Skip to content

GitLab

Commit e178cada authored by wangwei990215's avatar wangwei990215
Browse files

initial commit

parents
Expand all Hide whitespace changes
Inline Side-by-side
Showing with 2203 additions and 0 deletions
diffusers-0.27.0/.github/workflows/pr_torch_dependency_test.yml 0 → 100755
View file @ e178cada
name: Run Torch dependency tests
on:
pull_request:
branches:
- main
paths:
- "src/diffusers/**.py"
push:
branches:
- main
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}
cancel-in-progress: true
jobs:
check_torch_dependencies:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v3
- name: Set up Python
uses: actions/setup-python@v4
with:
python-version: "3.8"
- name: Install dependencies
run: |
python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
python -m pip install --upgrade pip uv
python -m uv pip install -e .
python -m uv pip install torch torchvision torchaudio
python -m uv pip install pytest
- name: Check for soft dependencies
run: |
python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
pytest tests/others/test_dependencies.py
diffusers-0.27.0/.github/workflows/push_tests.yml 0 → 100755
View file @ e178cada
name: Slow Tests on main
on:
push:
branches:
- main
paths:
- "src/diffusers/**.py"
- "examples/**.py"
- "tests/**.py"
env:
DIFFUSERS_IS_CI: yes
HF_HOME: /mnt/cache
OMP_NUM_THREADS: 8
MKL_NUM_THREADS: 8
PYTEST_TIMEOUT: 600
RUN_SLOW: yes
PIPELINE_USAGE_CUTOFF: 50000
jobs:
setup_torch_cuda_pipeline_matrix:
name: Setup Torch Pipelines CUDA Slow Tests Matrix
runs-on: [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: ${{ steps.fetch_pipeline_matrix.outputs.pipeline_test_matrix }}
steps:
- name: Checkout diffusers
uses: actions/checkout@v3
with:
fetch-depth: 2
- name: Install dependencies
run: |
apt-get update && apt-get install libsndfile1-dev libgl1 -y
python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
python -m uv pip install -e [quality,test]
python -m uv pip install accelerate@git+https://github.com/huggingface/accelerate.git
- name: Environment
run: |
python utils/print_env.py
- name: 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
torch_pipelines_cuda_tests:
name: Torch Pipelines CUDA Slow Tests
needs: setup_torch_cuda_pipeline_matrix
strategy:
fail-fast: false
matrix:
module: ${{ fromJson(needs.setup_torch_cuda_pipeline_matrix.outputs.pipeline_test_matrix) }}
runs-on: [single-gpu, nvidia-gpu, t4, ci]
container:
image: diffusers/diffusers-pytorch-cuda
options: --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/ --gpus 0
steps:
- name: Checkout diffusers
uses: actions/checkout@v3
with:
fetch-depth: 2
- name: NVIDIA-SMI
run: |
nvidia-smi
- name: Install dependencies
run: |
apt-get update && apt-get install libsndfile1-dev libgl1 -y
python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
python -m uv pip install -e [quality,test]
python -m uv pip install accelerate@git+https://github.com/huggingface/accelerate.git
- name: Environment
run: |
python utils/print_env.py
- name: Slow PyTorch CUDA checkpoint tests on Ubuntu
env:
HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
# https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
CUBLAS_WORKSPACE_CONFIG: :16:8
run: |
python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-s -v -k "not Flax and not Onnx" \
--make-reports=tests_pipeline_${{ matrix.module }}_cuda \
tests/pipelines/${{ matrix.module }}
- name: Failure short reports
if: ${{ failure() }}
run: |
cat reports/tests_pipeline_${{ matrix.module }}_cuda_stats.txt
cat reports/tests_pipeline_${{ matrix.module }}_cuda_failures_short.txt
- name: Test suite reports artifacts
if: ${{ always() }}
uses: actions/upload-artifact@v2
with:
name: pipeline_${{ matrix.module }}_test_reports
path: reports
torch_cuda_tests:
name: Torch CUDA Tests
runs-on: docker-gpu
container:
image: diffusers/diffusers-pytorch-cuda
options: --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/ --gpus 0
defaults:
run:
shell: bash
strategy:
matrix:
module: [models, schedulers, lora, others]
steps:
- name: Checkout diffusers
uses: actions/checkout@v3
with:
fetch-depth: 2
- name: Install dependencies
run: |
apt-get update && apt-get install libsndfile1-dev libgl1 -y
python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
python -m uv pip install -e [quality,test]
python -m uv pip install accelerate@git+https://github.com/huggingface/accelerate.git
- name: Environment
run: |
python utils/print_env.py
- name: Run slow PyTorch CUDA tests
env:
HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
# https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
CUBLAS_WORKSPACE_CONFIG: :16:8
run: |
python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-s -v -k "not Flax and not Onnx" \
--make-reports=tests_torch_cuda \
tests/${{ matrix.module }}
- name: Failure short reports
if: ${{ failure() }}
run: |
cat reports/tests_torch_cuda_stats.txt
cat reports/tests_torch_cuda_failures_short.txt
- name: Test suite reports artifacts
if: ${{ always() }}
uses: actions/upload-artifact@v2
with:
name: torch_cuda_test_reports
path: reports
peft_cuda_tests:
name: PEFT CUDA Tests
runs-on: docker-gpu
container:
image: diffusers/diffusers-pytorch-cuda
options: --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/ --gpus 0
defaults:
run:
shell: bash
steps:
- name: Checkout diffusers
uses: actions/checkout@v3
with:
fetch-depth: 2
- name: Install dependencies
run: |
apt-get update && apt-get install libsndfile1-dev libgl1 -y
python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
python -m uv pip install -e [quality,test]
python -m uv pip install accelerate@git+https://github.com/huggingface/accelerate.git
python -m uv pip install peft@git+https://github.com/huggingface/peft.git
- name: Environment
run: |
python utils/print_env.py
- name: Run slow PEFT CUDA tests
env:
HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
# https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
CUBLAS_WORKSPACE_CONFIG: :16:8
run: |
python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-s -v -k "not Flax and not Onnx and not PEFTLoRALoading" \
--make-reports=tests_peft_cuda \
tests/lora/
- name: Failure short reports
if: ${{ failure() }}
run: |
cat reports/tests_peft_cuda_stats.txt
cat reports/tests_peft_cuda_failures_short.txt
- name: Test suite reports artifacts
if: ${{ always() }}
uses: actions/upload-artifact@v2
with:
name: torch_peft_test_reports
path: reports
flax_tpu_tests:
name: Flax TPU Tests
runs-on: docker-tpu
container:
image: diffusers/diffusers-flax-tpu
options: --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/ --privileged
defaults:
run:
shell: bash
steps:
- name: Checkout diffusers
uses: actions/checkout@v3
with:
fetch-depth: 2
- name: Install dependencies
run: |
apt-get update && apt-get install libsndfile1-dev libgl1 -y
python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
python -m uv pip install -e [quality,test]
python -m uv pip install accelerate@git+https://github.com/huggingface/accelerate.git
- name: Environment
run: |
python utils/print_env.py
- name: Run slow Flax TPU tests
env:
HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
run: |
python -m pytest -n 0 \
-s -v -k "Flax" \
--make-reports=tests_flax_tpu \
tests/
- name: Failure short reports
if: ${{ failure() }}
run: |
cat reports/tests_flax_tpu_stats.txt
cat reports/tests_flax_tpu_failures_short.txt
- name: Test suite reports artifacts
if: ${{ always() }}
uses: actions/upload-artifact@v2
with:
name: flax_tpu_test_reports
path: reports
onnx_cuda_tests:
name: ONNX CUDA Tests
runs-on: docker-gpu
container:
image: diffusers/diffusers-onnxruntime-cuda
options: --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/ --gpus 0
defaults:
run:
shell: bash
steps:
- name: Checkout diffusers
uses: actions/checkout@v3
with:
fetch-depth: 2
- name: Install dependencies
run: |
apt-get update && apt-get install libsndfile1-dev libgl1 -y
python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
python -m uv pip install -e [quality,test]
python -m uv pip install accelerate@git+https://github.com/huggingface/accelerate.git
- name: Environment
run: |
python utils/print_env.py
- name: Run slow ONNXRuntime CUDA tests
env:
HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
run: |
python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-s -v -k "Onnx" \
--make-reports=tests_onnx_cuda \
tests/
- name: Failure short reports
if: ${{ failure() }}
run: |
cat reports/tests_onnx_cuda_stats.txt
cat reports/tests_onnx_cuda_failures_short.txt
- name: Test suite reports artifacts
if: ${{ always() }}
uses: actions/upload-artifact@v2
with:
name: onnx_cuda_test_reports
path: reports
run_torch_compile_tests:
name: PyTorch Compile CUDA tests
runs-on: docker-gpu
container:
image: diffusers/diffusers-pytorch-compile-cuda
options: --gpus 0 --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/
steps:
- name: Checkout diffusers
uses: actions/checkout@v3
with:
fetch-depth: 2
- name: NVIDIA-SMI
run: |
nvidia-smi
- name: Install dependencies
run: |
python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
python -m uv pip install -e [quality,test,training]
- name: Environment
run: |
python utils/print_env.py
- name: Run example tests on GPU
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 "compile" --make-reports=tests_torch_compile_cuda tests/
- name: Failure short reports
if: ${{ failure() }}
run: cat reports/tests_torch_compile_cuda_failures_short.txt
- name: Test suite reports artifacts
if: ${{ always() }}
uses: actions/upload-artifact@v2
with:
name: torch_compile_test_reports
path: reports
run_xformers_tests:
name: PyTorch xformers CUDA tests
runs-on: docker-gpu
container:
image: diffusers/diffusers-pytorch-xformers-cuda
options: --gpus 0 --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/
steps:
- name: Checkout diffusers
uses: actions/checkout@v3
with:
fetch-depth: 2
- name: NVIDIA-SMI
run: |
nvidia-smi
- name: Install dependencies
run: |
python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
python -m uv pip install -e [quality,test,training]
- name: Environment
run: |
python utils/print_env.py
- name: Run example tests on GPU
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 "xformers" --make-reports=tests_torch_xformers_cuda tests/
- name: Failure short reports
if: ${{ failure() }}
run: cat reports/tests_torch_xformers_cuda_failures_short.txt
- name: Test suite reports artifacts
if: ${{ always() }}
uses: actions/upload-artifact@v2
with:
name: torch_xformers_test_reports
path: reports
run_examples_tests:
name: Examples PyTorch CUDA tests on Ubuntu
runs-on: docker-gpu
container:
image: diffusers/diffusers-pytorch-cuda
options: --gpus 0 --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/
steps:
- name: Checkout diffusers
uses: actions/checkout@v3
with:
fetch-depth: 2
- name: NVIDIA-SMI
run: |
nvidia-smi
- name: Install dependencies
run: |
python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
python -m uv pip install -e [quality,test,training]
- name: Environment
run: |
python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
python utils/print_env.py
- name: Run example tests on GPU
env:
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 --make-reports=examples_torch_cuda examples/
- name: Failure short reports
if: ${{ failure() }}
run: |
cat reports/examples_torch_cuda_stats.txt
cat reports/examples_torch_cuda_failures_short.txt
- name: Test suite reports artifacts
if: ${{ always() }}
uses: actions/upload-artifact@v2
with:
name: examples_test_reports
path: reports
\ No newline at end of file
diffusers-0.27.0/.github/workflows/push_tests_fast.yml 0 → 100755
View file @ e178cada
name: Fast tests on main
on:
push:
branches:
- main
paths:
- "src/diffusers/**.py"
- "examples/**.py"
- "tests/**.py"
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}
cancel-in-progress: true
env:
DIFFUSERS_IS_CI: yes
HF_HOME: /mnt/cache
OMP_NUM_THREADS: 8
MKL_NUM_THREADS: 8
PYTEST_TIMEOUT: 600
RUN_SLOW: no
jobs:
run_fast_tests:
strategy:
fail-fast: false
matrix:
config:
- name: Fast PyTorch CPU tests on Ubuntu
framework: pytorch
runner: docker-cpu
image: diffusers/diffusers-pytorch-cpu
report: torch_cpu
- name: Fast Flax CPU tests on Ubuntu
framework: flax
runner: docker-cpu
image: diffusers/diffusers-flax-cpu
report: flax_cpu
- name: Fast ONNXRuntime CPU tests on Ubuntu
framework: onnxruntime
runner: docker-cpu
image: diffusers/diffusers-onnxruntime-cpu
report: onnx_cpu
- name: PyTorch Example CPU tests on Ubuntu
framework: pytorch_examples
runner: docker-cpu
image: diffusers/diffusers-pytorch-cpu
report: torch_example_cpu
name: ${{ matrix.config.name }}
runs-on: ${{ matrix.config.runner }}
container:
image: ${{ matrix.config.image }}
options: --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/
defaults:
run:
shell: bash
steps:
- name: Checkout diffusers
uses: actions/checkout@v3
with:
fetch-depth: 2
- name: Install dependencies
run: |
apt-get update && apt-get install libsndfile1-dev libgl1 -y
python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
python -m uv pip install -e [quality,test]
- name: Environment
run: |
python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
python utils/print_env.py
- name: Run fast PyTorch CPU tests
if: ${{ matrix.config.framework == 'pytorch' }}
run: |
python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
python -m pytest -n 2 --max-worker-restart=0 --dist=loadfile \
-s -v -k "not Flax and not Onnx" \
--make-reports=tests_${{ matrix.config.report }} \
tests/
- name: Run fast Flax TPU tests
if: ${{ matrix.config.framework == 'flax' }}
run: |
python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
python -m pytest -n 2 --max-worker-restart=0 --dist=loadfile \
-s -v -k "Flax" \
--make-reports=tests_${{ matrix.config.report }} \
tests/
- name: Run fast ONNXRuntime CPU tests
if: ${{ matrix.config.framework == 'onnxruntime' }}
run: |
python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
python -m pytest -n 2 --max-worker-restart=0 --dist=loadfile \
-s -v -k "Onnx" \
--make-reports=tests_${{ matrix.config.report }} \
tests/
- name: Run example PyTorch CPU tests
if: ${{ matrix.config.framework == 'pytorch_examples' }}
run: |
python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
