..., adapter_name="my_adapter") 
-scales = {
-    "text_encoder": 0.5,
-    "text_encoder_2": 0.5,  # only usable if pipe has a 2nd text encoder
-    "unet": {
-        "down": 0.9,  # all transformers in the down-part will use scale 0.9
-        # "mid"  # in this example "mid" is not given, therefore all transformers in the mid part will use the default scale 1.0
-        "up": {
-            "block_0": 0.6,  # all 3 transformers in the 0th block in the up-part will use scale 0.6
-            "block_1": [0.4, 0.8, 1.0],  # the 3 transformers in the 1st block in the up-part will use scales 0.4, 0.8 and 1.0 respectively
-        }
-    }
-}
-pipe.set_adapters("my_adapter", scales)
-```
-
-This also works with multiple adapters - see [this guide](https://huggingface.co/docs/diffusers/tutorials/using_peft_for_inference#customize-adapters-strength) for how to do it.
-
-<Tip warning={true}>
-
-Currently, [`~loaders.LoraLoaderMixin.set_adapters`] only supports scaling attention weights. If a LoRA has other parts (e.g., resnets or down-/upsamplers), they will keep a scale of 1.0.
-
-</Tip>
-
 ### Kohya and TheLastBen

 Other popular LoRA trainers from the community include those by [Kohya](https://github.com/kohya-ss/sd-scripts/) and [TheLastBen](https://github.com/TheLastBen/fast-stable-diffusion). These trainers create different LoRA checkpoints than those trained by 🤗 Diffusers, but they can still be loaded in the same way.
@@ -21,7 +21,7 @@ This guide will show you how to use SVD to generate short videos from images.
 Before you begin, make sure you have the following libraries installed:

 ```py
-!pip install -q -U diffusers transformers accelerate
+!pip install -q -U diffusers transformers accelerate 
 ```

 The are two variants of this model, [SVD](https://huggingface.co/stabilityai/stable-video-diffusion-img2vid) and [SVD-XT](https://huggingface.co/stabilityai/stable-video-diffusion-img2vid-xt). The SVD checkpoint is trained to generate 14 frames and the SVD-XT checkpoint is further finetuned to generate 25 frames.
@@ -86,7 +86,7 @@ Video generation is very memory intensive because you're essentially generating
 + frames = pipe(image, decode_chunk_size=2, generator=generator, num_frames=25).frames[0]
 ```

-Using all these tricks together should lower the memory requirement to less than 8GB VRAM.
+Using all these tricks togethere should lower the memory requirement to less than 8GB VRAM.

 ## Micro-conditioning

@@ -12,7 +12,7 @@ specific language governing permissions and limitations under the License.

 # 메모리와 속도

-메모리 또는 속도에 대해 🤗 Diffusers *추론*을 최적화하기 위한 몇 가지 기술과 아이디어를 제시합니다.
+메모리 또는 속도에 대해 🤗 Diffusers *추론*을 최적화하기 위한 몇 가지 기술과 아이디어를 제시합니다. 
 일반적으로, memory-efficient attention을 위해 [xFormers](https://github.com/facebookresearch/xformers) 사용을 추천하기 때문에, 추천하는 [설치 방법](xformers)을 보고 설치해 보세요.

 다음 설정이 성능과 메모리에 미치는 영향에 대해 설명합니다.
@@ -27,7 +27,7 @@ specific language governing permissions and limitations under the License.
 | memory-efficient attention | 2.63s  | x3.61   |

 <em>
-   NVIDIA TITAN RTX에서 50 DDIM 스텝의 "a photo of an astronaut riding a horse on mars" 프롬프트로 512x512 크기의 단일 이미지를 생성하였습니다.
+   NVIDIA TITAN RTX에서 50 DDIM 스텝의 "a photo of an astronaut riding a horse on mars" 프롬프트로 512x512 크기의 단일 이미지를 생성하였습니다. 
 </em>

 ## cuDNN auto-tuner 활성화하기
@@ -44,11 +44,11 @@ torch.backends.cudnn.benchmark = True

 ### fp32 대신 tf32 사용하기  (Ampere 및 이후 CUDA 장치들에서)

-Ampere 및 이후 CUDA 장치에서 행렬곱 및 컨볼루션은 TensorFloat32(TF32) 모드를 사용하여 더 빠르지만 약간 덜 정확할 수 있습니다.
-기본적으로 PyTorch는 컨볼루션에 대해 TF32 모드를 활성화하지만 행렬 곱셈은 활성화하지 않습니다.
-네트워크에 완전한 float32 정밀도가 필요한 경우가 아니면 행렬 곱셈에 대해서도 이 설정을 활성화하는 것이 좋습니다.
-이는 일반적으로 무시할 수 있는 수치의 정확도 손실이 있지만, 계산 속도를 크게 높일 수 있습니다.
-그것에 대해 [여기](https://huggingface.co/docs/transformers/v4.18.0/en/performance#tf32)서 더 읽을 수 있습니다.
+Ampere 및 이후 CUDA 장치에서 행렬곱 및 컨볼루션은 TensorFloat32(TF32) 모드를 사용하여 더 빠르지만 약간 덜 정확할 수 있습니다. 
+기본적으로 PyTorch는 컨볼루션에 대해 TF32 모드를 활성화하지만 행렬 곱셈은 활성화하지 않습니다. 
+네트워크에 완전한 float32 정밀도가 필요한 경우가 아니면 행렬 곱셈에 대해서도 이 설정을 활성화하는 것이 좋습니다. 
+이는 일반적으로 무시할 수 있는 수치의 정확도 손실이 있지만, 계산 속도를 크게 높일 수 있습니다. 
+그것에 대해 [여기](https://huggingface.co/docs/transformers/v4.18.0/en/performance#tf32)서 더 읽을 수 있습니다. 
 추론하기 전에 다음을 추가하기만 하면 됩니다:

 ```python
@@ -59,13 +59,13 @@ torch.backends.cuda.matmul.allow_tf32 = True

 ## 반정밀도 가중치

-더 많은 GPU 메모리를 절약하고 더 빠른 속도를 얻기 위해 모델 가중치를 반정밀도(half precision)로 직접 불러오고 실행할 수 있습니다.
+더 많은 GPU 메모리를 절약하고 더 빠른 속도를 얻기 위해 모델 가중치를 반정밀도(half precision)로 직접 불러오고 실행할 수 있습니다. 
 여기에는 `fp16`이라는 브랜치에 저장된 float16 버전의 가중치를 불러오고, 그 때 `float16` 유형을 사용하도록 PyTorch에 지시하는 작업이 포함됩니다.

 ```Python
 pipe = StableDiffusionPipeline.from_pretrained(
    "runwayml/stable-diffusion-v1-5",
-
+    
    torch_dtype=torch.float16,
 )
 pipe = pipe.to("cuda")
@@ -75,7 +75,7 @@ image = pipe(prompt).images[0]
 ```

 <Tip warning={true}>
-  어떤 파이프라인에서도 [`torch.autocast`](https://pytorch.org/docs/stable/amp.html#torch.autocast) 를 사용하는 것은 검은색 이미지를 생성할 수 있고, 순수한 float16 정밀도를 사용하는 것보다 항상 느리기 때문에 사용하지 않는 것이 좋습니다.
+  어떤 파이프라인에서도 [`torch.autocast`](https://pytorch.org/docs/stable/amp.html#torch.autocast) 를 사용하는 것은 검은색 이미지를 생성할 수 있고, 순수한 float16 정밀도를 사용하는 것보다 항상 느리기 때문에 사용하지 않는 것이 좋습니다. 
 </Tip>

 ## 추가 메모리 절약을 위한 슬라이스 어텐션
@@ -95,7 +95,7 @@ from diffusers import StableDiffusionPipeline

 pipe = StableDiffusionPipeline.from_pretrained(
    "runwayml/stable-diffusion-v1-5",
-
+    
    torch_dtype=torch.float16,
 )
 pipe = pipe.to("cuda")
@@ -122,7 +122,7 @@ from diffusers import StableDiffusionPipeline

 pipe = StableDiffusionPipeline.from_pretrained(
    "runwayml/stable-diffusion-v1-5",
-
+    
    torch_dtype=torch.float16,
 )
 pipe = pipe.to("cuda")
@@ -148,7 +148,7 @@ from diffusers import StableDiffusionPipeline

 pipe = StableDiffusionPipeline.from_pretrained(
    "runwayml/stable-diffusion-v1-5",
-
+    
    torch_dtype=torch.float16,
 )

@@ -165,7 +165,7 @@ image = pipe(prompt).images[0]
 또 다른 최적화 방법인 <a href="#model_offloading">모델 오프로딩</a>을 사용하는 것을 고려하십시오. 이는 훨씬 빠르지만 메모리 절약이 크지는 않습니다.
 </Tip>

-또한 ttention slicing과 연결해서 최소 메모리(< 2GB)로도 동작할 수 있습니다.
+또한 ttention slicing과 연결해서 최소 메모리(< 2GB)로도 동작할 수 있습니다. 


 ```Python
@@ -174,7 +174,7 @@ from diffusers import StableDiffusionPipeline

 pipe = StableDiffusionPipeline.from_pretrained(
    "runwayml/stable-diffusion-v1-5",
-
+    
    torch_dtype=torch.float16,
 )

@@ -204,7 +204,7 @@ import torch
 from diffusers import StableDiffusionPipeline

 pipe = StableDiffusionPipeline.from_pretrained(
-    "runwayml/stable-diffusion-v1-5",
+    "runwayml/stable-diffusion-v1-5",  
    torch_dtype=torch.float16,
 )

@@ -355,7 +355,7 @@ unet_traced = torch.jit.load("unet_traced.pt")
 class TracedUNet(torch.nn.Module):
    def __init__(self):
        super().__init__()
-        self.in_channels = pipe.unet.config.in_channels
+        self.in_channels = pipe.unet.in_channels
        self.device = pipe.unet.device

    def forward(self, latent_model_input, t, encoder_hidden_states):
@@ -387,7 +387,7 @@ with torch.inference_mode():
 | A100-SXM4-40GB    	| 18.6it/s            	| 29.it/s                        	|
 | A100-SXM-80GB    	| 18.7it/s            	| 29.5it/s                        	|

-이를 활용하려면 다음을 만족해야 합니다:
+이를 활용하려면 다음을 만족해야 합니다: 
 - PyTorch > 1.12
 - Cuda 사용 가능
 - [xformers 라이브러리를 설치함](xformers)
@@ -14,7 +14,7 @@ specific language governing permissions and limitations under the License.

 [[open-in-colab]]

-🧨 Diffusers는 사용자 친화적이며 유연한 도구 상자로, 사용사례에 맞게 diffusion 시스템을 구축 할 수 있도록 설계되었습니다. 이 도구 상자의 핵심은 모델과 스케줄러입니다. [`DiffusionPipeline`]은 편의를 위해 이러한 구성 요소를 번들로 제공하지만, 파이프라인을 분리하고 모델과 스케줄러를 개별적으로 사용해 새로운 diffusion 시스템을 만들 수도 있습니다.
+🧨 Diffusers는 사용자 친화적이며 유연한 도구 상자로, 사용사례에 맞게 diffusion 시스템을 구축 할 수 있도록 설계되었습니다. 이 도구 상자의 핵심은 모델과 스케줄러입니다. [`DiffusionPipeline`]은 편의를 위해 이러한 구성 요소를 번들로 제공하지만, 파이프라인을 분리하고 모델과 스케줄러를 개별적으로 사용해 새로운 diffusion 시스템을 만들 수도 있습니다. 

 이 튜토리얼에서는 기본 파이프라인부터 시작해 Stable Diffusion 파이프라인까지 진행하며 모델과 스케줄러를 사용해 추론을 위한 diffusion 시스템을 조립하는 방법을 배웁니다.

@@ -36,7 +36,7 @@ specific language governing permissions and limitations under the License.

 정말 쉽습니다. 그런데 파이프라인은 어떻게 이렇게 할 수 있었을까요? 파이프라인을 세분화하여 내부에서 어떤 일이 일어나고 있는지 살펴보겠습니다.

-위 예시에서 파이프라인에는 [`UNet2DModel`] 모델과 [`DDPMScheduler`]가 포함되어 있습니다. 파이프라인은 원하는 출력 크기의 랜덤 노이즈를 받아 모델을 여러번 통과시켜 이미지의 노이즈를 제거합니다. 각 timestep에서 모델은 *noise residual*을 예측하고 스케줄러는 이를 사용하여 노이즈가 적은 이미지를 예측합니다. 파이프라인은 지정된 추론 스텝수에 도달할 때까지 이 과정을 반복합니다.
+위 예시에서 파이프라인에는 [`UNet2DModel`] 모델과 [`DDPMScheduler`]가 포함되어 있습니다. 파이프라인은 원하는 출력 크기의 랜덤 노이즈를 받아 모델을 여러번 통과시켜 이미지의 노이즈를 제거합니다. 각 timestep에서 모델은 *noise residual*을 예측하고 스케줄러는 이를 사용하여 노이즈가 적은 이미지를 예측합니다. 파이프라인은 지정된 추론 스텝수에 도달할 때까지 이 과정을 반복합니다. 

 모델과 스케줄러를 별도로 사용하여 파이프라인을 다시 생성하기 위해 자체적인 노이즈 제거 프로세스를 작성해 보겠습니다.

@@ -210,7 +210,7 @@ Stable Diffusion 은 text-to-image *latent diffusion* 모델입니다. latent di

 ```py
 >>> latents = torch.randn(
-...     (batch_size, unet.config.in_channels, height // 8, width // 8),
+...     (batch_size, unet.in_channels, height // 8, width // 8),
 ...     generator=generator,
 ...     device=torch_device,
 ... )
@@ -42,7 +42,7 @@ Training examples show how to pretrain or fine-tune diffusion models for a varie
 | [**Dreambooth**](./dreambooth) | ✅ | - | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/sd_dreambooth_training.ipynb)
 | [**ControlNet**](./controlnet) | ✅ | ✅ | -
 | [**InstructPix2Pix**](./instruct_pix2pix) | ✅ | ✅ | -
-| [**Reinforcement Learning for Control**](./reinforcement_learning)                    | - | - | coming soon.
+| [**Reinforcement Learning for Control**](https://github.com/huggingface/diffusers/blob/main/examples/reinforcement_learning/run_diffusers_locomotion.py)                    | - | - | coming soon.

 ## Community

@@ -259,55 +259,11 @@ pip install git+https://github.com/huggingface/peft.git
 **Inference** 
 The inference is the same as if you train a regular LoRA 🤗

-## Conducting EDM-style training
-
-It's now possible to perform EDM-style training as proposed in [Elucidating the Design Space of Diffusion-Based Generative Models](https://arxiv.org/abs/2206.00364). 
-
-simply set:
-
-```diff
-+  --do_edm_style_training \
-```
-
-Other SDXL-like models that use the EDM formulation, such as [playgroundai/playground-v2.5-1024px-aesthetic](https://huggingface.co/playgroundai/playground-v2.5-1024px-aesthetic), can also be DreamBooth'd with the script. Below is an example command:
-
-```bash
-accelerate launch train_dreambooth_lora_sdxl_advanced.py \
-  --pretrained_model_name_or_path="playgroundai/playground-v2.5-1024px-aesthetic"  \
-  --dataset_name="linoyts/3d_icon" \
-  --instance_prompt="3d icon in the style of TOK" \
-  --validation_prompt="a TOK icon of an astronaut riding a horse, in the style of TOK" \
-  --output_dir="3d-icon-SDXL-LoRA" \
-  --do_edm_style_training \
-  --caption_column="prompt" \
-  --mixed_precision="bf16" \
-  --resolution=1024 \
-  --train_batch_size=3 \
-  --repeats=1 \
-  --report_to="wandb"\
-  --gradient_accumulation_steps=1 \
-  --gradient_checkpointing \
-  --learning_rate=1.0 \
-  --text_encoder_lr=1.0 \
-  --optimizer="prodigy"\
-  --train_text_encoder_ti\
-  --train_text_encoder_ti_frac=0.5\
-  --lr_scheduler="constant" \
-  --lr_warmup_steps=0 \
-  --rank=8 \
-  --max_train_steps=1000 \
-  --checkpointing_steps=2000 \
-  --seed="0" \
-  --push_to_hub
-```
-
-> [!CAUTION]
-> Min-SNR gamma is not supported with the EDM-style training yet. When training with the PlaygroundAI model, it's recommended to not pass any "variant".