python -m uv pip install peft
python -m pytest -n 2 --max-worker-restart=0 --dist=loadfile \
--make-reports=tests_${{ matrix.config.report }} \
examples
- name: Failure short reports
if: ${{ failure() }}
run: cat reports/tests_${{ matrix.config.report }}_failures_short.txt
- name: Test suite reports artifacts
if: ${{ always() }}
uses: actions/upload-artifact@v2
with:
name: pr_${{ matrix.config.report }}_test_reports
path: reports
diffusers-0.27.0/.github/workflows/push_tests_mps.yml 0 → 100755
View file @ e178cada
name: Fast mps tests on main
on:
push:
branches:
- main
paths:
- "src/diffusers/**.py"
- "tests/**.py"
env:
DIFFUSERS_IS_CI: yes
HF_HOME: /mnt/cache
OMP_NUM_THREADS: 8
MKL_NUM_THREADS: 8
PYTEST_TIMEOUT: 600
RUN_SLOW: no
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}
cancel-in-progress: true
jobs:
run_fast_tests_apple_m1:
name: Fast PyTorch MPS tests on MacOS
runs-on: [ self-hosted, apple-m1 ]
steps:
- name: Checkout diffusers
uses: actions/checkout@v3
with:
fetch-depth: 2
- name: Clean checkout
shell: arch -arch arm64 bash {0}
run: |
git clean -fxd
- name: Setup miniconda
uses: ./.github/actions/setup-miniconda
with:
python-version: 3.9
- name: Install dependencies
shell: arch -arch arm64 bash {0}
run: |
${CONDA_RUN} python -m pip install --upgrade pip uv
${CONDA_RUN} python -m uv pip install -e [quality,test]
${CONDA_RUN} python -m uv pip install torch torchvision torchaudio
${CONDA_RUN} python -m uv pip install accelerate@git+https://github.com/huggingface/accelerate.git
${CONDA_RUN} python -m uv pip install transformers --upgrade
- name: Environment
shell: arch -arch arm64 bash {0}
run: |
${CONDA_RUN} python utils/print_env.py
- name: Run fast PyTorch tests on M1 (MPS)
shell: arch -arch arm64 bash {0}
env:
HF_HOME: /System/Volumes/Data/mnt/cache
HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
run: |
${CONDA_RUN} python -m pytest -n 0 -s -v --make-reports=tests_torch_mps tests/
- name: Failure short reports
if: ${{ failure() }}
run: cat reports/tests_torch_mps_failures_short.txt
- name: Test suite reports artifacts
if: ${{ always() }}
uses: actions/upload-artifact@v2
with:
name: pr_torch_mps_test_reports
path: reports
diffusers-0.27.0/.github/workflows/pypi_publish.yaml 0 → 100755
View file @ e178cada
# 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
- 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
diffusers-0.27.0/.github/workflows/stale.yml 0 → 100755
View file @ e178cada
name: Stale Bot
on:
schedule:
- cron: "0 15 * * *"
jobs:
close_stale_issues:
name: Close Stale Issues
if: github.repository == 'huggingface/diffusers'
runs-on: ubuntu-latest
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
steps:
- uses: actions/checkout@v2
- name: Setup Python
uses: actions/setup-python@v1
with:
python-version: 3.8
- name: Install requirements
run: |
pip install PyGithub
- name: Close stale issues
run: |
python utils/stale.py
diffusers-0.27.0/.github/workflows/typos.yml 0 → 100755
View file @ e178cada
name: Check typos
on:
workflow_dispatch:
jobs:
build:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v3
- name: typos-action
uses: crate-ci/typos@v1.12.4
diffusers-0.27.0/.github/workflows/upload_pr_documentation.yml 0 → 100755
View file @ e178cada
name: Upload PR Documentation
on:
workflow_run:
workflows: ["Build PR Documentation"]
types:
- completed
jobs:
build:
uses: huggingface/doc-builder/.github/workflows/upload_pr_documentation.yml@main
with:
package_name: diffusers
secrets:
hf_token: ${{ secrets.HF_DOC_BUILD_PUSH }}
comment_bot_token: ${{ secrets.COMMENT_BOT_TOKEN }}
diffusers-0.27.0/.gitignore 0 → 100755
View file @ e178cada
# Initially taken from GitHub's Python gitignore file
# Byte-compiled / optimized / DLL files
__pycache__/
*.py[cod]
*$py.class
# C extensions
*.so
# tests and logs
tests/fixtures/cached_*_text.txt
logs/
lightning_logs/
lang_code_data/
# Distribution / packaging
.Python
build/
develop-eggs/
dist/
downloads/
eggs/
.eggs/
lib/
lib64/
parts/
sdist/
var/
wheels/
*.egg-info/
.installed.cfg
*.egg
MANIFEST
# PyInstaller
# Usually these files are written by a Python script from a template
# before PyInstaller builds the exe, so as to inject date/other infos into it.
*.manifest
*.spec
# Installer logs
pip-log.txt
pip-delete-this-directory.txt
# Unit test / coverage reports
htmlcov/
.tox/
.nox/
.coverage
.coverage.*
.cache
nosetests.xml
coverage.xml
*.cover
.hypothesis/
.pytest_cache/
# Translations
*.mo
*.pot
# Django stuff:
*.log
local_settings.py
db.sqlite3
# Flask stuff:
instance/
.webassets-cache
# Scrapy stuff:
.scrapy
# Sphinx documentation
docs/_build/
# PyBuilder
target/
# Jupyter Notebook
.ipynb_checkpoints
# IPython
profile_default/
ipython_config.py
# pyenv
.python-version
# celery beat schedule file
celerybeat-schedule
# SageMath parsed files
*.sage.py
# Environments
.env
.venv
env/
venv/
ENV/
env.bak/
venv.bak/
# Spyder project settings
.spyderproject
.spyproject
# Rope project settings
.ropeproject
# mkdocs documentation
/site
# mypy
.mypy_cache/
.dmypy.json
dmypy.json
# Pyre type checker
.pyre/
# vscode
.vs
.vscode
# Pycharm
.idea
# TF code
tensorflow_code
# Models
proc_data
# examples
runs
/runs_old
/wandb
/examples/runs
/examples/**/*.args
/examples/rag/sweep
# data
/data
serialization_dir
# emacs
*.*~
debug.env
# vim
.*.swp
# ctags
tags
# pre-commit
.pre-commit*
# .lock
*.lock
# DS_Store (MacOS)
.DS_Store
# RL pipelines may produce mp4 outputs
*.mp4
# dependencies
/transformers
# ruff
.ruff_cache
# wandb
wandb
diffusers-0.27.0/CITATION.cff 0 → 100755
View file @ e178cada
cff-version: 1.2.0
title: 'Diffusers: State-of-the-art diffusion models'
message: >-
If you use this software, please cite it using the
metadata from this file.
type: software
authors:
- given-names: Patrick
family-names: von Platen
- given-names: Suraj
family-names: Patil
- given-names: Anton
family-names: Lozhkov
- given-names: Pedro
family-names: Cuenca
- given-names: Nathan
family-names: Lambert
- given-names: Kashif
family-names: Rasul
- given-names: Mishig
family-names: Davaadorj
- given-names: Thomas
family-names: Wolf
repository-code: 'https://github.com/huggingface/diffusers'
abstract: >-
Diffusers provides pretrained diffusion models across
multiple modalities, such as vision and audio, and serves
as a modular toolbox for inference and training of
diffusion models.
keywords:
- deep-learning
- pytorch
- image-generation
- hacktoberfest
- diffusion
- text2image
- image2image
- score-based-generative-modeling
- stable-diffusion
- stable-diffusion-diffusers
license: Apache-2.0
version: 0.12.1
diffusers-0.27.0/CODE_OF_CONDUCT.md 0 → 100755
View file @ e178cada
# Contributor Covenant Code of Conduct
## Our Pledge
We as members, contributors, and leaders pledge to make participation in our
community a harassment-free experience for everyone, regardless of age, body
size, visible or invisible disability, ethnicity, sex characteristics, gender
identity and expression, level of experience, education, socio-economic status,
nationality, personal appearance, race, caste, color, religion, or sexual identity
and orientation.