 ### Tips and Tricks
 Check out [these recommended practices](https://huggingface.co/blog/sdxl_lora_advanced_script#additional-good-practices)

 ## Running on Colab Notebook
-Check out [this notebook](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/SDXL_Dreambooth_LoRA_advanced_example.ipynb).
+Check out [this notebook](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/SDXL_DreamBooth_LoRA_advanced_example.ipynb). 
 to train using the advanced features (including pivotal tuning), and [this notebook](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/SDXL_DreamBooth_LoRA_.ipynb) to train on a free colab, using some of the advanced features (excluding pivotal tuning)

@@ -70,7 +70,7 @@ from diffusers.utils.import_utils import is_xformers_available


 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.28.0.dev0")
+check_min_version("0.27.0.dev0")

 logger = get_logger(__name__)

@@ -656,6 +656,7 @@ def parse_args(input_args=None):
    )
    parser.add_argument(
        "--use_dora",
+        type=bool,
        action="store_true",
        default=False,
        help=(
@@ -1214,7 +1215,7 @@ def main(args):

            xformers_version = version.parse(xformers.__version__)
            if xformers_version == version.parse("0.0.16"):
-                logger.warning(
+                logger.warn(
                    "xFormers 0.0.16 cannot be used for training in some GPUs. If you observe problems during training, "
                    "please update xFormers to at least 0.0.17. See https://huggingface.co/docs/diffusers/main/en/optimization/xformers for more details."
                )
@@ -1365,14 +1366,14 @@ def main(args):

    # Optimizer creation
    if not (args.optimizer.lower() == "prodigy" or args.optimizer.lower() == "adamw"):
-        logger.warning(
+        logger.warn(
            f"Unsupported choice of optimizer: {args.optimizer}.Supported optimizers include [adamW, prodigy]."
            "Defaulting to adamW"
        )
        args.optimizer = "adamw"

    if args.use_8bit_adam and not args.optimizer.lower() == "adamw":
-        logger.warning(
+        logger.warn(
            f"use_8bit_adam is ignored when optimizer is not set to 'AdamW'. Optimizer was "
            f"set to {args.optimizer.lower()}"
        )
@@ -1406,11 +1407,11 @@ def main(args):
        optimizer_class = prodigyopt.Prodigy

        if args.learning_rate <= 0.1:
-            logger.warning(
+            logger.warn(
                "Learning rate is too low. When using prodigy, it's generally better to set learning rate around 1.0"
            )
        if args.train_text_encoder and args.text_encoder_lr:
-            logger.warning(
+            logger.warn(
                f"Learning rates were provided both for the unet and the text encoder- e.g. text_encoder_lr:"
                f" {args.text_encoder_lr} and learning_rate: {args.learning_rate}. "
                f"When using prodigy only learning_rate is used as the initial learning rate."
@@ -14,11 +14,9 @@
 # See the License for the specific language governing permissions and

 import argparse
-import contextlib
 import gc
 import hashlib
 import itertools
-import json
 import logging
 import math
 import os
@@ -39,7 +37,7 @@ import transformers
 from accelerate import Accelerator
 from accelerate.logging import get_logger
 from accelerate.utils import DistributedDataParallelKwargs, ProjectConfiguration, set_seed
-from huggingface_hub import create_repo, hf_hub_download, upload_folder
+from huggingface_hub import create_repo, upload_folder
 from packaging import version
 from peft import LoraConfig, set_peft_model_state_dict
 from peft.utils import get_peft_model_state_dict
@@ -57,8 +55,6 @@ from diffusers import (
    AutoencoderKL,
    DDPMScheduler,
    DPMSolverMultistepScheduler,
-    EDMEulerScheduler,
-    EulerDiscreteScheduler,
    StableDiffusionXLPipeline,
    UNet2DConditionModel,
 )
@@ -78,25 +74,11 @@ from diffusers.utils.torch_utils import is_compiled_module


 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.28.0.dev0")
+check_min_version("0.27.0.dev0")

 logger = get_logger(__name__)


-def determine_scheduler_type(pretrained_model_name_or_path, revision):
-    model_index_filename = "model_index.json"
-    if os.path.isdir(pretrained_model_name_or_path):
-        model_index = os.path.join(pretrained_model_name_or_path, model_index_filename)
-    else:
-        model_index = hf_hub_download(
-            repo_id=pretrained_model_name_or_path, filename=model_index_filename, revision=revision
-        )
-
-    with open(model_index, "r") as f:
-        scheduler_type = json.load(f)["scheduler"][1]
-    return scheduler_type
-
-
 def save_model_card(
    repo_id: str,
    use_dora: bool,
@@ -388,11 +370,6 @@ def parse_args(input_args=None):
            " `args.validation_prompt` multiple times: `args.num_validation_images`."
        ),
    )
-    parser.add_argument(
-        "--do_edm_style_training",
-        action="store_true",
-        help="Flag to conduct training using the EDM formulation as introduced in https://arxiv.org/abs/2206.00364.",
-    )
    parser.add_argument(
        "--with_prior_preservation",
        default=False,
@@ -1140,8 +1117,6 @@ def main(args):
            "You cannot use both --report_to=wandb and --hub_token due to a security risk of exposing your token."
            " Please use `huggingface-cli login` to authenticate with the Hub."
        )
-    if args.do_edm_style_training and args.snr_gamma is not None:
-        raise ValueError("Min-SNR formulation is not supported when conducting EDM-style training.")

    logging_dir = Path(args.output_dir, args.logging_dir)

@@ -1259,19 +1234,7 @@ def main(args):
    )

    # Load scheduler and models
-    scheduler_type = determine_scheduler_type(args.pretrained_model_name_or_path, args.revision)
-    if "EDM" in scheduler_type:
-        args.do_edm_style_training = True
-        noise_scheduler = EDMEulerScheduler.from_pretrained(args.pretrained_model_name_or_path, subfolder="scheduler")
-        logger.info("Performing EDM-style training!")
-    elif args.do_edm_style_training:
-        noise_scheduler = EulerDiscreteScheduler.from_pretrained(
-            args.pretrained_model_name_or_path, subfolder="scheduler"
-        )
-        logger.info("Performing EDM-style training!")
-    else:
-        noise_scheduler = DDPMScheduler.from_pretrained(args.pretrained_model_name_or_path, subfolder="scheduler")
-
+    noise_scheduler = DDPMScheduler.from_pretrained(args.pretrained_model_name_or_path, subfolder="scheduler")
    text_encoder_one = text_encoder_cls_one.from_pretrained(
        args.pretrained_model_name_or_path, subfolder="text_encoder", revision=args.revision, variant=args.variant
    )
@@ -1289,12 +1252,7 @@ def main(args):
        revision=args.revision,
        variant=args.variant,
    )
-    latents_mean = latents_std = None
-    if hasattr(vae.config, "latents_mean") and vae.config.latents_mean is not None:
-        latents_mean = torch.tensor(vae.config.latents_mean).view(1, 4, 1, 1)
-    if hasattr(vae.config, "latents_std") and vae.config.latents_std is not None:
-        latents_std = torch.tensor(vae.config.latents_std).view(1, 4, 1, 1)
-
+    vae_scaling_factor = vae.config.scaling_factor
    unet = UNet2DConditionModel.from_pretrained(
        args.pretrained_model_name_or_path, subfolder="unet", revision=args.revision, variant=args.variant
    )
@@ -1359,7 +1317,7 @@ def main(args):

            xformers_version = version.parse(xformers.__version__)
            if xformers_version == version.parse("0.0.16"):
-                logger.warning(
+                logger.warn(
                    "xFormers 0.0.16 cannot be used for training in some GPUs. If you observe problems during training, "
                    "please update xFormers to at least 0.0.17. See https://huggingface.co/docs/diffusers/main/en/optimization/xformers for more details."
                )
@@ -1564,14 +1522,14 @@ def main(args):

    # Optimizer creation
    if not (args.optimizer.lower() == "prodigy" or args.optimizer.lower() == "adamw"):
-        logger.warning(
+        logger.warn(
            f"Unsupported choice of optimizer: {args.optimizer}.Supported optimizers include [adamW, prodigy]."
            "Defaulting to adamW"
        )
        args.optimizer = "adamw"

    if args.use_8bit_adam and not args.optimizer.lower() == "adamw":
-        logger.warning(
+        logger.warn(
            f"use_8bit_adam is ignored when optimizer is not set to 'AdamW'. Optimizer was "
            f"set to {args.optimizer.lower()}"
        )
@@ -1605,11 +1563,11 @@ def main(args):
        optimizer_class = prodigyopt.Prodigy

        if args.learning_rate <= 0.1:
-            logger.warning(
+            logger.warn(
                "Learning rate is too low. When using prodigy, it's generally better to set learning rate around 1.0"
            )
        if args.train_text_encoder and args.text_encoder_lr:
-            logger.warning(
+            logger.warn(
                f"Learning rates were provided both for the unet and the text encoder- e.g. text_encoder_lr:"
                f" {args.text_encoder_lr} and learning_rate: {args.learning_rate}. "
                f"When using prodigy only learning_rate is used as the initial learning rate."
@@ -1832,19 +1790,6 @@ def main(args):
        disable=not accelerator.is_local_main_process,
    )

-    def get_sigmas(timesteps, n_dim=4, dtype=torch.float32):
-        # TODO: revisit other sampling algorithms
-        sigmas = noise_scheduler.sigmas.to(device=accelerator.device, dtype=dtype)
-        schedule_timesteps = noise_scheduler.timesteps.to(accelerator.device)
-        timesteps = timesteps.to(accelerator.device)
-
-        step_indices = [(schedule_timesteps == t).nonzero().item() for t in timesteps]
-
-        sigma = sigmas[step_indices].flatten()
-        while len(sigma.shape) < n_dim:
-            sigma = sigma.unsqueeze(-1)
-        return sigma
-
    if args.train_text_encoder:
        num_train_epochs_text_encoder = int(args.train_text_encoder_frac * args.num_train_epochs)
    elif args.train_text_encoder_ti:  # args.train_text_encoder_ti
@@ -1896,15 +1841,9 @@ def main(args):
                    pixel_values = batch["pixel_values"].to(dtype=vae.dtype)
                    model_input = vae.encode(pixel_values).latent_dist.sample()

-                if latents_mean is None and latents_std is None:
-                    model_input = model_input * vae.config.scaling_factor
-                    if args.pretrained_vae_model_name_or_path is None:
-                        model_input = model_input.to(weight_dtype)
-                else:
-                    latents_mean = latents_mean.to(device=model_input.device, dtype=model_input.dtype)
-                    latents_std = latents_std.to(device=model_input.device, dtype=model_input.dtype)
-                    model_input = (model_input - latents_mean) * vae.config.scaling_factor / latents_std
-                    model_input = model_input.to(dtype=weight_dtype)
+                model_input = model_input * vae_scaling_factor
+                if args.pretrained_vae_model_name_or_path is None:
+                    model_input = model_input.to(weight_dtype)

                # Sample noise that we'll add to the latents
                noise = torch.randn_like(model_input)
@@ -1915,32 +1854,15 @@ def main(args):
                    )

                bsz = model_input.shape[0]
-
                # Sample a random timestep for each image
-                if not args.do_edm_style_training:
-                    timesteps = torch.randint(
-                        0, noise_scheduler.config.num_train_timesteps, (bsz,), device=model_input.device
-                    )
-                    timesteps = timesteps.long()
-                else:
-                    # in EDM formulation, the model is conditioned on the pre-conditioned noise levels
-                    # instead of discrete timesteps, so here we sample indices to get the noise levels
-                    # from `scheduler.timesteps`
-                    indices = torch.randint(0, noise_scheduler.config.num_train_timesteps, (bsz,))
-                    timesteps = noise_scheduler.timesteps[indices].to(device=model_input.device)
+                timesteps = torch.randint(
+                    0, noise_scheduler.config.num_train_timesteps, (bsz,), device=model_input.device
+                )
+                timesteps = timesteps.long()

                # Add noise to the model input according to the noise magnitude at each timestep
                # (this is the forward diffusion process)
                noisy_model_input = noise_scheduler.add_noise(model_input, noise, timesteps)
-                # For EDM-style training, we first obtain the sigmas based on the continuous timesteps.
-                # We then precondition the final model inputs based on these sigmas instead of the timesteps.
-                # Follow: Section 5 of https://arxiv.org/abs/2206.00364.
-                if args.do_edm_style_training:
-                    sigmas = get_sigmas(timesteps, len(noisy_model_input.shape), noisy_model_input.dtype)
-                    if "EDM" in scheduler_type:
-                        inp_noisy_latents = noise_scheduler.precondition_inputs(noisy_model_input, sigmas)
-                    else:
-                        inp_noisy_latents = noisy_model_input / ((sigmas**2 + 1) ** 0.5)

                # time ids
                add_time_ids = torch.cat(
@@ -1966,7 +1888,7 @@ def main(args):
                    }
                    prompt_embeds_input = prompt_embeds.repeat(elems_to_repeat_text_embeds, 1, 1)
                    model_pred = unet(
-                        inp_noisy_latents if args.do_edm_style_training else noisy_model_input,
+                        noisy_model_input,
                        timesteps,
                        prompt_embeds_input,
                        added_cond_kwargs=unet_added_conditions,
@@ -1984,42 +1906,14 @@ def main(args):
                    )
                    prompt_embeds_input = prompt_embeds.repeat(elems_to_repeat_text_embeds, 1, 1)
                    model_pred = unet(
-                        inp_noisy_latents if args.do_edm_style_training else noisy_model_input,
-                        timesteps,
-                        prompt_embeds_input,
-                        added_cond_kwargs=unet_added_conditions,
+                        noisy_model_input, timesteps, prompt_embeds_input, added_cond_kwargs=unet_added_conditions
                    ).sample

-                weighting = None
-                if args.do_edm_style_training:
-                    # Similar to the input preconditioning, the model predictions are also preconditioned
-                    # on noised model inputs (before preconditioning) and the sigmas.
-                    # Follow: Section 5 of https://arxiv.org/abs/2206.00364.
-                    if "EDM" in scheduler_type:
-                        model_pred = noise_scheduler.precondition_outputs(noisy_model_input, model_pred, sigmas)
-                    else:
-                        if noise_scheduler.config.prediction_type == "epsilon":
-                            model_pred = model_pred * (-sigmas) + noisy_model_input
-                        elif noise_scheduler.config.prediction_type == "v_prediction":
-                            model_pred = model_pred * (-sigmas / (sigmas**2 + 1) ** 0.5) + (
-                                noisy_model_input / (sigmas**2 + 1)
-                            )
-                    # We are not doing weighting here because it tends result in numerical problems.
-                    # See: https://github.com/huggingface/diffusers/pull/7126#issuecomment-1968523051
-                    # There might be other alternatives for weighting as well:
-                    # https://github.com/huggingface/diffusers/pull/7126#discussion_r1505404686
-                    if "EDM" not in scheduler_type:
-                        weighting = (sigmas**-2.0).float()
-
                # Get the target for loss depending on the prediction type
                if noise_scheduler.config.prediction_type == "epsilon":
-                    target = model_input if args.do_edm_style_training else noise
+                    target = noise
                elif noise_scheduler.config.prediction_type == "v_prediction":
-                    target = (
-                        model_input
-                        if args.do_edm_style_training
-                        else noise_scheduler.get_velocity(model_input, noise, timesteps)
-                    )
+                    target = noise_scheduler.get_velocity(model_input, noise, timesteps)
                else:
                    raise ValueError(f"Unknown prediction type {noise_scheduler.config.prediction_type}")