We pledge to act and interact in ways that contribute to an open, welcoming,
diverse, inclusive, and healthy community.
## Our Standards
Examples of behavior that contributes to a positive environment for our
community include:
* Demonstrating empathy and kindness toward other people
* Being respectful of differing opinions, viewpoints, and experiences
* Giving and gracefully accepting constructive feedback
* Accepting responsibility and apologizing to those affected by our mistakes,
and learning from the experience
* Focusing on what is best not just for us as individuals, but for the
overall Diffusers community
Examples of unacceptable behavior include:
* The use of sexualized language or imagery, and sexual attention or
advances of any kind
* Trolling, insulting or derogatory comments, and personal or political attacks
* Public or private harassment
* Publishing others' private information, such as a physical or email
address, without their explicit permission
* Spamming issues or PRs with links to projects unrelated to this library
* Other conduct which could reasonably be considered inappropriate in a
professional setting
## Enforcement Responsibilities
Community leaders are responsible for clarifying and enforcing our standards of
acceptable behavior and will take appropriate and fair corrective action in
response to any behavior that they deem inappropriate, threatening, offensive,
or harmful.
Community leaders have the right and responsibility to remove, edit, or reject
comments, commits, code, wiki edits, issues, and other contributions that are
not aligned to this Code of Conduct, and will communicate reasons for moderation
decisions when appropriate.
## Scope
This Code of Conduct applies within all community spaces, and also applies when
an individual is officially representing the community in public spaces.
Examples of representing our community include using an official e-mail address,
posting via an official social media account, or acting as an appointed
representative at an online or offline event.
## Enforcement
Instances of abusive, harassing, or otherwise unacceptable behavior may be
reported to the community leaders responsible for enforcement at
feedback@huggingface.co.
All complaints will be reviewed and investigated promptly and fairly.
All community leaders are obligated to respect the privacy and security of the
reporter of any incident.
## Enforcement Guidelines
Community leaders will follow these Community Impact Guidelines in determining
the consequences for any action they deem in violation of this Code of Conduct:
### 1. Correction
**Community Impact**: Use of inappropriate language or other behavior deemed
unprofessional or unwelcome in the community.
**Consequence**: A private, written warning from community leaders, providing
clarity around the nature of the violation and an explanation of why the
behavior was inappropriate. A public apology may be requested.
### 2. Warning
**Community Impact**: A violation through a single incident or series
of actions.
**Consequence**: A warning with consequences for continued behavior. No
interaction with the people involved, including unsolicited interaction with
those enforcing the Code of Conduct, for a specified period of time. This
includes avoiding interactions in community spaces as well as external channels
like social media. Violating these terms may lead to a temporary or
permanent ban.
### 3. Temporary Ban
**Community Impact**: A serious violation of community standards, including
sustained inappropriate behavior.
**Consequence**: A temporary ban from any sort of interaction or public
communication with the community for a specified period of time. No public or
private interaction with the people involved, including unsolicited interaction
with those enforcing the Code of Conduct, is allowed during this period.
Violating these terms may lead to a permanent ban.
### 4. Permanent Ban
**Community Impact**: Demonstrating a pattern of violation of community
standards, including sustained inappropriate behavior, harassment of an
individual, or aggression toward or disparagement of classes of individuals.
**Consequence**: A permanent ban from any sort of public interaction within
the community.
## Attribution
This Code of Conduct is adapted from the [Contributor Covenant][homepage],
version 2.1, available at
https://www.contributor-covenant.org/version/2/1/code_of_conduct.html.
Community Impact Guidelines were inspired by [Mozilla's code of conduct
enforcement ladder](https://github.com/mozilla/diversity).
[homepage]: https://www.contributor-covenant.org
For answers to common questions about this code of conduct, see the FAQ at
https://www.contributor-covenant.org/faq. Translations are available at
https://www.contributor-covenant.org/translations.
diffusers-0.27.0/CONTRIBUTING.md 0 → 100755
View file @ e178cada
This diff is collapsed.
diffusers-0.27.0/LICENSE 0 → 100755
View file @ e178cada
Apache License
Version 2.0, January 2004
http://www.apache.org/licenses/
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
1. Definitions.
"License" shall mean the terms and conditions for use, reproduction,
and distribution as defined by Sections 1 through 9 of this document.
"Licensor" shall mean the copyright owner or entity authorized by
the copyright owner that is granting the License.
"Legal Entity" shall mean the union of the acting entity and all
other entities that control, are controlled by, or are under common
control with that entity. For the purposes of this definition,
"control" means (i) the power, direct or indirect, to cause the
direction or management of such entity, whether by contract or
otherwise, or (ii) ownership of fifty percent (50%) or more of the
outstanding shares, or (iii) beneficial ownership of such entity.
"You" (or "Your") shall mean an individual or Legal Entity
exercising permissions granted by this License.
"Source" form shall mean the preferred form for making modifications,
including but not limited to software source code, documentation
source, and configuration files.
"Object" form shall mean any form resulting from mechanical
transformation or translation of a Source form, including but
not limited to compiled object code, generated documentation,
and conversions to other media types.
"Work" shall mean the work of authorship, whether in Source or
Object form, made available under the License, as indicated by a
copyright notice that is included in or attached to the work
(an example is provided in the Appendix below).
"Derivative Works" shall mean any work, whether in Source or Object
form, that is based on (or derived from) the Work and for which the
editorial revisions, annotations, elaborations, or other modifications
represent, as a whole, an original work of authorship. For the purposes
of this License, Derivative Works shall not include works that remain
separable from, or merely link (or bind by name) to the interfaces of,
the Work and Derivative Works thereof.
"Contribution" shall mean any work of authorship, including
the original version of the Work and any modifications or additions
to that Work or Derivative Works thereof, that is intentionally
submitted to Licensor for inclusion in the Work by the copyright owner
or by an individual or Legal Entity authorized to submit on behalf of
the copyright owner. For the purposes of this definition, "submitted"
means any form of electronic, verbal, or written communication sent
to the Licensor or its representatives, including but not limited to
communication on electronic mailing lists, source code control systems,
and issue tracking systems that are managed by, or on behalf of, the
Licensor for the purpose of discussing and improving the Work, but
excluding communication that is conspicuously marked or otherwise
designated in writing by the copyright owner as "Not a Contribution."
"Contributor" shall mean Licensor and any individual or Legal Entity
on behalf of whom a Contribution has been received by Licensor and
subsequently incorporated within the Work.
2. Grant of Copyright License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
copyright license to reproduce, prepare Derivative Works of,
publicly display, publicly perform, sublicense, and distribute the
Work and such Derivative Works in Source or Object form.
3. Grant of Patent License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
(except as stated in this section) patent license to make, have made,
use, offer to sell, sell, import, and otherwise transfer the Work,
where such license applies only to those patent claims licensable
by such Contributor that are necessarily infringed by their
Contribution(s) alone or by combination of their Contribution(s)
with the Work to which such Contribution(s) was submitted. If You
institute patent litigation against any entity (including a
cross-claim or counterclaim in a lawsuit) alleging that the Work
or a Contribution incorporated within the Work constitutes direct
or contributory patent infringement, then any patent licenses
granted to You under this License for that Work shall terminate
as of the date such litigation is filed.