@@ -2029,28 +1923,10 @@ def main(args):
                    target, target_prior = torch.chunk(target, 2, dim=0)

                    # Compute prior loss
-                    if weighting is not None:
-                        prior_loss = torch.mean(
-                            (weighting.float() * (model_pred_prior.float() - target_prior.float()) ** 2).reshape(
-                                target_prior.shape[0], -1
-                            ),
-                            1,
-                        )
-                        prior_loss = prior_loss.mean()
-                    else:
-                        prior_loss = F.mse_loss(model_pred_prior.float(), target_prior.float(), reduction="mean")
+                    prior_loss = F.mse_loss(model_pred_prior.float(), target_prior.float(), reduction="mean")

                if args.snr_gamma is None:
-                    if weighting is not None:
-                        loss = torch.mean(
-                            (weighting.float() * (model_pred.float() - target.float()) ** 2).reshape(
-                                target.shape[0], -1
-                            ),
-                            1,
-                        )
-                        loss = loss.mean()
-                    else:
-                        loss = F.mse_loss(model_pred.float(), target.float(), reduction="mean")
+                    loss = F.mse_loss(model_pred.float(), target.float(), reduction="mean")
                else:
                    # Compute loss-weights as per Section 3.4 of https://arxiv.org/abs/2303.09556.
                    # Since we predict the noise instead of x_0, the original formulation is slightly changed.
@@ -2173,18 +2049,17 @@ def main(args):
                # We train on the simplified learning objective. If we were previously predicting a variance, we need the scheduler to ignore it
                scheduler_args = {}

-                if not args.do_edm_style_training:
-                    if "variance_type" in pipeline.scheduler.config:
-                        variance_type = pipeline.scheduler.config.variance_type
+                if "variance_type" in pipeline.scheduler.config:
+                    variance_type = pipeline.scheduler.config.variance_type

-                        if variance_type in ["learned", "learned_range"]:
-                            variance_type = "fixed_small"
+                    if variance_type in ["learned", "learned_range"]:
+                        variance_type = "fixed_small"

-                        scheduler_args["variance_type"] = variance_type
+                    scheduler_args["variance_type"] = variance_type

-                    pipeline.scheduler = DPMSolverMultistepScheduler.from_config(
-                        pipeline.scheduler.config, **scheduler_args
-                    )
+                pipeline.scheduler = DPMSolverMultistepScheduler.from_config(
+                    pipeline.scheduler.config, **scheduler_args
+                )

                pipeline = pipeline.to(accelerator.device)
                pipeline.set_progress_bar_config(disable=True)
@@ -2192,13 +2067,8 @@ def main(args):
                # run inference
                generator = torch.Generator(device=accelerator.device).manual_seed(args.seed) if args.seed else None
                pipeline_args = {"prompt": args.validation_prompt}
-                inference_ctx = (
-                    contextlib.nullcontext()
-                    if "playground" in args.pretrained_model_name_or_path
-                    else torch.cuda.amp.autocast()
-                )

-                with inference_ctx:
+                with torch.cuda.amp.autocast():
                    images = [
                        pipeline(**pipeline_args, generator=generator).images[0]
                        for _ in range(args.num_validation_images)
@@ -2274,18 +2144,15 @@ def main(args):
            # We train on the simplified learning objective. If we were previously predicting a variance, we need the scheduler to ignore it
            scheduler_args = {}

-            if not args.do_edm_style_training:
-                if "variance_type" in pipeline.scheduler.config:
-                    variance_type = pipeline.scheduler.config.variance_type
+            if "variance_type" in pipeline.scheduler.config:
+                variance_type = pipeline.scheduler.config.variance_type

-                    if variance_type in ["learned", "learned_range"]:
-                        variance_type = "fixed_small"
+                if variance_type in ["learned", "learned_range"]:
+                    variance_type = "fixed_small"

-                    scheduler_args["variance_type"] = variance_type
+                scheduler_args["variance_type"] = variance_type

-                pipeline.scheduler = DPMSolverMultistepScheduler.from_config(
-                    pipeline.scheduler.config, **scheduler_args
-                )
+            pipeline.scheduler = DPMSolverMultistepScheduler.from_config(pipeline.scheduler.config, **scheduler_args)

            # load attention processors
            pipeline.load_lora_weights(args.output_dir)
@@ -1,12 +1,10 @@
-# Community Pipeline Examples
+# Community Examples

 > **For more information about community pipelines, please have a look at [this issue](https://github.com/huggingface/diffusers/issues/841).**

-**Community pipeline** examples consist pipelines that have been added by the community.
-Please have a look at the following tables to get an overview of all community examples. Click on the **Code Example** to get a copy-and-paste ready code example that you can try out.
-If a community pipeline doesn't work as expected, please open an issue and ping the author on it.
-
-Please also check out our [Community Scripts](https://github.com/huggingface/diffusers/blob/main/examples/community/README_community_scripts.md) examples for tips and tricks that you can use with diffusers without having to run a community pipeline.
+**Community** examples consist of both inference and training examples that have been added by the community.
+Please have a look at the following table to get an overview of all community examples. Click on the **Code Example** to get a copy-and-paste ready code example that you can try out.
+If a community doesn't work as expected, please open an issue and ping the author on it.

 | Example                                                                                                                               | Description                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              | Code Example                                                                              | Colab                                                                                                                                                                                                              |                                                        Author |
 |:--------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|--------------------------------------------------------------:|
@@ -85,25 +83,14 @@ This depth estimation pipeline processes a single input image through multiple d

 ```python
 import numpy as np
-import torch
 from PIL import Image
 from diffusers import DiffusionPipeline
 from diffusers.utils import load_image

-# Original DDIM version (higher quality)
 pipe = DiffusionPipeline.from_pretrained(
-    "prs-eth/marigold-v1-0",
+    "Bingxin/Marigold",
    custom_pipeline="marigold_depth_estimation"
    # torch_dtype=torch.float16,                # (optional) Run with half-precision (16-bit float).
-    # variant="fp16",                           # (optional) Use with `torch_dtype=torch.float16`, to directly load fp16 checkpoint
-)
-
-# (New) LCM version (faster speed)
-pipe = DiffusionPipeline.from_pretrained(
-    "prs-eth/marigold-lcm-v1-0",
-    custom_pipeline="marigold_depth_estimation"
-    # torch_dtype=torch.float16,                # (optional) Run with half-precision (16-bit float).
-    # variant="fp16",                           # (optional) Use with `torch_dtype=torch.float16`, to directly load fp16 checkpoint
 )

 pipe.to("cuda")
@@ -112,21 +99,12 @@ img_path_or_url = "https://share.phys.ethz.ch/~pf/bingkedata/marigold/pipeline_e
 image: Image.Image = load_image(img_path_or_url)

 pipeline_output = pipe(
-    image,                    # Input image.
-    # ----- recommended setting for DDIM version -----
+    image,                  # Input image.
    # denoising_steps=10,     # (optional) Number of denoising steps of each inference pass. Default: 10.
    # ensemble_size=10,       # (optional) Number of inference passes in the ensemble. Default: 10.
-    # ------------------------------------------------
-    
-    # ----- recommended setting for LCM version ------
-    # denoising_steps=4,
-    # ensemble_size=5,
-    # -------------------------------------------------
-    
    # processing_res=768,     # (optional) Maximum resolution of processing. If set to 0: will not resize at all. Defaults to 768.
    # match_input_res=True,   # (optional) Resize depth prediction to match input resolution.
    # batch_size=0,           # (optional) Inference batch size, no bigger than `num_ensemble`. If set to 0, the script will automatically decide the proper batch size. Defaults to 0.
-    # seed=2024,              # (optional) Random seed can be set to ensure additional reproducibility. Default: None (unseeded). Note: forcing --batch_size 1 helps to increase reproducibility. To ensure full reproducibility, deterministic mode needs to be used.
    # color_map="Spectral",   # (optional) Colormap used to colorize the depth map. Defaults to "Spectral". Set to `None` to skip colormap generation.
    # show_progress_bar=True, # (optional) If true, will show progress bars of the inference progress.
 )
@@ -955,7 +933,7 @@ image = pipe(prompt, generator=generator, num_inference_steps=50).images[0]
 ### Checkpoint Merger Pipeline
 Based on the AUTOMATIC1111/webui for checkpoint merging. This is a custom pipeline that merges upto 3 pretrained model checkpoints as long as they are in the HuggingFace model_index.json format.

-The checkpoint merging is currently memory intensive as it modifies the weights of a DiffusionPipeline object in place. Expect at least 13GB RAM Usage on Kaggle GPU kernels and
+The checkpoint merging is currently memory intensive as it modifies the weights of a DiffusionPipeline object in place. Expect atleast 13GB RAM Usage on Kaggle GPU kernels and
 on colab you might run out of the 12GB memory even while merging two checkpoints.

 Usage:-
@@ -1909,7 +1887,7 @@ In the above code, the `prompt2` is appended to the `prompt`, which is more than

 For more results, checkout [PR #6114](https://github.com/huggingface/diffusers/pull/6114).

-### Example Images Mixing (with CoCa)
+## Example Images Mixing (with CoCa)
 ```python
 import requests
 from io import BytesIO
@@ -2956,7 +2934,7 @@ pipe(prompt =prompt, rp_args = rp_args)

 The Pipeline supports `compel` syntax. Input prompts using the `compel` structure will be automatically applied and processed.