4. Redistribution. You may reproduce and distribute copies of the
Work or Derivative Works thereof in any medium, with or without
modifications, and in Source or Object form, provided that You
meet the following conditions:
(a) You must give any other recipients of the Work or
Derivative Works a copy of this License; and
(b) You must cause any modified files to carry prominent notices
stating that You changed the files; and
(c) You must retain, in the Source form of any Derivative Works
that You distribute, all copyright, patent, trademark, and
attribution notices from the Source form of the Work,
excluding those notices that do not pertain to any part of
the Derivative Works; and
(d) If the Work includes a "NOTICE" text file as part of its
distribution, then any Derivative Works that You distribute must
include a readable copy of the attribution notices contained
within such NOTICE file, excluding those notices that do not
pertain to any part of the Derivative Works, in at least one
of the following places: within a NOTICE text file distributed
as part of the Derivative Works; within the Source form or
documentation, if provided along with the Derivative Works; or,
within a display generated by the Derivative Works, if and
wherever such third-party notices normally appear. The contents
of the NOTICE file are for informational purposes only and
do not modify the License. You may add Your own attribution
notices within Derivative Works that You distribute, alongside
or as an addendum to the NOTICE text from the Work, provided
that such additional attribution notices cannot be construed
as modifying the License.
You may add Your own copyright statement to Your modifications and
may provide additional or different license terms and conditions
for use, reproduction, or distribution of Your modifications, or
for any such Derivative Works as a whole, provided Your use,
reproduction, and distribution of the Work otherwise complies with
the conditions stated in this License.
5. Submission of Contributions. Unless You explicitly state otherwise,
any Contribution intentionally submitted for inclusion in the Work
by You to the Licensor shall be under the terms and conditions of
this License, without any additional terms or conditions.
Notwithstanding the above, nothing herein shall supersede or modify
the terms of any separate license agreement you may have executed
with Licensor regarding such Contributions.
6. Trademarks. This License does not grant permission to use the trade
names, trademarks, service marks, or product names of the Licensor,
except as required for reasonable and customary use in describing the
origin of the Work and reproducing the content of the NOTICE file.
7. Disclaimer of Warranty. Unless required by applicable law or
agreed to in writing, Licensor provides the Work (and each
Contributor provides its Contributions) on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
implied, including, without limitation, any warranties or conditions
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
PARTICULAR PURPOSE. You are solely responsible for determining the
appropriateness of using or redistributing the Work and assume any
risks associated with Your exercise of permissions under this License.
8. Limitation of Liability. In no event and under no legal theory,
whether in tort (including negligence), contract, or otherwise,
unless required by applicable law (such as deliberate and grossly
negligent acts) or agreed to in writing, shall any Contributor be
liable to You for damages, including any direct, indirect, special,
incidental, or consequential damages of any character arising as a
result of this License or out of the use or inability to use the
Work (including but not limited to damages for loss of goodwill,
work stoppage, computer failure or malfunction, or any and all
other commercial damages or losses), even if such Contributor
has been advised of the possibility of such damages.
9. Accepting Warranty or Additional Liability. While redistributing
the Work or Derivative Works thereof, You may choose to offer,
and charge a fee for, acceptance of support, warranty, indemnity,
or other liability obligations and/or rights consistent with this
License. However, in accepting such obligations, You may act only
on Your own behalf and on Your sole responsibility, not on behalf
of any other Contributor, and only if You agree to indemnify,
defend, and hold each Contributor harmless for any liability
incurred by, or claims asserted against, such Contributor by reason
of your accepting any such warranty or additional liability.
END OF TERMS AND CONDITIONS
APPENDIX: How to apply the Apache License to your work.
To apply the Apache License to your work, attach the following
boilerplate notice, with the fields enclosed by brackets "[]"
replaced with your own identifying information. (Don't include
the brackets!) The text should be enclosed in the appropriate
comment syntax for the file format. We also recommend that a
file or class name and description of purpose be included on the
same "printed page" as the copyright notice for easier
identification within third-party archives.
Copyright [yyyy] [name of copyright owner]
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.
diffusers-0.27.0/MANIFEST.in 0 → 100755
View file @ e178cada
include LICENSE
include src/diffusers/utils/model_card_template.md
diffusers-0.27.0/Makefile 0 → 100755
View file @ e178cada
.PHONY: deps_table_update modified_only_fixup extra_style_checks quality style fixup fix-copies test test-examples
# make sure to test the local checkout in scripts and not the pre-installed one (don't use quotes!)
export PYTHONPATH = src
check_dirs := examples scripts src tests utils benchmarks
modified_only_fixup:
$(eval modified_py_files := $(shell python utils/get_modified_files.py $(check_dirs)))
@if test -n "$(modified_py_files)"; then \
echo "Checking/fixing $(modified_py_files)"; \
ruff check $(modified_py_files) --fix; \
ruff format $(modified_py_files);\
else \
echo "No library .py files were modified"; \
fi
# Update src/diffusers/dependency_versions_table.py
deps_table_update:
@python setup.py deps_table_update
deps_table_check_updated:
@md5sum src/diffusers/dependency_versions_table.py > md5sum.saved
@python setup.py deps_table_update
@md5sum -c --quiet md5sum.saved || (printf "\nError: the version dependency table is outdated.\nPlease run 'make fixup' or 'make style' and commit the changes.\n\n" && exit 1)
@rm md5sum.saved
# autogenerating code
autogenerate_code: deps_table_update
# Check that the repo is in a good state
repo-consistency:
python utils/check_dummies.py
python utils/check_repo.py
python utils/check_inits.py
# this target runs checks on all files
quality:
ruff check $(check_dirs) setup.py
ruff format --check $(check_dirs) setup.py
python utils/check_doc_toc.py
# Format source code automatically and check is there are any problems left that need manual fixing
extra_style_checks:
python utils/custom_init_isort.py
python utils/check_doc_toc.py --fix_and_overwrite
# this target runs checks on all files and potentially modifies some of them
style:
ruff check $(check_dirs) setup.py --fix
ruff format $(check_dirs) setup.py
${MAKE} autogenerate_code
${MAKE} extra_style_checks
# Super fast fix and check target that only works on relevant modified files since the branch was made
fixup: modified_only_fixup extra_style_checks autogenerate_code repo-consistency
# Make marked copies of snippets of codes conform to the original
fix-copies:
python utils/check_copies.py --fix_and_overwrite
python utils/check_dummies.py --fix_and_overwrite
# Run tests for the library
test:
python -m pytest -n auto --dist=loadfile -s -v ./tests/
# Run tests for examples
test-examples:
python -m pytest -n auto --dist=loadfile -s -v ./examples/
# Release stuff
pre-release:
python utils/release.py
pre-patch:
python utils/release.py --patch
post-release:
python utils/release.py --post_release
post-patch:
python utils/release.py --post_release --patch
diffusers-0.27.0/PHILOSOPHY.md 0 → 100755
View file @ e178cada
<!--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.
-->
# Philosophy
🧨 Diffusers provides **state-of-the-art** pretrained diffusion models across multiple modalities.
Its purpose is to serve as a **modular toolbox** for both inference and training.
We aim at building a library that stands the test of time and therefore take API design very seriously.
In a nutshell, Diffusers is built to be a natural extension of PyTorch. Therefore, most of our design choices are based on [PyTorch's Design Principles](https://pytorch.org/docs/stable/community/design.html#pytorch-design-philosophy). Let's go over the most important ones:
## Usability over Performance
- While Diffusers has many built-in performance-enhancing features (see [Memory and Speed](https://huggingface.co/docs/diffusers/optimization/fp16)), models are always loaded with the highest precision and lowest optimization. Therefore, by default diffusion pipelines are always instantiated on CPU with float32 precision if not otherwise defined by the user. This ensures usability across different platforms and accelerators and means that no complex installations are required to run the library.
- Diffusers aims to be a **light-weight** package and therefore has very few required dependencies, but many soft dependencies that can improve performance (such as `accelerate`, `safetensors`, `onnx`, etc...). We strive to keep the library as lightweight as possible so that it can be added without much concern as a dependency on other packages.
- Diffusers prefers simple, self-explainable code over condensed, magic code. This means that short-hand code syntaxes such as lambda functions, and advanced PyTorch operators are often not desired.
## Simple over easy
As PyTorch states, **explicit is better than implicit** and **simple is better than complex**. This design philosophy is reflected in multiple parts of the library:
- We follow PyTorch's API with methods like [`DiffusionPipeline.to`](https://huggingface.co/docs/diffusers/main/en/api/diffusion_pipeline#diffusers.DiffusionPipeline.to) to let the user handle device management.
- Raising concise error messages is preferred to silently correct erroneous input. Diffusers aims at teaching the user, rather than making the library as easy to use as possible.
- Complex model vs. scheduler logic is exposed instead of magically handled inside. Schedulers/Samplers are separated from diffusion models with minimal dependencies on each other. This forces the user to write the unrolled denoising loop. However, the separation allows for easier debugging and gives the user more control over adapting the denoising process or switching out diffusion models or schedulers.
- Separately trained components of the diffusion pipeline, *e.g.* the text encoder, the UNet, and the variational autoencoder, each has their own model class. This forces the user to handle the interaction between the different model components, and the serialization format separates the model components into different files. However, this allows for easier debugging and customization. DreamBooth or Textual Inversion training
is very simple thanks to Diffusers' ability to separate single components of the diffusion pipeline.
## Tweakable, contributor-friendly over abstraction
For large parts of the library, Diffusers adopts an important design principle of the [Transformers library](https://github.com/huggingface/transformers), which is to prefer copy-pasted code over hasty abstractions. This design principle is very opinionated and stands in stark contrast to popular design principles such as [Don't repeat yourself (DRY)](https://en.wikipedia.org/wiki/Don%27t_repeat_yourself).
In short, just like Transformers does for modeling files, Diffusers prefers to keep an extremely low level of abstraction and very self-contained code for pipelines and schedulers.
Functions, long code blocks, and even classes can be copied across multiple files which at first can look like a bad, sloppy design choice that makes the library unmaintainable.
**However**, this design has proven to be extremely successful for Transformers and makes a lot of sense for community-driven, open-source machine learning libraries because:
- Machine Learning is an extremely fast-moving field in which paradigms, model architectures, and algorithms are changing rapidly, which therefore makes it very difficult to define long-lasting code abstractions.
- Machine Learning practitioners like to be able to quickly tweak existing code for ideation and research and therefore prefer self-contained code over one that contains many abstractions.
- Open-source libraries rely on community contributions and therefore must build a library that is easy to contribute to. The more abstract the code, the more dependencies, the harder to read, and the harder to contribute to. Contributors simply stop contributing to very abstract libraries out of fear of breaking vital functionality. If contributing to a library cannot break other fundamental code, not only is it more inviting for potential new contributors, but it is also easier to review and contribute to multiple parts in parallel.
At Hugging Face, we call this design the **single-file policy** which means that almost all of the code of a certain class should be written in a single, self-contained file. To read more about the philosophy, you can have a look
at [this blog post](https://huggingface.co/blog/transformers-design-philosophy).
In Diffusers, we follow this philosophy for both pipelines and schedulers, but only partly for diffusion models. The reason we don't follow this design fully for diffusion models is because almost all diffusion pipelines, such
as [DDPM](https://huggingface.co/docs/diffusers/api/pipelines/ddpm), [Stable Diffusion](https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion/overview#stable-diffusion-pipelines), [unCLIP (DALL·E 2)](https://huggingface.co/docs/diffusers/api/pipelines/unclip) and [Imagen](https://imagen.research.google/) all rely on the same diffusion model, the [UNet](https://huggingface.co/docs/diffusers/api/models/unet2d-cond).
Great, now you should have generally understood why 🧨 Diffusers is designed the way it is 🤗.
We try to apply these design principles consistently across the library. Nevertheless, there are some minor exceptions to the philosophy or some unlucky design choices. If you have feedback regarding the design, we would ❤️ to hear it [directly on GitHub](https://github.com/huggingface/diffusers/issues/new?assignees=&labels=&template=feedback.md&title=).
## Design Philosophy in Details
Now, let's look a bit into the nitty-gritty details of the design philosophy. Diffusers essentially consists of three major classes: [pipelines](https://github.com/huggingface/diffusers/tree/main/src/diffusers/pipelines), [models](https://github.com/huggingface/diffusers/tree/main/src/diffusers/models), and [schedulers](https://github.com/huggingface/diffusers/tree/main/src/diffusers/schedulers).
Let's walk through more detailed design decisions for each class.
### Pipelines
Pipelines are designed to be easy to use (therefore do not follow [*Simple over easy*](#simple-over-easy) 100%), are not feature complete, and should loosely be seen as examples of how to use [models](#models) and [schedulers](#schedulers) for inference.
The following design principles are followed:
- Pipelines follow the single-file policy. All pipelines can be found in individual directories under src/diffusers/pipelines. One pipeline folder corresponds to one diffusion paper/project/release. Multiple pipeline files can be gathered in one pipeline folder, as it’s done for [`src/diffusers/pipelines/stable-diffusion`](https://github.com/huggingface/diffusers/tree/main/src/diffusers/pipelines/stable_diffusion). If pipelines share similar functionality, one can make use of the [#Copied from mechanism](https://github.com/huggingface/diffusers/blob/125d783076e5bd9785beb05367a2d2566843a271/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_img2img.py#L251).
- Pipelines all inherit from [`DiffusionPipeline`].
- Every pipeline consists of different model and scheduler components, that are documented in the [`model_index.json` file](https://huggingface.co/runwayml/stable-diffusion-v1-5/blob/main/model_index.json), are accessible under the same name as attributes of the pipeline and can be shared between pipelines with [`DiffusionPipeline.components`](https://huggingface.co/docs/diffusers/main/en/api/diffusion_pipeline#diffusers.DiffusionPipeline.components) function.
- Every pipeline should be loadable via the [`DiffusionPipeline.from_pretrained`](https://huggingface.co/docs/diffusers/main/en/api/diffusion_pipeline#diffusers.DiffusionPipeline.from_pretrained) function.
- Pipelines should be used **only** for inference.
- Pipelines should be very readable, self-explanatory, and easy to tweak.
- Pipelines should be designed to build on top of each other and be easy to integrate into higher-level APIs.
- Pipelines are **not** intended to be feature-complete user interfaces. For future complete user interfaces one should rather have a look at [InvokeAI](https://github.com/invoke-ai/InvokeAI), [Diffuzers](https://github.com/abhishekkrthakur/diffuzers), and [lama-cleaner](https://github.com/Sanster/lama-cleaner).
- Every pipeline should have one and only one way to run it via a `__call__` method. The naming of the `__call__` arguments should be shared across all pipelines.
- Pipelines should be named after the task they are intended to solve.
- In almost all cases, novel diffusion pipelines shall be implemented in a new pipeline folder/file.
### Models
Models are designed as configurable toolboxes that are natural extensions of [PyTorch's Module class](https://pytorch.org/docs/stable/generated/torch.nn.Module.html). They only partly follow the **single-file policy**.