-### Diffusion Posterior Sampling Pipeline
+## Diffusion Posterior Sampling Pipeline
 * Reference paper
    ```
    @article{chung2022diffusion,
@@ -3763,80 +3741,3 @@ onestep_image = pipe(prompt, num_inference_steps=1).images[0]
 # Multistep sampling
 multistep_image = pipe(prompt, num_inference_steps=4).images[0]
 ```
-
-# Perturbed-Attention Guidance
-
-[Project](https://ku-cvlab.github.io/Perturbed-Attention-Guidance/) / [arXiv](https://arxiv.org/abs/2403.17377) / [GitHub](https://github.com/KU-CVLAB/Perturbed-Attention-Guidance)
-
-This implementation is based on [Diffusers](https://huggingface.co/docs/diffusers/index). StableDiffusionPAGPipeline is a modification of StableDiffusionPipeline to support Perturbed-Attention Guidance (PAG).
-
-## Example Usage
-
-```
-import os
-import torch
-
-from accelerate.utils import set_seed
-
-from diffusers import StableDiffusionPipeline
-from diffusers.utils import load_image, make_image_grid
-from diffusers.utils.torch_utils import randn_tensor
-
-pipe = StableDiffusionPipeline.from_pretrained(
-    "runwayml/stable-diffusion-v1-5",
-    custom_pipeline="hyoungwoncho/sd_perturbed_attention_guidance",
-    torch_dtype=torch.float16
-)
-
-device="cuda"
-pipe = pipe.to(device)
-
-pag_scale = 5.0
-pag_applied_layers_index = ['m0']
-
-batch_size = 4
-seed=10
-
-base_dir = "./results/"
-grid_dir = base_dir + "/pag" + str(pag_scale) + "/"
-
-if not os.path.exists(grid_dir):
-    os.makedirs(grid_dir)
-
-set_seed(seed)
-
-latent_input = randn_tensor(shape=(batch_size,4,64,64),generator=None, device=device, dtype=torch.float16)
-
-output_baseline = pipe(
-    "",
-    width=512,
-    height=512,
-    num_inference_steps=50,
-    guidance_scale=0.0,
-    pag_scale=0.0,
-    pag_applied_layers_index=pag_applied_layers_index,
-    num_images_per_prompt=batch_size,
-    latents=latent_input
-).images
-
-output_pag = pipe(
-    "",
-    width=512,
-    height=512,
-    num_inference_steps=50,
-    guidance_scale=0.0,
-    pag_scale=5.0,
-    pag_applied_layers_index=pag_applied_layers_index,
-    num_images_per_prompt=batch_size,
-    latents=latent_input
-).images
-
-grid_image = make_image_grid(output_baseline + output_pag, rows=2, cols=batch_size)
-grid_image.save(grid_dir + "sample.png")
-```
-
-## PAG Parameters
-
-pag_scale : gudiance scale of PAG (ex: 5.0)
-
-pag_applied_layers_index : index of the layer to apply perturbation (ex: ['m0'])
@@ -1,232 +0,0 @@
-# Community Scripts
-
-**Community scripts** consist of inference examples using Diffusers pipelines that have been added by the community. 
-Please have a look at the following table to get an overview of all community examples. Click on the **Code Example** to get a copy-and-paste code example that you can try out.
-If a community script doesn't work as expected, please open an issue and ping the author on it.
-
-| Example                                                                                                                               | Description                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              | Code Example                                                                              | Colab                                                                                                                                                                                                              |                                                        Author |
-|:--------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|--------------------------------------------------------------:|
-| Using IP-Adapter with negative noise                                                                                                  | Using negative noise with IP-adapter to better control the generation (see the [original post](https://github.com/huggingface/diffusers/discussions/7167) on the forum for more details)                                                                                                                                                                                                                                                    | [IP-Adapter Negative Noise](#ip-adapter-negative-noise)                                   | | [Álvaro Somoza](https://github.com/asomoza)|
-| asymmetric tiling                                                                                                  |configure seamless image tiling independently for the X and Y axes                                                                                                                                                                                                      | [Asymmetric Tiling](#asymmetric-tiling )                                   | | [alexisrolland](https://github.com/alexisrolland)|
-
-
-## Example usages
-
-### IP Adapter Negative Noise
-
-Diffusers pipelines are fully integrated with IP-Adapter, which allows you to prompt the diffusion model with an image. However, it does not support negative image prompts (there is no `negative_ip_adapter_image` argument) the same way it supports negative text prompts. When you pass an `ip_adapter_image,` it will create a zero-filled tensor as a negative image. This script shows you how to create a negative noise from `ip_adapter_image` and use it to significantly improve the generation quality while preserving the composition of images.
-
-[cubiq](https://github.com/cubiq) initially developed this feature in his [repository](https://github.com/cubiq/ComfyUI_IPAdapter_plus). The community script was contributed by [asomoza](https://github.com/Somoza). You can find more details about this experimentation [this discussion](https://github.com/huggingface/diffusers/discussions/7167)
-
-IP-Adapter without negative noise
-|source|result|
-|---|---|
-|![20240229150812](https://github.com/huggingface/diffusers/assets/5442875/901d8bd8-7a59-4fe7-bda1-a0e0d6c7dffd)|![20240229163923_normal](https://github.com/huggingface/diffusers/assets/5442875/3432e25a-ece6-45f4-a3f4-fca354f40b5b)|
-
-IP-Adapter with negative noise
-|source|result|
-|---|---|
-|![20240229150812](https://github.com/huggingface/diffusers/assets/5442875/901d8bd8-7a59-4fe7-bda1-a0e0d6c7dffd)|![20240229163923](https://github.com/huggingface/diffusers/assets/5442875/736fd15a-36ba-40c0-a7d8-6ec1ac26f788)|
-
-```python
-import torch
-
-from diffusers import AutoencoderKL, DPMSolverMultistepScheduler, StableDiffusionXLPipeline
-from diffusers.models import ImageProjection
-from diffusers.utils import load_image
-
-
-def encode_image(
-    image_encoder,
-    feature_extractor,
-    image,
-    device,
-    num_images_per_prompt,
-    output_hidden_states=None,
-    negative_image=None,
-):
-    dtype = next(image_encoder.parameters()).dtype
-
-    if not isinstance(image, torch.Tensor):
-        image = feature_extractor(image, return_tensors="pt").pixel_values
-
-    image = image.to(device=device, dtype=dtype)
-    if output_hidden_states:
-        image_enc_hidden_states = image_encoder(image, output_hidden_states=True).hidden_states[-2]
-        image_enc_hidden_states = image_enc_hidden_states.repeat_interleave(num_images_per_prompt, dim=0)
-
-        if negative_image is None:
-            uncond_image_enc_hidden_states = image_encoder(
-                torch.zeros_like(image), output_hidden_states=True
-            ).hidden_states[-2]
-        else:
-            if not isinstance(negative_image, torch.Tensor):
-                negative_image = feature_extractor(negative_image, return_tensors="pt").pixel_values
-            negative_image = negative_image.to(device=device, dtype=dtype)
-            uncond_image_enc_hidden_states = image_encoder(negative_image, output_hidden_states=True).hidden_states[-2]
-
-        uncond_image_enc_hidden_states = uncond_image_enc_hidden_states.repeat_interleave(num_images_per_prompt, dim=0)
-        return image_enc_hidden_states, uncond_image_enc_hidden_states
-    else:
-        image_embeds = image_encoder(image).image_embeds
-        image_embeds = image_embeds.repeat_interleave(num_images_per_prompt, dim=0)
-        uncond_image_embeds = torch.zeros_like(image_embeds)
-
-        return image_embeds, uncond_image_embeds
-
-
-@torch.no_grad()
-def prepare_ip_adapter_image_embeds(
-    unet,
-    image_encoder,
-    feature_extractor,
-    ip_adapter_image,
-    do_classifier_free_guidance,
-    device,
-    num_images_per_prompt,
-    ip_adapter_negative_image=None,
-):
-    if not isinstance(ip_adapter_image, list):
-        ip_adapter_image = [ip_adapter_image]
-
-    if len(ip_adapter_image) != len(unet.encoder_hid_proj.image_projection_layers):
-        raise ValueError(
-            f"`ip_adapter_image` must have same length as the number of IP Adapters. Got {len(ip_adapter_image)} images and {len(unet.encoder_hid_proj.image_projection_layers)} IP Adapters."
-        )
-
-    image_embeds = []
-    for single_ip_adapter_image, image_proj_layer in zip(
-        ip_adapter_image, unet.encoder_hid_proj.image_projection_layers
-    ):
-        output_hidden_state = not isinstance(image_proj_layer, ImageProjection)
-        single_image_embeds, single_negative_image_embeds = encode_image(
-            image_encoder,
-            feature_extractor,
-            single_ip_adapter_image,
-            device,
-            1,
-            output_hidden_state,
-            negative_image=ip_adapter_negative_image,
-        )
-        single_image_embeds = torch.stack([single_image_embeds] * num_images_per_prompt, dim=0)
-        single_negative_image_embeds = torch.stack([single_negative_image_embeds] * num_images_per_prompt, dim=0)
-
-        if do_classifier_free_guidance:
-            single_image_embeds = torch.cat([single_negative_image_embeds, single_image_embeds])
-            single_image_embeds = single_image_embeds.to(device)
-
-        image_embeds.append(single_image_embeds)
-
-    return image_embeds
-
-
-vae = AutoencoderKL.from_pretrained(
-    "madebyollin/sdxl-vae-fp16-fix",
-    torch_dtype=torch.float16,
-).to("cuda")
-
-pipeline = StableDiffusionXLPipeline.from_pretrained(
-    "RunDiffusion/Juggernaut-XL-v9",
-    torch_dtype=torch.float16,
-    vae=vae,
-    variant="fp16",
-).to("cuda")
-
-pipeline.scheduler = DPMSolverMultistepScheduler.from_config(pipeline.scheduler.config)
-pipeline.scheduler.config.use_karras_sigmas = True
-
-pipeline.load_ip_adapter(
-    "h94/IP-Adapter",
-    subfolder="sdxl_models",
-    weight_name="ip-adapter-plus_sdxl_vit-h.safetensors",
-    image_encoder_folder="models/image_encoder",
-)
-pipeline.set_ip_adapter_scale(0.7)
-
-ip_image = load_image("source.png")
-negative_ip_image = load_image("noise.png")
-
-image_embeds = prepare_ip_adapter_image_embeds(
-    unet=pipeline.unet,
-    image_encoder=pipeline.image_encoder,
-    feature_extractor=pipeline.feature_extractor,
-    ip_adapter_image=[[ip_image]],
-    do_classifier_free_guidance=True,
-    device="cuda",
-    num_images_per_prompt=1,
-    ip_adapter_negative_image=negative_ip_image,
-)
-
-
-prompt = "cinematic photo of a cyborg in the city, 4k, high quality, intricate, highly detailed"
-negative_prompt = "blurry, smooth, plastic"
-
-image = pipeline(
-    prompt=prompt,
-    negative_prompt=negative_prompt,
-    ip_adapter_image_embeds=image_embeds,
-    guidance_scale=6.0,
-    num_inference_steps=25,
-    generator=torch.Generator(device="cpu").manual_seed(1556265306),
-).images[0]
-
-image.save("result.png")
-```
-
-### Asymmetric Tiling
-Stable Diffusion is not trained to generate seamless textures. However, you can use this simple script to add tiling to your generation. This script is contributed by [alexisrolland](https://github.com/alexisrolland). See more details in the [this issue](https://github.com/huggingface/diffusers/issues/556)
-
-
-|Generated|Tiled|
-|---|---|
-|![20240313003235_573631814](https://github.com/huggingface/diffusers/assets/5442875/eca174fb-06a4-464e-a3a7-00dbb024543e)|![wall](https://github.com/huggingface/diffusers/assets/5442875/b4aa774b-2a6a-4316-a8eb-8f30b5f4d024)|
-
-
-```py
-import torch
-from typing import Optional
-from diffusers import StableDiffusionPipeline
-from diffusers.models.lora import LoRACompatibleConv
-
-def seamless_tiling(pipeline, x_axis, y_axis):
-    def asymmetric_conv2d_convforward(self, input: torch.Tensor, weight: torch.Tensor, bias: Optional[torch.Tensor] = None):
-        self.paddingX = (self._reversed_padding_repeated_twice[0], self._reversed_padding_repeated_twice[1], 0, 0)
-        self.paddingY = (0, 0, self._reversed_padding_repeated_twice[2], self._reversed_padding_repeated_twice[3])
-        working = torch.nn.functional.pad(input, self.paddingX, mode=x_mode)
-        working = torch.nn.functional.pad(working, self.paddingY, mode=y_mode)
-        return torch.nn.functional.conv2d(working, weight, bias, self.stride, torch.nn.modules.utils._pair(0), self.dilation, self.groups)
-    x_mode = 'circular' if x_axis else 'constant'
-    y_mode = 'circular' if y_axis else 'constant'
-    targets = [pipeline.vae, pipeline.text_encoder, pipeline.unet]
-    convolution_layers = []
-    for target in targets:
-        for module in target.modules():
-            if isinstance(module, torch.nn.Conv2d):
-                convolution_layers.append(module)
-    for layer in convolution_layers:
-        if isinstance(layer, LoRACompatibleConv) and layer.lora_layer is None:
-            layer.lora_layer = lambda * x: 0
-        layer._conv_forward = asymmetric_conv2d_convforward.__get__(layer, torch.nn.Conv2d)
-    return pipeline
-
-pipeline = StableDiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16, use_safetensors=True)
-pipeline.enable_model_cpu_offload()
-prompt = ["texture of a red brick wall"]
-seed = 123456
-generator = torch.Generator(device='cuda').manual_seed(seed)
-
-pipeline = seamless_tiling(pipeline=pipeline, x_axis=True, y_axis=True)
-image = pipeline(
-    prompt=prompt,
-    width=512,
-    height=512,
-    num_inference_steps=20,
-    guidance_scale=7,
-    num_images_per_prompt=1,
-    generator=generator
-).images[0]
-seamless_tiling(pipeline=pipeline, x_axis=False, y_axis=False)
-
-torch.cuda.empty_cache()
-image.save('image.png')
-```
@@ -103,7 +103,7 @@ class CheckpointMergerPipeline(DiffusionPipeline):
        print(f"Combining with alpha={alpha}, interpolation mode={interp}")

        checkpoint_count = len(pretrained_model_name_or_path_list)
-        # Ignore result from model_index_json comparison of the two checkpoints
+        # Ignore result from model_index_json comparision of the two checkpoints
        force = kwargs.pop("force", False)

        # If less than 2 checkpoints, nothing to merge. If more than 3, not supported for now.
@@ -217,7 +217,7 @@ class CheckpointMergerPipeline(DiffusionPipeline):
                        ]
                        checkpoint_path_2 = files[0] if len(files) > 0 else None
                # For an attr if both checkpoint_path_1 and 2 are None, ignore.
-                # If at least one is present, deal with it according to interp method, of course only if the state_dict keys match.
+                # If atleast one is present, deal with it according to interp method, of course only if the state_dict keys match.
                if checkpoint_path_1 is None and checkpoint_path_2 is None:
                    print(f"Skipping {attr}: not present in 2nd or 3d model")
                    continue
@@ -1,8 +1,7 @@
 """
-modeled after the textual_inversion.py / train_dreambooth.py and the work
-of justinpinkney here: https://github.com/justinpinkney/stable-diffusion/blob/main/notebooks/imagic.ipynb
+    modeled after the textual_inversion.py / train_dreambooth.py and the work
+    of justinpinkney here: https://github.com/justinpinkney/stable-diffusion/blob/main/notebooks/imagic.ipynb
 """
-
 import inspect
 import warnings
 from typing import List, Optional, Union
@@ -440,7 +440,7 @@ def betas_for_alpha_bar(
            return math.exp(t * -12.0)

    else:
-        raise ValueError(f"Unsupported alpha_transform_type: {alpha_transform_type}")
+        raise ValueError(f"Unsupported alpha_tranform_type: {alpha_transform_type}")

    betas = []
    for i in range(num_diffusion_timesteps):
@@ -513,7 +513,9 @@ class LCMSchedulerWithTimestamp(SchedulerMixin, ConfigMixin):
            there is no previous alpha. When this option is `True` the previous alpha product is fixed to `1`,
            otherwise it uses the alpha value at step 0.
        steps_offset (`int`, defaults to 0):
-            An offset added to the inference steps, as required by some model families.
+            An offset added to the inference steps. You can use a combination of `offset=1` and
+            `set_alpha_to_one=False` to make the last step use step 0 for the previous alpha product like in Stable
+            Diffusion.
        prediction_type (`str`, defaults to `epsilon`, *optional*):
            Prediction type of the scheduler function; can be `epsilon` (predicts the noise of the diffusion process),
            `sample` (directly predicts the noisy sample`) or `v_prediction` (see section 2.4 of [Imagen
@@ -726,7 +726,7 @@ class LatentConsistencyModelWalkPipeline(
            callback_on_step_end_tensor_inputs (`List`, *optional*):
                The list of tensor inputs for the `callback_on_step_end` function. The tensors specified in the list
                will be passed as `callback_kwargs` argument. You will only be able to include variables listed in the
-                `._callback_tensor_inputs` attribute of your pipeline class.
+                `._callback_tensor_inputs` attribute of your pipeine class.
            embedding_interpolation_type (`str`, *optional*, defaults to `"lerp"`):
                The type of interpolation to use for interpolating between text embeddings. Choose between `"lerp"` and `"slerp"`.
            latent_interpolation_type (`str`, *optional*, defaults to `"slerp"`):
@@ -779,7 +779,7 @@ class LatentConsistencyModelWalkPipeline(
        else:
            batch_size = prompt_embeds.shape[0]
        if batch_size < 2:
-            raise ValueError(f"`prompt` must have length of at least 2 but found {batch_size}")
+            raise ValueError(f"`prompt` must have length of atleast 2 but found {batch_size}")
        if num_images_per_prompt != 1:
            raise ValueError("`num_images_per_prompt` must be `1` as no other value is supported yet")
        if prompt_embeds is not None:
@@ -883,7 +883,7 @@ class LatentConsistencyModelWalkPipeline(
                ) as batch_progress_bar:
                    for batch_index in range(0, bs, process_batch_size):
                        batch_inference_latents = inference_latents[batch_index : batch_index + process_batch_size]
-                        batch_inference_embeddings = inference_embeddings[
+                        batch_inference_embedddings = inference_embeddings[
                            batch_index : batch_index + process_batch_size
                        ]

@@ -892,7 +892,7 @@ class LatentConsistencyModelWalkPipeline(
                        )
                        timesteps = self.scheduler.timesteps

-                        current_bs = batch_inference_embeddings.shape[0]
+                        current_bs = batch_inference_embedddings.shape[0]
                        w = torch.tensor(self.guidance_scale - 1).repeat(current_bs)
                        w_embedding = self.get_guidance_scale_embedding(
                            w, embedding_dim=self.unet.config.time_cond_proj_dim
@@ -901,14 +901,14 @@ class LatentConsistencyModelWalkPipeline(
                        # 10. Perform inference for current batch
                        with self.progress_bar(total=num_inference_steps) as progress_bar:
                            for index, t in enumerate(timesteps):
-                                batch_inference_latents = batch_inference_latents.to(batch_inference_embeddings.dtype)
+                                batch_inference_latents = batch_inference_latents.to(batch_inference_embedddings.dtype)

                                # model prediction (v-prediction, eps, x)
                                model_pred = self.unet(
                                    batch_inference_latents,
                                    t,
                                    timestep_cond=w_embedding,
-                                    encoder_hidden_states=batch_inference_embeddings,
+                                    encoder_hidden_states=batch_inference_embedddings,
                                    cross_attention_kwargs=self.cross_attention_kwargs,
                                    return_dict=False,
                                )[0]
@@ -924,8 +924,8 @@ class LatentConsistencyModelWalkPipeline(
                                    callback_outputs = callback_on_step_end(self, index, t, callback_kwargs)

                                    batch_inference_latents = callback_outputs.pop("latents", batch_inference_latents)
-                                    batch_inference_embeddings = callback_outputs.pop(
-                                        "prompt_embeds", batch_inference_embeddings
+                                    batch_inference_embedddings = callback_outputs.pop(
+                                        "prompt_embeds", batch_inference_embedddings
                                    )
                                    w_embedding = callback_outputs.pop("w_embedding", w_embedding)
                                    denoised = callback_outputs.pop("denoised", denoised)
@@ -939,7 +939,7 @@ class LatentConsistencyModelWalkPipeline(
                                        step_idx = index // getattr(self.scheduler, "order", 1)
                                        callback(step_idx, t, batch_inference_latents)

-                        denoised = denoised.to(batch_inference_embeddings.dtype)
+                        denoised = denoised.to(batch_inference_embedddings.dtype)

                        # Note: This is not supported because you would get black images in your latent walk if
                        #       NSFW concept is detected
@@ -348,7 +348,7 @@ def betas_for_alpha_bar(
            return math.exp(t * -12.0)

    else:
-        raise ValueError(f"Unsupported alpha_transform_type: {alpha_transform_type}")
+        raise ValueError(f"Unsupported alpha_tranform_type: {alpha_transform_type}")

    betas = []
    for i in range(num_diffusion_timesteps):
@@ -418,7 +418,9 @@ class LCMScheduler(SchedulerMixin, ConfigMixin):
            there is no previous alpha. When this option is `True` the previous alpha product is fixed to `1`,
            otherwise it uses the alpha value at step 0.
        steps_offset (`int`, defaults to 0):
-            An offset added to the inference steps, as required by some model families.
+            An offset added to the inference steps. You can use a combination of `offset=1` and
+            `set_alpha_to_one=False` to make the last step use step 0 for the previous alpha product like in Stable
+            Diffusion.
        prediction_type (`str`, defaults to `epsilon`, *optional*):
            Prediction type of the scheduler function; can be `epsilon` (predicts the noise of the diffusion process),
            `sample` (directly predicts the noisy sample`) or `v_prediction` (see section 2.4 of [Imagen
@@ -530,7 +530,7 @@ class LLMGroundedDiffusionPipeline(
                )

        if len(phrases) != len(boxes):
-            raise ValueError(
+            ValueError(
                "length of `phrases` and `boxes` has to be same, but"
                f" got: `phrases` {len(phrases)} != `boxes` {len(boxes)}"
            )
@@ -164,7 +164,7 @@ def get_prompts_tokens_with_weights(clip_tokenizer: CLIPTokenizer, prompt: str):
        text_tokens (list)
            A list contains token ids
        text_weight (list)
-            A list contains the correspondent weight of token ids
+            A list contains the correspodent weight of token ids

    Example:
        import torch
@@ -1028,7 +1028,7 @@ class SDXLLongPromptWeightingPipeline(
                # because `num_inference_steps` might be even given that every timestep
                # (except the highest one) is duplicated. If `num_inference_steps` is even it would
                # mean that we cut the timesteps in the middle of the denoising step
-                # (between 1st and 2nd derivative) which leads to incorrect results. By adding 1
+                # (between 1st and 2nd devirative) which leads to incorrect results. By adding 1
                # we ensure that the denoising process always ends after the 2nd derivate step of the scheduler
                num_inference_steps = num_inference_steps + 1

@@ -1531,7 +1531,7 @@ class SDXLLongPromptWeightingPipeline(
            callback_on_step_end_tensor_inputs (`List`, *optional*):
                The list of tensor inputs for the `callback_on_step_end` function. The tensors specified in the list
                will be passed as `callback_kwargs` argument. You will only be able to include variables listed in the
-                `._callback_tensor_inputs` attribute of your pipeline class.
+                `._callback_tensor_inputs` attribute of your pipeine class.

        Examples:

@@ -2131,7 +2131,7 @@ class SDXLLongPromptWeightingPipeline(
            **kwargs,
        )

-    # Override to properly handle the loading and unloading of the additional text encoder.
+    # Overrride to properly handle the loading and unloading of the additional text encoder.
    def load_lora_weights(self, pretrained_model_name_or_path_or_dict: Union[str, Dict[str, torch.Tensor]], **kwargs):
        # We could have accessed the unet config from `lora_state_dict()` too. We pass
        # it here explicitly to be able to tell that it's coming from an SDXL
@@ -18,7 +18,6 @@
 # --------------------------------------------------------------------------


-import logging
 import math
 from typing import Dict, Union

@@ -26,7 +25,6 @@ import matplotlib
 import numpy as np
 import torch
 from PIL import Image
-from PIL.Image import Resampling
 from scipy.optimize import minimize
 from torch.utils.data import DataLoader, TensorDataset
 from tqdm.auto import tqdm
@@ -36,14 +34,13 @@ from diffusers import (
    AutoencoderKL,
    DDIMScheduler,
    DiffusionPipeline,
-    LCMScheduler,
    UNet2DConditionModel,
 )
 from diffusers.utils import BaseOutput, check_min_version


 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.25.0")
+check_min_version("0.27.0.dev0")


 class MarigoldDepthOutput(BaseOutput):
@@ -64,19 +61,6 @@ class MarigoldDepthOutput(BaseOutput):
    uncertainty: Union[None, np.ndarray]


-def get_pil_resample_method(method_str: str) -> Resampling:
-    resample_method_dic = {
-        "bilinear": Resampling.BILINEAR,
-        "bicubic": Resampling.BICUBIC,
-        "nearest": Resampling.NEAREST,
-    }
-    resample_method = resample_method_dic.get(method_str, None)
-    if resample_method is None:
-        raise ValueError(f"Unknown resampling method: {resample_method}")
-    else:
-        return resample_method
-
-
 class MarigoldPipeline(DiffusionPipeline):
    """
    Pipeline for monocular depth estimation using Marigold: https://marigoldmonodepth.github.io.
@@ -129,9 +113,7 @@ class MarigoldPipeline(DiffusionPipeline):
        ensemble_size: int = 10,
        processing_res: int = 768,
        match_input_res: bool = True,
-        resample_method: str = "bilinear",
        batch_size: int = 0,
-        seed: Union[int, None] = None,
        color_map: str = "Spectral",
        show_progress_bar: bool = True,
        ensemble_kwargs: Dict = None,
@@ -147,9 +129,7 @@ class MarigoldPipeline(DiffusionPipeline):
                If set to 0: will not resize at all.
            match_input_res (`bool`, *optional*, defaults to `True`):
                Resize depth prediction to match input resolution.
-                Only valid if `processing_res` > 0.
-            resample_method: (`str`, *optional*, defaults to `bilinear`):
-                Resampling method used to resize images and depth predictions. This can be one of `bilinear`, `bicubic` or `nearest`, defaults to: `bilinear`.
+                Only valid if `limit_input_res` is not None.
            denoising_steps (`int`, *optional*, defaults to `10`):
                Number of diffusion denoising steps (DDIM) during inference.
            ensemble_size (`int`, *optional*, defaults to `10`):
@@ -157,8 +137,6 @@ class MarigoldPipeline(DiffusionPipeline):
            batch_size (`int`, *optional*, defaults to `0`):
                Inference batch size, no bigger than `num_ensemble`.
                If set to 0, the script will automatically decide the proper batch size.
-            seed (`int`, *optional*, defaults to `None`)
-                Reproducibility seed.
            show_progress_bar (`bool`, *optional*, defaults to `True`):
                Display a progress bar of diffusion denoising.
            color_map (`str`, *optional*, defaults to `"Spectral"`, pass `None` to skip colorized depth map generation):
@@ -168,7 +146,8 @@ class MarigoldPipeline(DiffusionPipeline):
        Returns:
            `MarigoldDepthOutput`: Output class for Marigold monocular depth prediction pipeline, including:
            - **depth_np** (`np.ndarray`) Predicted depth map, with depth values in the range of [0, 1]
-            - **depth_colored** (`PIL.Image.Image`) Colorized depth map, with the shape of [3, H, W] and values in [0, 1], None if `color_map` is `None`
+            - **depth_colored** (`None` or `PIL.Image.Image`) Colorized depth map, with the shape of [3, H, W] and
+                    values in [0, 1]. None if `color_map` is `None`
            - **uncertainty** (`None` or `np.ndarray`) Uncalibrated uncertainty(MAD, median absolute deviation)
                    coming from ensembling. None if `ensemble_size = 1`
        """
@@ -179,21 +158,13 @@ class MarigoldPipeline(DiffusionPipeline):
        if not match_input_res:
            assert processing_res is not None, "Value error: `resize_output_back` is only valid with "
        assert processing_res >= 0
+        assert denoising_steps >= 1
        assert ensemble_size >= 1

-        # Check if denoising step is reasonable
-        self._check_inference_step(denoising_steps)
-
-        resample_method: Resampling = get_pil_resample_method(resample_method)
-
        # ----------------- Image Preprocess -----------------
        # Resize image
        if processing_res > 0:
-            input_image = self.resize_max_res(
-                input_image,
-                max_edge_resolution=processing_res,
-                resample_method=resample_method,
-            )
+            input_image = self.resize_max_res(input_image, max_edge_resolution=processing_res)
        # Convert the image to RGB, to 1.remove the alpha channel 2.convert B&W to 3-channel
        input_image = input_image.convert("RGB")
        image = np.asarray(input_image)
@@ -232,10 +203,9 @@ class MarigoldPipeline(DiffusionPipeline):
                rgb_in=batched_img,
                num_inference_steps=denoising_steps,
                show_pbar=show_progress_bar,
-                seed=seed,
            )
-            depth_pred_ls.append(depth_pred_raw.detach())
-        depth_preds = torch.concat(depth_pred_ls, dim=0).squeeze()
+            depth_pred_ls.append(depth_pred_raw.detach().clone())
+        depth_preds = torch.concat(depth_pred_ls, axis=0).squeeze()
        torch.cuda.empty_cache()  # clear vram cache for ensembling

        # ----------------- Test-time ensembling -----------------
@@ -257,7 +227,7 @@ class MarigoldPipeline(DiffusionPipeline):
        # Resize back to original resolution
        if match_input_res:
            pred_img = Image.fromarray(depth_pred)
-            pred_img = pred_img.resize(input_size, resample=resample_method)
+            pred_img = pred_img.resize(input_size)
            depth_pred = np.asarray(pred_img)

        # Clip output range
@@ -273,32 +243,12 @@ class MarigoldPipeline(DiffusionPipeline):
            depth_colored_img = Image.fromarray(depth_colored_hwc)
        else:
            depth_colored_img = None
-
        return MarigoldDepthOutput(
            depth_np=depth_pred,
            depth_colored=depth_colored_img,
            uncertainty=pred_uncert,
        )

-    def _check_inference_step(self, n_step: int):
-        """
-        Check if denoising step is reasonable
-        Args:
-            n_step (`int`): denoising steps
-        """
-        assert n_step >= 1
-
-        if isinstance(self.scheduler, DDIMScheduler):
-            if n_step < 10:
-                logging.warning(
-                    f"Too few denoising steps: {n_step}. Recommended to use the LCM checkpoint for few-step inference."
-                )
-        elif isinstance(self.scheduler, LCMScheduler):
-            if not 1 <= n_step <= 4:
-                logging.warning(f"Non-optimal setting of denoising steps: {n_step}. Recommended setting is 1-4 steps.")
-        else:
-            raise RuntimeError(f"Unsupported scheduler type: {type(self.scheduler)}")
-
    def _encode_empty_text(self):
        """
        Encode text embedding for empty prompt.
@@ -315,13 +265,7 @@ class MarigoldPipeline(DiffusionPipeline):
        self.empty_text_embed = self.text_encoder(text_input_ids)[0].to(self.dtype)

    @torch.no_grad()
-    def single_infer(
-        self,
-        rgb_in: torch.Tensor,
-        num_inference_steps: int,
-        seed: Union[int, None],
-        show_pbar: bool,
-    ) -> torch.Tensor:
+    def single_infer(self, rgb_in: torch.Tensor, num_inference_steps: int, show_pbar: bool) -> torch.Tensor:
        """
        Perform an individual depth prediction without ensembling.

@@ -342,20 +286,10 @@ class MarigoldPipeline(DiffusionPipeline):
        timesteps = self.scheduler.timesteps  # [T]

        # Encode image
-        rgb_latent = self.encode_rgb(rgb_in)
+        rgb_latent = self._encode_rgb(rgb_in)

        # Initial depth map (noise)
-        if seed is None:
-            rand_num_generator = None
-        else:
-            rand_num_generator = torch.Generator(device=device)
-            rand_num_generator.manual_seed(seed)
-        depth_latent = torch.randn(
-            rgb_latent.shape,
-            device=device,
-            dtype=self.dtype,
-            generator=rand_num_generator,
-        )  # [B, 4, h, w]
+        depth_latent = torch.randn(rgb_latent.shape, device=device, dtype=self.dtype)  # [B, 4, h, w]

        # Batched empty text embedding
        if self.empty_text_embed is None:
@@ -380,9 +314,9 @@ class MarigoldPipeline(DiffusionPipeline):
            noise_pred = self.unet(unet_input, t, encoder_hidden_states=batch_empty_text_embed).sample  # [B, 4, h, w]

            # compute the previous noisy sample x_t -> x_t-1
-            depth_latent = self.scheduler.step(noise_pred, t, depth_latent, generator=rand_num_generator).prev_sample
-
-        depth = self.decode_depth(depth_latent)
+            depth_latent = self.scheduler.step(noise_pred, t, depth_latent).prev_sample
+        torch.cuda.empty_cache()
+        depth = self._decode_depth(depth_latent)

        # clip prediction
        depth = torch.clip(depth, -1.0, 1.0)
@@ -391,7 +325,7 @@ class MarigoldPipeline(DiffusionPipeline):

        return depth

-    def encode_rgb(self, rgb_in: torch.Tensor) -> torch.Tensor:
+    def _encode_rgb(self, rgb_in: torch.Tensor) -> torch.Tensor:
        """
        Encode RGB image into latent.

@@ -410,7 +344,7 @@ class MarigoldPipeline(DiffusionPipeline):
        rgb_latent = mean * self.rgb_latent_scale_factor
        return rgb_latent

-    def decode_depth(self, depth_latent: torch.Tensor) -> torch.Tensor:
+    def _decode_depth(self, depth_latent: torch.Tensor) -> torch.Tensor:
        """
        Decode depth latent into depth map.

@@ -431,7 +365,7 @@ class MarigoldPipeline(DiffusionPipeline):
        return depth_mean

    @staticmethod
-    def resize_max_res(img: Image.Image, max_edge_resolution: int, resample_method=Resampling.BILINEAR) -> Image.Image:
+    def resize_max_res(img: Image.Image, max_edge_resolution: int) -> Image.Image:
        """
        Resize image to limit maximum edge length while keeping aspect ratio.

@@ -440,8 +374,6 @@ class MarigoldPipeline(DiffusionPipeline):
                Image to be resized.
            max_edge_resolution (`int`):
                Maximum edge length (pixel).
-            resample_method (`PIL.Image.Resampling`):
-                Resampling method used to resize images.

        Returns:
            `Image.Image`: Resized image.
@@ -452,7 +384,7 @@ class MarigoldPipeline(DiffusionPipeline):
        new_width = int(original_width * downscale_factor)
        new_height = int(original_height * downscale_factor)

-        resized_img = img.resize((new_width, new_height), resample=resample_method)
+        resized_img = img.resize((new_width, new_height))
        return resized_img

    @staticmethod
@@ -196,7 +196,7 @@ class StableDiffusionTilingPipeline(DiffusionPipeline, StableDiffusionExtrasMixi
            guidance_scale_tiles: specific weights for classifier-free guidance in each tile.
            guidance_scale_tiles: specific weights for classifier-free guidance in each tile. If None, the value provided in guidance_scale will be used.
            seed_tiles: specific seeds for the initialization latents in each tile. These will override the latents generated for the whole canvas using the standard seed parameter.
-            seed_tiles_mode: either "full" "exclusive". If "full", all the latents affected by the tile be overriden. If "exclusive", only the latents that are affected exclusively by this tile (and no other tiles) will be overriden.
+            seed_tiles_mode: either "full" "exclusive". If "full", all the latents affected by the tile be overriden. If "exclusive", only the latents that are affected exclusively by this tile (and no other tiles) will be overrriden.
            seed_reroll_regions: a list of tuples in the form (start row, end row, start column, end column, seed) defining regions in pixel space for which the latents will be overriden using the given seed. Takes priority over seed_tiles.
            cpu_vae: the decoder from latent space to pixel space can require too mucho GPU RAM for large images. If you find out of memory errors at the end of the generation process, try setting this parameter to True to run the decoder in CPU. Slower, but should run without memory issues.

@@ -325,7 +325,7 @@ class StableDiffusionTilingPipeline(DiffusionPipeline, StableDiffusionExtrasMixi
        if accepts_eta:
            extra_step_kwargs["eta"] = eta

-        # Mask for tile weights strength
+        # Mask for tile weights strenght
        tile_weights = self._gaussian_weights(tile_width, tile_height, batch_size)

        # Diffusion timesteps
@@ -832,7 +832,7 @@ class AnimateDiffControlNetPipeline(
            clip_skip (`int`, *optional*):
                Number of layers to be skipped from CLIP while computing the prompt embeddings. A value of 1 means that
                the output of the pre-final layer will be used for computing the prompt embeddings.
-            callback_on_step_end (`Callable`, *optional*):
+            allback_on_step_end (`Callable`, *optional*):
                A function that calls at the end of each denoising steps during the inference. The function is called
                with the following arguments: `callback_on_step_end(self: DiffusionPipeline, step: int, timestep: int,
                callback_kwargs: Dict)`. `callback_kwargs` will include a list of all tensors as specified by
@@ -840,7 +840,7 @@ class AnimateDiffControlNetPipeline(
            callback_on_step_end_tensor_inputs (`List`, *optional*):
                The list of tensor inputs for the `callback_on_step_end` function. The tensors specified in the list
                will be passed as `callback_kwargs` argument. You will only be able to include variables listed in the
-                `._callback_tensor_inputs` attribute of your pipeline class.
+                `._callback_tensor_inputs` attribute of your pipeine class.

        Examples:

@@ -1280,7 +1280,7 @@ class DemoFusionSDXLPipeline(

        return output_images

-    # Override to properly handle the loading and unloading of the additional text encoder.
+    # Overrride to properly handle the loading and unloading of the additional text encoder.
    def load_lora_weights(self, pretrained_model_name_or_path_or_dict: Union[str, Dict[str, torch.Tensor]], **kwargs):
        # We could have accessed the unet config from `lora_state_dict()` too. We pass
        # it here explicitly to be able to tell that it's coming from an SDXL
@@ -887,7 +887,7 @@ class StyleAlignedSDXLPipeline(
                # because `num_inference_steps` might be even given that every timestep
                # (except the highest one) is duplicated. If `num_inference_steps` is even it would
                # mean that we cut the timesteps in the middle of the denoising step
-                # (between 1st and 2nd derivative) which leads to incorrect results. By adding 1
+                # (between 1st and 2nd devirative) which leads to incorrect results. By adding 1
                # we ensure that the denoising process always ends after the 2nd derivate step of the scheduler
                num_inference_steps = num_inference_steps + 1

@@ -26,7 +26,7 @@ from diffusers.loaders import FromSingleFileMixin, LoraLoaderMixin, TextualInver
 from diffusers.models import AutoencoderKL, UNet2DConditionModel
 from diffusers.models.lora import adjust_lora_scale_text_encoder
 from diffusers.pipelines.stable_diffusion import StableDiffusionSafetyChecker
-from diffusers.pipelines.stable_diffusion_ldm3d.pipeline_stable_diffusion_ldm3d import LDM3DPipelineOutput
+from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion_ldm3d import LDM3DPipelineOutput
 from diffusers.schedulers import DDPMScheduler, KarrasDiffusionSchedulers
 from diffusers.utils import (
    USE_PEFT_BACKEND,
@@ -206,7 +206,7 @@ def prepare_mask_and_masked_image(image, mask, height, width, return_image: bool
            dimensions: ``batch x channels x height x width``.
    """

-    # checkpoint. #TODO(Yiyi) - need to clean this up later
+    # checkpoint. TOD(Yiyi) - need to clean this up later
    if image is None:
        raise ValueError("`image` input cannot be undefined.")

@@ -277,7 +277,7 @@ def prepare_mask_and_masked_image(image, mask, height, width, return_image: bool
        # images are in latent space and thus can't
        # be masked set masked_image to None
        # we assume that the checkpoint is not an inpainting
-        # checkpoint. #TODO(Yiyi) - need to clean this up later
+        # checkpoint. TOD(Yiyi) - need to clean this up later
        masked_image = None
    else:
        masked_image = image * (mask < 0.5)
@@ -1073,7 +1073,7 @@ class StableDiffusionXLControlNetAdapterInpaintPipeline(
                # because `num_inference_steps` might be even given that every timestep
                # (except the highest one) is duplicated. If `num_inference_steps` is even it would
                # mean that we cut the timesteps in the middle of the denoising step
-                # (between 1st and 2nd derivative) which leads to incorrect results. By adding 1
+                # (between 1st and 2nd devirative) which leads to incorrect results. By adding 1
                # we ensure that the denoising process always ends after the 2nd derivate step of the scheduler
                num_inference_steps = num_inference_steps + 1

@@ -46,11 +46,6 @@ except Exception:

 logger = logging.get_logger(__name__)  # pylint: disable=invalid-name

-logger.warning(
-    "To use instant id pipelines, please make sure you have the `insightface` library installed: `pip install insightface`."
-    "Please refer to: https://huggingface.co/InstantX/InstantID for further instructions regarding inference"
-)
-

 def FeedForward(dim, mult=4):
    inner_dim = int(dim * mult)
@@ -457,7 +452,7 @@ class StableDiffusionXLInstantIDPipeline(StableDiffusionXLControlNetPipeline):

                xformers_version = version.parse(xformers.__version__)
                if xformers_version == version.parse("0.0.16"):
-                    logger.warning(
+                    logger.warn(
                        "xFormers 0.0.16 cannot be used for training in some GPUs. If you observe problems during training, please update xFormers to at least 0.0.17. See https://huggingface.co/docs/diffusers/main/en/optimization/xformers for more details."
                    )
                self.enable_xformers_memory_efficient_attention()
@@ -706,7 +701,7 @@ class StableDiffusionXLInstantIDPipeline(StableDiffusionXLControlNetPipeline):
            callback_on_step_end_tensor_inputs (`List`, *optional*):
                The list of tensor inputs for the `callback_on_step_end` function. The tensors specified in the list
                will be passed as `callback_kwargs` argument. You will only be able to include variables listed in the
-                `._callback_tensor_inputs` attribute of your pipeline class.
+                `._callback_tensor_inputs` attribute of your pipeine class.

        Examples:

@@ -81,7 +81,7 @@ def betas_for_alpha_bar(
            return math.exp(t * -12.0)

    else:
-        raise ValueError(f"Unsupported alpha_transform_type: {alpha_transform_type}")
+        raise ValueError(f"Unsupported alpha_tranform_type: {alpha_transform_type}")

    betas = []
    for i in range(num_diffusion_timesteps):
@@ -171,7 +171,9 @@ class UFOGenScheduler(SchedulerMixin, ConfigMixin):
            The way the timesteps should be scaled. Refer to Table 2 of the [Common Diffusion Noise Schedules and
            Sample Steps are Flawed](https://huggingface.co/papers/2305.08891) for more information.
        steps_offset (`int`, defaults to 0):
-            An offset added to the inference steps, as required by some model families.
+            An offset added to the inference steps. You can use a combination of `offset=1` and
+            `set_alpha_to_one=False` to make the last step use step 0 for the previous alpha product like in Stable
+            Diffusion.
        rescale_betas_zero_snr (`bool`, defaults to `False`):
            Whether to rescale the betas to have zero terminal SNR. This enables the model to generate very bright and
            dark samples instead of limiting it to samples with medium brightness. Loosely related to
@@ -1,7 +1,6 @@
 """
-modified based on diffusion library from Huggingface: https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion.py
+    modified based on diffusion library from Huggingface: https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion.py
 """
-
 import inspect
 from typing import Callable, List, Optional, Union

@@ -224,7 +224,7 @@ class StableDiffusionIPEXPipeline(
        # 5. Prepare latent variables
        latents = self.prepare_latents(
            batch_size * num_images_per_prompt,
-            self.unet.config.in_channels,
+            self.unet.in_channels,
            height,
            width,
            prompt_embeds.dtype,
@@ -679,7 +679,7 @@ class StableDiffusionIPEXPipeline(
        timesteps = self.scheduler.timesteps

        # 5. Prepare latent variables
-        num_channels_latents = self.unet.config.in_channels
+        num_channels_latents = self.unet.in_channels
        latents = self.prepare_latents(
            batch_size * num_images_per_prompt,
            num_channels_latents,
@@ -917,7 +917,7 @@ class TensorRTStableDiffusionPipeline(StableDiffusionPipeline):
            text_embeddings = self.__encode_prompt(prompt, negative_prompt)

            # Pre-initialize latents
-            num_channels_latents = self.unet.config.in_channels
+            num_channels_latents = self.unet.in_channels
            latents = self.prepare_latents(
                batch_size,
                num_channels_latents,
@@ -35,6 +35,7 @@ def slerp(val, low, high):


 class UnCLIPTextInterpolationPipeline(DiffusionPipeline):
+
    """
    Pipeline for prompt-to-prompt interpolation on CLIP text embeddings and using the UnCLIP / Dall-E to decode them to images.

@@ -48,7 +49,7 @@ class UnCLIPTextInterpolationPipeline(DiffusionPipeline):
            Tokenizer of class
            [CLIPTokenizer](https://huggingface.co/docs/transformers/v4.21.0/en/model_doc/clip#transformers.CLIPTokenizer).
        prior ([`PriorTransformer`]):
-            The canonical unCLIP prior to approximate the image embedding from the text embedding.
+            The canonincal unCLIP prior to approximate the image embedding from the text embedding.
        text_proj ([`UnCLIPTextProjModel`]):
            Utility class to prepare and combine the embeddings before they are passed to the decoder.
        decoder ([`UNet2DConditionModel`]):
@@ -72,7 +72,7 @@ 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("0.28.0.dev0")
+check_min_version("0.27.0.dev0")

 logger = get_logger(__name__)

@@ -308,7 +308,7 @@ def log_validation(vae, unet, args, accelerator, weight_dtype, step):

            tracker.log({"validation": formatted_images})
        else:
-            logger.warning(f"image logging not implemented for {tracker.name}")
+            logger.warn(f"image logging not implemented for {tracker.name}")

        del pipeline
        gc.collect()
@@ -1068,7 +1068,7 @@ def main(args):

            xformers_version = version.parse(xformers.__version__)
            if xformers_version == version.parse("0.0.16"):
-                logger.warning(
+                logger.warn(
                    "xFormers 0.0.16 cannot be used for training in some GPUs. If you observe problems during training, please update xFormers to at least 0.0.17. See https://huggingface.co/docs/diffusers/main/en/optimization/xformers for more details."
                )
            unet.enable_xformers_memory_efficient_attention()
@@ -65,7 +65,7 @@ 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("0.28.0.dev0")
+check_min_version("0.27.0.dev0")

 logger = get_logger(__name__)

@@ -180,7 +180,7 @@ def log_validation(vae, args, accelerator, weight_dtype, step, unet=None, is_fin
            logger_name = "test" if is_final_validation else "validation"
            tracker.log({logger_name: formatted_images})
        else:
-            logger.warning(f"image logging not implemented for {tracker.name}")
+            logger.warn(f"image logging not implemented for {tracker.name}")

        del pipeline
        gc.collect()
@@ -928,7 +928,7 @@ def main(args):

            xformers_version = version.parse(xformers.__version__)
            if xformers_version == version.parse("0.0.16"):
-                logger.warning(
+                logger.warn(
                    "xFormers 0.0.16 cannot be used for training in some GPUs. If you observe problems during training, please update xFormers to at least 0.0.17. See https://huggingface.co/docs/diffusers/main/en/optimization/xformers for more details."
                )
            unet.enable_xformers_memory_efficient_attention()
@@ -78,7 +78,7 @@ 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("0.28.0.dev0")
+check_min_version("0.27.0.dev0")

 logger = get_logger(__name__)

@@ -325,7 +325,7 @@ def log_validation(vae, unet, args, accelerator, weight_dtype, step):

            tracker.log({"validation": formatted_images})
        else:
-            logger.warning(f"image logging not implemented for {tracker.name}")
+            logger.warn(f"image logging not implemented for {tracker.name}")

        del pipeline
        gc.collect()
@@ -1083,7 +1083,7 @@ def main(args):

            xformers_version = version.parse(xformers.__version__)
            if xformers_version == version.parse("0.0.16"):
-                logger.warning(
+                logger.warn(
                    "xFormers 0.0.16 cannot be used for training in some GPUs. If you observe problems during training, please update xFormers to at least 0.0.17. See https://huggingface.co/docs/diffusers/main/en/optimization/xformers for more details."
                )
            unet.enable_xformers_memory_efficient_attention()
@@ -71,7 +71,7 @@ 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("0.28.0.dev0")
+check_min_version("0.27.0.dev0")

 logger = get_logger(__name__)

@@ -285,7 +285,7 @@ def log_validation(vae, unet, args, accelerator, weight_dtype, step, name="targe

            tracker.log({f"validation/{name}": formatted_images})
        else:
-            logger.warning(f"image logging not implemented for {tracker.name}")
+            logger.warn(f"image logging not implemented for {tracker.name}")

        del pipeline
        gc.collect()
@@ -1023,7 +1023,7 @@ def main(args):

            xformers_version = version.parse(xformers.__version__)
            if xformers_version == version.parse("0.0.16"):
-                logger.warning(
+                logger.warn(
                    "xFormers 0.0.16 cannot be used for training in some GPUs. If you observe problems during training, please update xFormers to at least 0.0.17. See https://huggingface.co/docs/diffusers/main/en/optimization/xformers for more details."
                )
            unet.enable_xformers_memory_efficient_attention()
@@ -77,7 +77,7 @@ 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("0.28.0.dev0")
+check_min_version("0.27.0.dev0")

 logger = get_logger(__name__)

@@ -303,7 +303,7 @@ def log_validation(vae, unet, args, accelerator, weight_dtype, step, name="targe

            tracker.log({f"validation/{name}": formatted_images})
        else:
-            logger.warning(f"image logging not implemented for {tracker.name}")
+            logger.warn(f"image logging not implemented for {tracker.name}")

        del pipeline
        gc.collect()
@@ -1083,7 +1083,7 @@ def main(args):

            xformers_version = version.parse(xformers.__version__)
            if xformers_version == version.parse("0.0.16"):
-                logger.warning(
+                logger.warn(
                    "xFormers 0.0.16 cannot be used for training in some GPUs. If you observe problems during training, please update xFormers to at least 0.0.17. See https://huggingface.co/docs/diffusers/main/en/optimization/xformers for more details."
                )
            unet.enable_xformers_memory_efficient_attention()
@@ -60,7 +60,7 @@ 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("0.28.0.dev0")
+check_min_version("0.27.0.dev0")

 logger = get_logger(__name__)

@@ -178,7 +178,7 @@ def log_validation(

            tracker.log({tracker_key: formatted_images})
        else:
-            logger.warning(f"image logging not implemented for {tracker.name}")
+            logger.warn(f"image logging not implemented for {tracker.name}")

        del pipeline
        gc.collect()
@@ -861,7 +861,7 @@ def main(args):

            xformers_version = version.parse(xformers.__version__)
            if xformers_version == version.parse("0.0.16"):
-                logger.warning(
+                logger.warn(
                    "xFormers 0.0.16 cannot be used for training in some GPUs. If you observe problems during training, please update xFormers to at least 0.0.17. See https://huggingface.co/docs/diffusers/main/en/optimization/xformers for more details."
                )
            unet.enable_xformers_memory_efficient_attention()
@@ -60,7 +60,7 @@ 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("0.28.0.dev0")
+check_min_version("0.27.0.dev0")

 logger = logging.getLogger(__name__)

@@ -128,7 +128,7 @@ def log_validation(pipeline, pipeline_params, controlnet_params, tokenizer, args

        wandb.log({"validation": formatted_images})
    else:
-        logger.warning(f"image logging not implemented for {args.report_to}")
+        logger.warn(f"image logging not implemented for {args.report_to}")

    return image_logs

@@ -61,7 +61,7 @@ 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("0.28.0.dev0")
+check_min_version("0.27.0.dev0")

 logger = get_logger(__name__)

@@ -125,11 +125,7 @@ def log_validation(vae, unet, controlnet, args, accelerator, weight_dtype, step,
        )

    image_logs = []
-    inference_ctx = (
-        contextlib.nullcontext()
-        if (is_final_validation or torch.backends.mps.is_available())
-        else torch.autocast("cuda")
-    )
+    inference_ctx = contextlib.nullcontext() if is_final_validation else torch.autocast("cuda")

    for validation_prompt, validation_image in zip(validation_prompts, validation_images):
        validation_image = Image.open(validation_image).convert("RGB")
@@ -182,7 +178,7 @@ def log_validation(vae, unet, controlnet, args, accelerator, weight_dtype, step,

            tracker.log({tracker_key: formatted_images})
        else:
-            logger.warning(f"image logging not implemented for {tracker.name}")
+            logger.warn(f"image logging not implemented for {tracker.name}")

        del pipeline
        gc.collect()
@@ -796,12 +792,6 @@ def main(args):

    logging_dir = Path(args.output_dir, args.logging_dir)

-    if torch.backends.mps.is_available() and args.mixed_precision == "bf16":
-        # due to pytorch#99272, MPS does not yet support bfloat16.
-        raise ValueError(
-            "Mixed precision training with bfloat16 is not supported on MPS. Please use fp16 (recommended) or fp32 instead."
-        )
-
    accelerator_project_config = ProjectConfiguration(project_dir=args.output_dir, logging_dir=logging_dir)

    accelerator = Accelerator(
@@ -939,7 +929,7 @@ def main(args):

            xformers_version = version.parse(xformers.__version__)
            if xformers_version == version.parse("0.0.16"):
-                logger.warning(
+                logger.warn(
                    "xFormers 0.0.16 cannot be used for training in some GPUs. If you observe problems during training, please update xFormers to at least 0.0.17. See https://huggingface.co/docs/diffusers/main/en/optimization/xformers for more details."
                )
            unet.enable_xformers_memory_efficient_attention()
@@ -63,7 +63,7 @@ from diffusers.utils.import_utils import is_xformers_available


 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.28.0.dev0")
+check_min_version("0.27.0.dev0")

 logger = get_logger(__name__)

@@ -904,7 +904,7 @@ def main(args):

            xformers_version = version.parse(xformers.__version__)
            if xformers_version == version.parse("0.0.16"):
-                logger.warning(
+                logger.warn(
                    "xFormers 0.0.16 cannot be used for training in some GPUs. If you observe problems during training, please update xFormers to at least 0.0.17. See https://huggingface.co/docs/diffusers/main/en/optimization/xformers for more details."
                )
            attention_class = CustomDiffusionXFormersAttnProcessor
@@ -1178,7 +1178,7 @@ def main(args):
                        grads_text_encoder = text_encoder.get_input_embeddings().weight.grad
                    # Get the index for tokens that we want to zero the grads for
                    index_grads_to_zero = torch.arange(len(tokenizer)) != modifier_token_id[0]
-                    for i in range(1, len(modifier_token_id)):
+                    for i in range(len(modifier_token_id[1:])):
                        index_grads_to_zero = index_grads_to_zero & (
                            torch.arange(len(tokenizer)) != modifier_token_id[i]
                        )
@@ -259,17 +259,13 @@ The authors found that by using DoRA, both the learning capacity and training st
 > This is also aligned with some of the quantitative analysis shown in the paper. 

 **Usage**
-1. To use DoRA you need to upgrade the installation of `peft`: 
+1. To use DoRA you need to install `peft` from main: 
 ```bash
-pip install-U peft
+pip install git+https://github.com/huggingface/peft.git
 ```
 2. Enable DoRA training by adding this flag
 ```bash
 --use_dora
 ```
 **Inference** 
-The inference is the same as if you train a regular LoRA 🤗
-
-## Format compatibility
-
-You can pass `--output_kohya_format` to additionally generate a state dictionary which should be compatible with other platforms and tools such as Automatic 1111, Comfy, Kohya, etc. The `output_dir` will contain a file named "pytorch_lora_weights_kohya.safetensors".
+The inference is the same as if you train a regular LoRA 🤗
@@ -63,7 +63,7 @@ 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("0.28.0.dev0")
+check_min_version("0.27.0.dev0")

 logger = get_logger(__name__)

@@ -987,7 +987,7 @@ def main(args):

            xformers_version = version.parse(xformers.__version__)
            if xformers_version == version.parse("0.0.16"):
-                logger.warning(
+                logger.warn(
                    "xFormers 0.0.16 cannot be used for training in some GPUs. If you observe problems during training, please update xFormers to at least 0.0.17. See https://huggingface.co/docs/diffusers/main/en/optimization/xformers for more details."
                )
            unet.enable_xformers_memory_efficient_attention()
@@ -35,7 +35,7 @@ from diffusers.utils import check_min_version


 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.28.0.dev0")
+check_min_version("0.27.0.dev0")

 # Cache compiled models across invocations of this script.
 cc.initialize_cache(os.path.expanduser("~/.cache/jax/compilation_cache"))
@@ -70,7 +70,7 @@ 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("0.28.0.dev0")
+check_min_version("0.27.0.dev0")

 logger = get_logger(__name__)

@@ -895,7 +895,7 @@ def main(args):

            xformers_version = version.parse(xformers.__version__)
            if xformers_version == version.parse("0.0.16"):
-                logger.warning(
+                logger.warn(
                    "xFormers 0.0.16 cannot be used for training in some GPUs. If you observe problems during training, please update xFormers to at least 0.0.17. See https://huggingface.co/docs/diffusers/main/en/optimization/xformers for more details."
                )
            unet.enable_xformers_memory_efficient_attention()
@@ -14,6 +14,7 @@
 # See the License for the specific language governing permissions and

 import argparse
+import contextlib
 import gc
 import itertools
 import json
@@ -40,7 +41,6 @@ from peft import LoraConfig, set_peft_model_state_dict
 from peft.utils import get_peft_model_state_dict
 from PIL import Image
 from PIL.ImageOps import exif_transpose
-from safetensors.torch import load_file, save_file
 from torch.utils.data import Dataset
 from torchvision import transforms
 from torchvision.transforms.functional import crop
@@ -62,9 +62,7 @@ from diffusers.optimization import get_scheduler
 from diffusers.training_utils import _set_state_dict_into_text_encoder, cast_training_params, compute_snr
 from diffusers.utils import (
    check_min_version,
-    convert_all_state_dict_to_peft,
    convert_state_dict_to_diffusers,
-    convert_state_dict_to_kohya,
    convert_unet_state_dict_to_peft,
    is_wandb_available,
 )
@@ -77,7 +75,7 @@ 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("0.28.0.dev0")
+check_min_version("0.27.0.dev0")

 logger = get_logger(__name__)

@@ -207,18 +205,11 @@ def log_validation(
    generator = torch.Generator(device=accelerator.device).manual_seed(args.seed) if args.seed else None
    # Currently the context determination is a bit hand-wavy. We can improve it in the future if there's a better
    # way to condition it. Reference: https://github.com/huggingface/diffusers/pull/7126#issuecomment-1968523051
-    enable_autocast = True
-    if torch.backends.mps.is_available() or (
-        accelerator.mixed_precision == "fp16" or accelerator.mixed_precision == "bf16"
-    ):
-        enable_autocast = False
-    if "playground" in args.pretrained_model_name_or_path:
-        enable_autocast = False
+    inference_ctx = (
+        contextlib.nullcontext() if "playground" in args.pretrained_model_name_or_path else torch.cuda.amp.autocast()
+    )

-    with torch.autocast(
-        accelerator.device.type,
-        enabled=enable_autocast,
-    ):
+    with inference_ctx:
        images = [pipeline(**pipeline_args, generator=generator).images[0] for _ in range(args.num_validation_images)]

    for tracker in accelerator.trackers:
@@ -236,8 +227,7 @@ def log_validation(
            )

    del pipeline
-    if torch.cuda.is_available():
-        torch.cuda.empty_cache()
+    torch.cuda.empty_cache()

    return images

@@ -406,11 +396,6 @@ def parse_args(input_args=None):
        default="lora-dreambooth-model",
        help="The output directory where the model predictions and checkpoints will be written.",
    )
-    parser.add_argument(
-        "--output_kohya_format",
-        action="store_true",
-        help="Flag to additionally generate final state dict in the Kohya format so that it becomes compatible with A111, Comfy, Kohya, etc.",
-    )
    parser.add_argument("--seed", type=int, default=None, help="A seed for reproducible training.")
    parser.add_argument(
        "--resolution",
@@ -974,12 +959,6 @@ def main(args):
    if args.do_edm_style_training and args.snr_gamma is not None:
        raise ValueError("Min-SNR formulation is not supported when conducting EDM-style training.")

-    if torch.backends.mps.is_available() and args.mixed_precision == "bf16":
-        # due to pytorch#99272, MPS does not yet support bfloat16.
-        raise ValueError(
-            "Mixed precision training with bfloat16 is not supported on MPS. Please use fp16 (recommended) or fp32 instead."
-        )
-
    logging_dir = Path(args.output_dir, args.logging_dir)

    accelerator_project_config = ProjectConfiguration(project_dir=args.output_dir, logging_dir=logging_dir)
@@ -1022,8 +1001,7 @@ def main(args):
        cur_class_images = len(list(class_images_dir.iterdir()))

        if cur_class_images < args.num_class_images:
-            has_supported_fp16_accelerator = torch.cuda.is_available() or torch.backends.mps.is_available()
-            torch_dtype = torch.float16 if has_supported_fp16_accelerator else torch.float32
+            torch_dtype = torch.float16 if accelerator.device.type == "cuda" else torch.float32
            if args.prior_generation_precision == "fp32":
                torch_dtype = torch.float32
            elif args.prior_generation_precision == "fp16":
@@ -1148,12 +1126,6 @@ def main(args):
    elif accelerator.mixed_precision == "bf16":
        weight_dtype = torch.bfloat16

-    if torch.backends.mps.is_available() and weight_dtype == torch.bfloat16:
-        # due to pytorch#99272, MPS does not yet support bfloat16.
-        raise ValueError(
-            "Mixed precision training with bfloat16 is not supported on MPS. Please use fp16 (recommended) or fp32 instead."
-        )
-
    # Move unet, vae and text_encoder to device and cast to weight_dtype
    unet.to(accelerator.device, dtype=weight_dtype)

@@ -1169,7 +1141,7 @@ def main(args):

            xformers_version = version.parse(xformers.__version__)
            if xformers_version == version.parse("0.0.16"):
-                logger.warning(
+                logger.warn(
                    "xFormers 0.0.16 cannot be used for training in some GPUs. If you observe problems during training, "
                    "please update xFormers to at least 0.0.17. See https://huggingface.co/docs/diffusers/main/en/optimization/xformers for more details."
                )
@@ -1298,7 +1270,7 @@ def main(args):

    # Enable TF32 for faster training on Ampere GPUs,
    # cf https://pytorch.org/docs/stable/notes/cuda.html#tensorfloat-32-tf32-on-ampere-devices
-    if args.allow_tf32 and torch.cuda.is_available():
+    if args.allow_tf32:
        torch.backends.cuda.matmul.allow_tf32 = True

    if args.scale_lr:
@@ -1345,14 +1317,14 @@ def main(args):

    # Optimizer creation
    if not (args.optimizer.lower() == "prodigy" or args.optimizer.lower() == "adamw"):
-        logger.warning(
+        logger.warn(
            f"Unsupported choice of optimizer: {args.optimizer}.Supported optimizers include [adamW, prodigy]."
            "Defaulting to adamW"
        )
        args.optimizer = "adamw"

    if args.use_8bit_adam and not args.optimizer.lower() == "adamw":
-        logger.warning(
+        logger.warn(
            f"use_8bit_adam is ignored when optimizer is not set to 'AdamW'. Optimizer was "
            f"set to {args.optimizer.lower()}"
        )
@@ -1386,11 +1358,11 @@ def main(args):
        optimizer_class = prodigyopt.Prodigy

        if args.learning_rate <= 0.1:
-            logger.warning(
+            logger.warn(
                "Learning rate is too low. When using prodigy, it's generally better to set learning rate around 1.0"
            )
        if args.train_text_encoder and args.text_encoder_lr:
-            logger.warning(
+            logger.warn(
                f"Learning rates were provided both for the unet and the text encoder- e.g. text_encoder_lr:"
                f" {args.text_encoder_lr} and learning_rate: {args.learning_rate}. "
                f"When using prodigy only learning_rate is used as the initial learning rate."
@@ -1475,8 +1447,7 @@ def main(args):
    if not args.train_text_encoder and not train_dataset.custom_instance_prompts:
        del tokenizers, text_encoders
        gc.collect()
-        if torch.cuda.is_available():
-            torch.cuda.empty_cache()
+        torch.cuda.empty_cache()

    # If custom instance prompts are NOT provided (i.e. the instance prompt is used for all images),
    # pack the statically computed variables appropriately here. This is so that we don't
@@ -1919,11 +1890,6 @@ def main(args):
            text_encoder_lora_layers=text_encoder_lora_layers,
            text_encoder_2_lora_layers=text_encoder_2_lora_layers,
        )
-        if args.output_kohya_format:
-            lora_state_dict = load_file(f"{args.output_dir}/pytorch_lora_weights.safetensors")
-            peft_state_dict = convert_all_state_dict_to_peft(lora_state_dict)
-            kohya_state_dict = convert_state_dict_to_kohya(peft_state_dict)
-            save_file(kohya_state_dict, f"{args.output_dir}/pytorch_lora_weights_kohya.safetensors")

        # Final inference
        # Load previous pipeline
@@ -53,7 +53,7 @@ from diffusers.utils.torch_utils import is_compiled_module


 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.28.0.dev0")
+check_min_version("0.27.0.dev0")

 logger = get_logger(__name__, log_level="INFO")

@@ -488,7 +488,7 @@ def main():

            xformers_version = version.parse(xformers.__version__)
            if xformers_version == version.parse("0.0.16"):
-                logger.warning(
+                logger.warn(
                    "xFormers 0.0.16 cannot be used for training in some GPUs. If you observe problems during training, please update xFormers to at least 0.0.17. See https://huggingface.co/docs/diffusers/main/en/optimization/xformers for more details."
                )
            unet.enable_xformers_memory_efficient_attention()
@@ -59,7 +59,7 @@ 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("0.28.0.dev0")
+check_min_version("0.27.0.dev0")

 logger = get_logger(__name__, log_level="INFO")

@@ -71,7 +71,12 @@ TORCH_DTYPE_MAPPING = {"fp32": torch.float32, "fp16": torch.float16, "bf16": tor


 def log_validation(
-    pipeline, args, accelerator, generator, global_step, is_final_validation=False, enable_autocast=True
+    pipeline,
+    args,
+    accelerator,
+    generator,
+    global_step,
+    is_final_validation=False,
 ):
    logger.info(
        f"Running validation... \n Generating {args.num_validation_images} images with prompt:"
@@ -91,7 +96,7 @@ def log_validation(
        else Image.open(image_url_or_path).convert("RGB")
    )(args.val_image_url_or_path)

-    with torch.autocast(accelerator.device.type, enabled=enable_autocast):
+    with torch.autocast(str(accelerator.device).replace(":0", ""), enabled=accelerator.mixed_precision == "fp16"):
        edited_images = []
        # Run inference
        for val_img_idx in range(args.num_validation_images):
@@ -492,13 +497,6 @@ def main():
            ),
        )