The following design principles are followed:
- Models correspond to **a type of model architecture**. *E.g.* the [`UNet2DConditionModel`] class is used for all UNet variations that expect 2D image inputs and are conditioned on some context.
- All models can be found in [`src/diffusers/models`](https://github.com/huggingface/diffusers/tree/main/src/diffusers/models) and every model architecture shall be defined in its file, e.g. [`unet_2d_condition.py`](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/unet_2d_condition.py), [`transformer_2d.py`](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/transformer_2d.py), etc...
- Models **do not** follow the single-file policy and should make use of smaller model building blocks, such as [`attention.py`](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention.py), [`resnet.py`](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/resnet.py), [`embeddings.py`](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/embeddings.py), etc... **Note**: This is in stark contrast to Transformers' modeling files and shows that models do not really follow the single-file policy.
- Models intend to expose complexity, just like PyTorch's `Module` class, and give clear error messages.
- Models all inherit from `ModelMixin` and `ConfigMixin`.
- Models can be optimized for performance when it doesn’t demand major code changes, keep backward compatibility, and give significant memory or compute gain.
- Models should by default have the highest precision and lowest performance setting.
- To integrate new model checkpoints whose general architecture can be classified as an architecture that already exists in Diffusers, the existing model architecture shall be adapted to make it work with the new checkpoint. One should only create a new file if the model architecture is fundamentally different.
- Models should be designed to be easily extendable to future changes. This can be achieved by limiting public function arguments, configuration arguments, and "foreseeing" future changes, *e.g.* it is usually better to add `string` "...type" arguments that can easily be extended to new future types instead of boolean `is_..._type` arguments. Only the minimum amount of changes shall be made to existing architectures to make a new model checkpoint work.
- The model design is a difficult trade-off between keeping code readable and concise and supporting many model checkpoints. For most parts of the modeling code, classes shall be adapted for new model checkpoints, while there are some exceptions where it is preferred to add new classes to make sure the code is kept concise and
readable long-term, such as [UNet blocks](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/unet_2d_blocks.py) and [Attention processors](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_processor.py).
### Schedulers
Schedulers are responsible to guide the denoising process for inference as well as to define a noise schedule for training. They are designed as individual classes with loadable configuration files and strongly follow the **single-file policy**.
The following design principles are followed:
- All schedulers are found in [`src/diffusers/schedulers`](https://github.com/huggingface/diffusers/tree/main/src/diffusers/schedulers).
- Schedulers are **not** allowed to import from large utils files and shall be kept very self-contained.
- One scheduler Python file corresponds to one scheduler algorithm (as might be defined in a paper).
- If schedulers share similar functionalities, we can make use of the `#Copied from` mechanism.
- Schedulers all inherit from `SchedulerMixin` and `ConfigMixin`.
- Schedulers can be easily swapped out with the [`ConfigMixin.from_config`](https://huggingface.co/docs/diffusers/main/en/api/configuration#diffusers.ConfigMixin.from_config) method as explained in detail [here](./docs/source/en/using-diffusers/schedulers.md).
- Every scheduler has to have a `set_num_inference_steps`, and a `step` function. `set_num_inference_steps(...)` has to be called before every denoising process, *i.e.* before `step(...)` is called.
- Every scheduler exposes the timesteps to be "looped over" via a `timesteps` attribute, which is an array of timesteps the model will be called upon.
- The `step(...)` function takes a predicted model output and the "current" sample (x_t) and returns the "previous", slightly more denoised sample (x_t-1).
- Given the complexity of diffusion schedulers, the `step` function does not expose all the complexity and can be a bit of a "black box".
- In almost all cases, novel schedulers shall be implemented in a new scheduling file.
diffusers-0.27.0/README.md 0 → 100755
View file @ e178cada
<!---
Copyright 2022 - 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.
-->
<p align="center">
<br>
<img src="https://raw.githubusercontent.com/huggingface/diffusers/main/docs/source/en/imgs/diffusers_library.jpg" width="400"/>
<br>
<p>
<p align="center">
<a href="https://github.com/huggingface/diffusers/blob/main/LICENSE">
<img alt="GitHub" src="https://img.shields.io/github/license/huggingface/datasets.svg?color=blue">
</a>
<a href="https://github.com/huggingface/diffusers/releases">
<img alt="GitHub release" src="https://img.shields.io/github/release/huggingface/diffusers.svg">
</a>
<a href="https://pepy.tech/project/diffusers">
<img alt="GitHub release" src="https://static.pepy.tech/badge/diffusers/month">
</a>
<a href="CODE_OF_CONDUCT.md">
<img alt="Contributor Covenant" src="https://img.shields.io/badge/Contributor%20Covenant-2.1-4baaaa.svg">
</a>
<a href="https://twitter.com/diffuserslib">
<img alt="X account" src="https://img.shields.io/twitter/url/https/twitter.com/diffuserslib.svg?style=social&label=Follow%20%40diffuserslib">
</a>
</p>
🤗 Diffusers is the go-to library for state-of-the-art pretrained diffusion models for generating images, audio, and even 3D structures of molecules. Whether you're looking for a simple inference solution or training your own diffusion models, 🤗 Diffusers is a modular toolbox that supports both. Our library is designed with a focus on [usability over performance](https://huggingface.co/docs/diffusers/conceptual/philosophy#usability-over-performance), [simple over easy](https://huggingface.co/docs/diffusers/conceptual/philosophy#simple-over-easy), and [customizability over abstractions](https://huggingface.co/docs/diffusers/conceptual/philosophy#tweakable-contributorfriendly-over-abstraction).
🤗 Diffusers offers three core components:
- State-of-the-art [diffusion pipelines](https://huggingface.co/docs/diffusers/api/pipelines/overview) that can be run in inference with just a few lines of code.
- Interchangeable noise [schedulers](https://huggingface.co/docs/diffusers/api/schedulers/overview) for different diffusion speeds and output quality.
- Pretrained [models](https://huggingface.co/docs/diffusers/api/models/overview) that can be used as building blocks, and combined with schedulers, for creating your own end-to-end diffusion systems.
## Installation
We recommend installing 🤗 Diffusers in a virtual environment from PyPI or Conda. For more details about installing [PyTorch](https://pytorch.org/get-started/locally/) and [Flax](https://flax.readthedocs.io/en/latest/#installation), please refer to their official documentation.
### PyTorch
With `pip` (official package):
```bash
pip install --upgrade diffusers[torch]
```
With `conda` (maintained by the community):
```sh
conda install -c conda-forge diffusers
```
### Flax
With `pip` (official package):
```bash
pip install --upgrade diffusers[flax]
```
### Apple Silicon (M1/M2) support
Please refer to the [How to use Stable Diffusion in Apple Silicon](https://huggingface.co/docs/diffusers/optimization/mps) guide.