    logging_dir = os.path.join(args.output_dir, args.logging_dir)
-
-    if torch.backends.mps.is_available() and args.mixed_precision == "bf16":
-        # due to pytorch#99272, MPS does not yet support bfloat16.
-        raise ValueError(
-            "Mixed precision training with bfloat16 is not supported on MPS. Please use fp16 (recommended) or fp32 instead."
-        )
-
    accelerator_project_config = ProjectConfiguration(project_dir=args.output_dir, logging_dir=logging_dir)
    accelerator = Accelerator(
        gradient_accumulation_steps=args.gradient_accumulation_steps,
@@ -582,7 +580,7 @@ def main():

            xformers_version = version.parse(xformers.__version__)
            if xformers_version == version.parse("0.0.16"):
-                logger.warning(
+                logger.warn(
                    "xFormers 0.0.16 cannot be used for training in some GPUs. If you observe problems during training, please update xFormers to at least 0.0.17. See https://huggingface.co/docs/diffusers/main/en/optimization/xformers for more details."
                )
            unet.enable_xformers_memory_efficient_attention()
@@ -983,13 +981,6 @@ def main():
    if accelerator.is_main_process:
        accelerator.init_trackers("instruct-pix2pix-xl", config=vars(args))

-    # Some configurations require autocast to be disabled.
-    enable_autocast = True
-    if torch.backends.mps.is_available() or (
-        accelerator.mixed_precision == "fp16" or accelerator.mixed_precision == "bf16"
-    ):
-        enable_autocast = False
-
    # Train!
    total_batch_size = args.train_batch_size * accelerator.num_processes * args.gradient_accumulation_steps

@@ -1202,7 +1193,6 @@ def main():
                        generator,
                        global_step,
                        is_final_validation=False,
-                        enable_autocast=enable_autocast,
                    )

                    if args.use_ema:
@@ -1252,7 +1242,6 @@ def main():
                generator,
                global_step,
                is_final_validation=True,
-                enable_autocast=enable_autocast,
            )

    accelerator.end_training()
@@ -52,7 +52,7 @@ if is_wandb_available():


 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.28.0.dev0")
+check_min_version("0.27.0.dev0")

 logger = get_logger(__name__, log_level="INFO")

@@ -177,7 +177,7 @@ def log_validation(vae, image_encoder, image_processor, unet, args, accelerator,
                }
            )
        else:
-            logger.warning(f"image logging not implemented for {tracker.name}")
+            logger.warn(f"image logging not implemented for {tracker.name}")

    del pipeline
    torch.cuda.empty_cache()
@@ -534,7 +534,7 @@ def main():

            xformers_version = version.parse(xformers.__version__)
            if xformers_version == version.parse("0.0.16"):
-                logger.warning(
+                logger.warn(
                    "xFormers 0.0.16 cannot be used for training in some GPUs. If you observe problems during training, please update xFormers to at least 0.0.17. See https://huggingface.co/docs/diffusers/main/en/optimization/xformers for more details."
                )
            unet.enable_xformers_memory_efficient_attention()
@@ -46,7 +46,7 @@ from diffusers.utils import check_min_version, is_wandb_available


 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.28.0.dev0")
+check_min_version("0.27.0.dev0")

 logger = get_logger(__name__, log_level="INFO")

@@ -46,7 +46,7 @@ from diffusers.utils import check_min_version, is_wandb_available


 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.28.0.dev0")
+check_min_version("0.27.0.dev0")

 logger = get_logger(__name__, log_level="INFO")

@@ -51,7 +51,7 @@ if is_wandb_available():


 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.28.0.dev0")
+check_min_version("0.27.0.dev0")

 logger = get_logger(__name__, log_level="INFO")

@@ -180,7 +180,7 @@ def log_validation(
                }
            )
        else:
-            logger.warning(f"image logging not implemented for {tracker.name}")
+            logger.warn(f"image logging not implemented for {tracker.name}")

    del pipeline
    torch.cuda.empty_cache()
@@ -219,7 +219,7 @@ def log_validation(unet, scheduler, args, accelerator, weight_dtype, step, name=
        if args.num_classes is not None:
            class_labels = list(range(args.num_classes))
        else:
-            logger.warning(
+            logger.warn(
                "The model is class-conditional but the number of classes is not set. The generated images will be"
                " unconditional rather than class-conditional."
            )
@@ -266,7 +266,7 @@ def log_validation(unet, scheduler, args, accelerator, weight_dtype, step, name=

            tracker.log({f"validation/{name}": formatted_images})
        else:
-            logger.warning(f"image logging not implemented for {tracker.name}")
+            logger.warn(f"image logging not implemented for {tracker.name}")

    del pipeline
    gc.collect()
@@ -863,14 +863,14 @@ def main(args):
    elif args.model_config_name_or_path is None:
        # TODO: use default architectures from iCT paper
        if not args.class_conditional and (args.num_classes is not None or args.class_embed_type is not None):
-            logger.warning(
+            logger.warn(
                f"`--class_conditional` is set to `False` but `--num_classes` is set to {args.num_classes} and"
                f" `--class_embed_type` is set to {args.class_embed_type}. These values will be overridden to `None`."
            )
            args.num_classes = None
            args.class_embed_type = None
        elif args.class_conditional and args.num_classes is None and args.class_embed_type is None:
-            logger.warning(
+            logger.warn(
                "`--class_conditional` is set to `True` but neither `--num_classes` nor `--class_embed_type` is set."
                "`class_conditional` will be overridden to `False`."
            )
@@ -996,7 +996,7 @@ def main(args):

            xformers_version = version.parse(xformers.__version__)
            if xformers_version == version.parse("0.0.16"):
-                logger.warning(
+                logger.warn(
                    "xFormers 0.0.16 cannot be used for training in some GPUs. If you observe problems during training, please update xFormers to at least 0.0.17. See https://huggingface.co/docs/diffusers/main/en/optimization/xformers for more details."
                )
            unet.enable_xformers_memory_efficient_attention()
@@ -407,7 +407,7 @@ def log_validation(vae, unet, controlnet, args, accelerator, weight_dtype, step)

            tracker.log({"validation": formatted_images})
        else:
-            logger.warning(f"image logging not implemented for {tracker.name}")
+            logger.warn(f"image logging not implemented for {tracker.name}")

        del pipeline
        gc.collect()
@@ -1057,7 +1057,7 @@ def main(args):

            xformers_version = version.parse(xformers.__version__)
            if xformers_version == version.parse("0.0.16"):
-                logger.warning(
+                logger.warn(
                    "xFormers 0.0.16 cannot be used for training in some GPUs. If you observe problems during training, please update xFormers to at least 0.0.17. See https://huggingface.co/docs/diffusers/main/en/optimization/xformers for more details."
                )
            unet.enable_xformers_memory_efficient_attention()
@@ -574,7 +574,7 @@ def main(args):

            xformers_version = version.parse(xformers.__version__)
            if xformers_version == version.parse("0.0.16"):
-                logger.warning(
+                logger.warn(
                    "xFormers 0.0.16 cannot be used for training in some GPUs. If you observe problems during training, please update xFormers to at least 0.0.17. See https://huggingface.co/docs/diffusers/main/en/optimization/xformers for more details."
                )
            unet.enable_xformers_memory_efficient_attention()
@@ -672,7 +672,7 @@ def main(args):

            xformers_version = version.parse(xformers.__version__)
            if xformers_version == version.parse("0.0.16"):
-                logger.warning(
+                logger.warn(
                    "xFormers 0.0.16 cannot be used for training in some GPUs. If you observe problems during training, please update xFormers to at least 0.0.17. See https://huggingface.co/docs/diffusers/main/en/optimization/xformers for more details."
                )
            unet.enable_xformers_memory_efficient_attention()
@@ -1,121 +0,0 @@
-This project is an attempt to check if it's possible to apply to [ORPO](https://arxiv.org/abs/2403.07691) on a text-conditioned diffusion model to align it on preference data WITHOUT a reference model. The implementation is based on https://github.com/huggingface/trl/pull/1435/. 
-
-> [!WARNING] 
-> We assume that MSE in the diffusion formulation approximates the log-probs as required by ORPO (hat-tip to [@kashif](https://github.com/kashif) for the idea). So, please consider this to be extremely experimental.
-
-## Training
-
-Here's training command you can use on a 40GB A100 to validate things on a [small preference
-dataset](https://hf.co/datasets/kashif/pickascore): 
-
-```bash
-accelerate launch train_diffusion_orpo_sdxl_lora.py \
-  --pretrained_model_name_or_path=stabilityai/stable-diffusion-xl-base-1.0  \
-  --pretrained_vae_model_name_or_path=madebyollin/sdxl-vae-fp16-fix \
-  --output_dir="diffusion-sdxl-orpo" \
-  --mixed_precision="fp16" \
-  --dataset_name=kashif/pickascore \
-  --train_batch_size=8 \
-  --gradient_accumulation_steps=2 \
-  --gradient_checkpointing \
-  --use_8bit_adam \
-  --rank=8 \
-  --learning_rate=1e-5 \
-  --report_to="wandb" \
-  --lr_scheduler="constant" \
-  --lr_warmup_steps=0 \
-  --max_train_steps=2000 \
-  --checkpointing_steps=500 \
-  --run_validation --validation_steps=50 \
-  --seed="0" \
-  --report_to="wandb" \
-  --push_to_hub
-```
-
-We also provide a simple script to scale up the training on the [yuvalkirstain/pickapic_v2](https://huggingface.co/datasets/yuvalkirstain/pickapic_v2) dataset:
-
-```bash
-accelerate launch --multi_gpu train_diffusion_orpo_sdxl_lora_wds.py \
-  --pretrained_model_name_or_path=stabilityai/stable-diffusion-xl-base-1.0  \
-  --pretrained_vae_model_name_or_path=madebyollin/sdxl-vae-fp16-fix \
-  --dataset_path="pipe:aws s3 cp s3://diffusion-preference-opt/{00000..00644}.tar -" \
-  --output_dir="diffusion-sdxl-orpo-wds" \
-  --mixed_precision="fp16" \
-  --gradient_accumulation_steps=1 \
-  --gradient_checkpointing \
-  --use_8bit_adam \
-  --rank=8 \
-  --dataloader_num_workers=8 \
-  --learning_rate=3e-5 \
-  --report_to="wandb" \
-  --lr_scheduler="constant" \
-  --lr_warmup_steps=0 \
-  --max_train_steps=50000 \
-  --checkpointing_steps=2000 \
-  --run_validation --validation_steps=500 \
-  --seed="0" \
-  --report_to="wandb" \
-  --push_to_hub
-```
-
-We tested the above on a node of 8 H100s but it should also work on A100s. It requires the `webdataset` library for faster dataloading. Note that we kept the dataset shards on an S3 bucket but it should be also possible to have them stored locally. 
-
-You can use the code below to convert the original dataset into `webdataset` shards:
-
-```python
-import os
-import io
-import ray
-import webdataset as wds
-from datasets import Dataset
-from PIL import Image
-
-ray.init(num_cpus=8)
-
-
-def convert_to_image(im_bytes):
-    return Image.open(io.BytesIO(im_bytes)).convert("RGB")
-
-def main():
-    dataset_path = "/pickapic_v2/data"
-    wds_shards_path = "/pickapic_v2_webdataset"
-    # get all .parquet files in the dataset path
-    dataset_files = [
-        os.path.join(dataset_path, f)
-        for f in os.listdir(dataset_path)
-        if f.endswith(".parquet")
-    ]
-
-    @ray.remote
-    def create_shard(path):
-        # get basename of the file
-        basename = os.path.basename(path)
-        # get the shard number data-00123-of-01034.parquet -> 00123
-        shard_num = basename.split("-")[1]
-        dataset = Dataset.from_parquet(path)
-        # create a webdataset shard
-        shard = wds.TarWriter(os.path.join(wds_shards_path, f"{shard_num}.tar"))
-        
-        for i, example in enumerate(dataset):
-            wds_example = {
-                "__key__": str(i),
-                "original_prompt.txt": example["caption"],
-                "jpg_0.jpg": convert_to_image(example["jpg_0"]),
-                "jpg_1.jpg": convert_to_image(example["jpg_1"]),
-                "label_0.txt": str(example["label_0"]),
-                "label_1.txt": str(example["label_1"])
-            }
-            shard.write(wds_example)
-        shard.close()
-
-    futures = [create_shard.remote(path) for path in dataset_files]
-    ray.get(futures)
-
-
-if __name__ == "__main__":
-    main()
-```
-
-## Inference
-
-Refer to [sayakpaul/diffusion-sdxl-orpo](https://huggingface.co/sayakpaul/diffusion-sdxl-orpo) for an experimental checkpoint.
@@ -1,7 +0,0 @@
-datasets
-accelerate
-transformers
-torchvision
-wandb
-peft
-webdataset
@@ -516,7 +516,7 @@ def main():

            xformers_version = version.parse(xformers.__version__)
            if xformers_version == version.parse("0.0.16"):
-                logger.warning(
+                logger.warn(
                    "xFormers 0.0.16 cannot be used for training in some GPUs. If you observe problems during training, please update xFormers to at least 0.0.17. See https://huggingface.co/docs/diffusers/main/en/optimization/xformers for more details."
                )
            unet.enable_xformers_memory_efficient_attention()
@@ -608,7 +608,7 @@ def main():
    # Create the pipeline using using the trained modules and save it.
    if accelerator.is_main_process:
        if args.push_to_hub and args.only_save_embeds:
-            logger.warning("Enabling full model saving because --push_to_hub=True was specified.")
+            logger.warn("Enabling full model saving because --push_to_hub=True was specified.")
            save_full_model = True
        else:
            save_full_model = not args.only_save_embeds
@@ -541,7 +541,7 @@ def main():

            xformers_version = version.parse(xformers.__version__)
            if xformers_version == version.parse("0.0.16"):
-                logger.warning(
+                logger.warn(
                    "xFormers 0.0.16 cannot be used for training in some GPUs. If you observe problems during training, please update xFormers to at least 0.0.17. See https://huggingface.co/docs/diffusers/main/en/optimization/xformers for more details."
                )
            unet.enable_xformers_memory_efficient_attention()
@@ -23,7 +23,6 @@ TODO:
 6. Integrate to training x
 7. Test
 """
-
 import copy
 import random

@@ -645,7 +645,7 @@ def main():

            xformers_version = version.parse(xformers.__version__)
            if xformers_version == version.parse("0.0.16"):
-                logger.warning(
+                logger.warn(
                    "xFormers 0.0.16 cannot be used for training in some GPUs. If you observe problems during training, please update xFormers to at least 0.0.17. See https://huggingface.co/docs/diffusers/main/en/optimization/xformers for more details."
                )
            unet.enable_xformers_memory_efficient_attention()
@@ -901,7 +901,7 @@ def main():
    accelerator.wait_for_everyone()
    if accelerator.is_main_process:
        if args.push_to_hub and args.only_save_embeds:
-            logger.warning("Enabling full model saving because --push_to_hub=True was specified.")
+            logger.warn("Enabling full model saving because --push_to_hub=True was specified.")
            save_full_model = True
        else:
            save_full_model = not args.only_save_embeds
@@ -108,7 +108,7 @@ def log_validation(vae, text_encoder, tokenizer, unet, args, accelerator, weight
                }
            )
        else:
-            logger.warning(f"image logging not implemented for {tracker.name}")
+            logger.warn(f"image logging not implemented for {tracker.name}")

    del pipeline
    torch.cuda.empty_cache()
@@ -523,7 +523,7 @@ def main():

            xformers_version = version.parse(xformers.__version__)
            if xformers_version == version.parse("0.0.16"):
-                logger.warning(
+                logger.warn(
                    "xFormers 0.0.16 cannot be used for training in some GPUs. If you observe problems during training, please update xFormers to at least 0.0.17. See https://huggingface.co/docs/diffusers/main/en/optimization/xformers for more details."
                )
            unet.enable_xformers_memory_efficient_attention()
@@ -687,7 +687,7 @@ def main():

            xformers_version = version.parse(xformers.__version__)
            if xformers_version == version.parse("0.0.16"):
-                logger.warning(
+                logger.warn(
                    "xFormers 0.0.16 cannot be used for training in some GPUs. If you observe problems during training, please update xFormers to at least 0.0.17. See https://huggingface.co/docs/diffusers/main/en/optimization/xformers for more details."
                )
            unet.enable_xformers_memory_efficient_attention()
@@ -916,7 +916,7 @@ def main():
    accelerator.wait_for_everyone()
    if accelerator.is_main_process:
        if args.push_to_hub and not args.save_as_full_pipeline:
-            logger.warning("Enabling full model saving because --push_to_hub=True was specified.")
+            logger.warn("Enabling full model saving because --push_to_hub=True was specified.")
            save_full_model = True
        else:
            save_full_model = args.save_as_full_pipeline
--- a/Show More
+++ b/Show More
Author	SHA1	Message	Date
Dhruv Nair	4b682be902	update	2024-03-12 13:08:23 +00:00
Dhruv Nair	3d0bb51d53	update	2024-03-12 13:04:25 +00:00
Dhruv Nair	4b72aae0cd	update	2024-03-12 08:52:55 +00:00
Dhruv Nair	33bbe58ea7	update	2024-03-12 05:41:37 +00:00