## Quickstart
Generating outputs is super easy with 🤗 Diffusers. To generate an image from text, use the `from_pretrained` method to load any pretrained diffusion model (browse the [Hub](https://huggingface.co/models?library=diffusers&sort=downloads) for 19000+ checkpoints):
```python
from diffusers import DiffusionPipeline
import torch
pipeline = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16)
pipeline.to("cuda")
pipeline("An image of a squirrel in Picasso style").images[0]
```
You can also dig into the models and schedulers toolbox to build your own diffusion system:
```python
from diffusers import DDPMScheduler, UNet2DModel
from PIL import Image
import torch
scheduler = DDPMScheduler.from_pretrained("google/ddpm-cat-256")
model = UNet2DModel.from_pretrained("google/ddpm-cat-256").to("cuda")
scheduler.set_timesteps(50)
sample_size = model.config.sample_size
noise = torch.randn((1, 3, sample_size, sample_size), device="cuda")
input = noise
for t in scheduler.timesteps:
with torch.no_grad():
noisy_residual = model(input, t).sample
prev_noisy_sample = scheduler.step(noisy_residual, t, input).prev_sample
input = prev_noisy_sample
image = (input / 2 + 0.5).clamp(0, 1)
image = image.cpu().permute(0, 2, 3, 1).numpy()[0]
image = Image.fromarray((image * 255).round().astype("uint8"))
image
```
Check out the [Quickstart](https://huggingface.co/docs/diffusers/quicktour) to launch your diffusion journey today!
## How to navigate the documentation
| **Documentation** | **What can I learn?** |
|---------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| [Tutorial](https://huggingface.co/docs/diffusers/tutorials/tutorial_overview) | A basic crash course for learning how to use the library's most important features like using models and schedulers to build your own diffusion system, and training your own diffusion model. |
| [Loading](https://huggingface.co/docs/diffusers/using-diffusers/loading_overview) | Guides for how to load and configure all the components (pipelines, models, and schedulers) of the library, as well as how to use different schedulers. |
| [Pipelines for inference](https://huggingface.co/docs/diffusers/using-diffusers/pipeline_overview) | Guides for how to use pipelines for different inference tasks, batched generation, controlling generated outputs and randomness, and how to contribute a pipeline to the library. |
| [Optimization](https://huggingface.co/docs/diffusers/optimization/opt_overview) | Guides for how to optimize your diffusion model to run faster and consume less memory. |
| [Training](https://huggingface.co/docs/diffusers/training/overview) | Guides for how to train a diffusion model for different tasks with different training techniques. |
## Contribution
We ❤️ contributions from the open-source community!
If you want to contribute to this library, please check out our [Contribution guide](https://github.com/huggingface/diffusers/blob/main/CONTRIBUTING.md).
You can look out for [issues](https://github.com/huggingface/diffusers/issues) you'd like to tackle to contribute to the library.
- See [Good first issues](https://github.com/huggingface/diffusers/issues?q=is%3Aopen+is%3Aissue+label%3A%22good+first+issue%22) for general opportunities to contribute
- See [New model/pipeline](https://github.com/huggingface/diffusers/issues?q=is%3Aopen+is%3Aissue+label%3A%22New+pipeline%2Fmodel%22) to contribute exciting new diffusion models / diffusion pipelines
- See [New scheduler](https://github.com/huggingface/diffusers/issues?q=is%3Aopen+is%3Aissue+label%3A%22New+scheduler%22)
Also, say 👋 in our public Discord channel <a href="https://discord.gg/G7tWnz98XR"><img alt="Join us on Discord" src="https://img.shields.io/discord/823813159592001537?color=5865F2&logo=discord&logoColor=white"></a>. We discuss the hottest trends about diffusion models, help each other with contributions, personal projects or just hang out ☕.
## Popular Tasks & Pipelines
<table>
<tr>
<th>Task</th>
<th>Pipeline</th>
<th>🤗 Hub</th>
</tr>
<tr style="border-top: 2px solid black">
<td>Unconditional Image Generation</td>
<td><a href="https://huggingface.co/docs/diffusers/api/pipelines/ddpm"> DDPM </a></td>
<td><a href="https://huggingface.co/google/ddpm-ema-church-256"> google/ddpm-ema-church-256 </a></td>
</tr>
<tr style="border-top: 2px solid black">
<td>Text-to-Image</td>
<td><a href="https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion/text2img">Stable Diffusion Text-to-Image</a></td>
<td><a href="https://huggingface.co/runwayml/stable-diffusion-v1-5"> runwayml/stable-diffusion-v1-5 </a></td>
</tr>
<tr>
<td>Text-to-Image</td>
<td><a href="https://huggingface.co/docs/diffusers/api/pipelines/unclip">unCLIP</a></td>
<td><a href="https://huggingface.co/kakaobrain/karlo-v1-alpha"> kakaobrain/karlo-v1-alpha </a></td>
</tr>
<tr>
<td>Text-to-Image</td>
<td><a href="https://huggingface.co/docs/diffusers/api/pipelines/deepfloyd_if">DeepFloyd IF</a></td>
<td><a href="https://huggingface.co/DeepFloyd/IF-I-XL-v1.0"> DeepFloyd/IF-I-XL-v1.0 </a></td>
</tr>
<tr>
<td>Text-to-Image</td>
<td><a href="https://huggingface.co/docs/diffusers/api/pipelines/kandinsky">Kandinsky</a></td>
<td><a href="https://huggingface.co/kandinsky-community/kandinsky-2-2-decoder"> kandinsky-community/kandinsky-2-2-decoder </a></td>
</tr>
<tr style="border-top: 2px solid black">
<td>Text-guided Image-to-Image</td>
<td><a href="https://huggingface.co/docs/diffusers/api/pipelines/controlnet">ControlNet</a></td>
<td><a href="https://huggingface.co/lllyasviel/sd-controlnet-canny"> lllyasviel/sd-controlnet-canny </a></td>
</tr>
<tr>
<td>Text-guided Image-to-Image</td>
<td><a href="https://huggingface.co/docs/diffusers/api/pipelines/pix2pix">InstructPix2Pix</a></td>
<td><a href="https://huggingface.co/timbrooks/instruct-pix2pix"> timbrooks/instruct-pix2pix </a></td>
</tr>
<tr>
<td>Text-guided Image-to-Image</td>
<td><a href="https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion/img2img">Stable Diffusion Image-to-Image</a></td>
<td><a href="https://huggingface.co/runwayml/stable-diffusion-v1-5"> runwayml/stable-diffusion-v1-5 </a></td>
</tr>
<tr style="border-top: 2px solid black">
<td>Text-guided Image Inpainting</td>
<td><a href="https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion/inpaint">Stable Diffusion Inpainting</a></td>
<td><a href="https://huggingface.co/runwayml/stable-diffusion-inpainting"> runwayml/stable-diffusion-inpainting </a></td>
</tr>
<tr style="border-top: 2px solid black">
<td>Image Variation</td>
<td><a href="https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion/image_variation">Stable Diffusion Image Variation</a></td>
<td><a href="https://huggingface.co/lambdalabs/sd-image-variations-diffusers"> lambdalabs/sd-image-variations-diffusers </a></td>
</tr>
<tr style="border-top: 2px solid black">
<td>Super Resolution</td>
<td><a href="https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion/upscale">Stable Diffusion Upscale</a></td>
<td><a href="https://huggingface.co/stabilityai/stable-diffusion-x4-upscaler"> stabilityai/stable-diffusion-x4-upscaler </a></td>
</tr>
<tr>
<td>Super Resolution</td>
<td><a href="https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion/latent_upscale">Stable Diffusion Latent Upscale</a></td>
<td><a href="https://huggingface.co/stabilityai/sd-x2-latent-upscaler"> stabilityai/sd-x2-latent-upscaler </a></td>
</tr>
</table>
## Popular libraries using 🧨 Diffusers
- https://github.com/microsoft/TaskMatrix
- https://github.com/invoke-ai/InvokeAI
- https://github.com/apple/ml-stable-diffusion
- https://github.com/Sanster/lama-cleaner
- https://github.com/IDEA-Research/Grounded-Segment-Anything
- https://github.com/ashawkey/stable-dreamfusion
- https://github.com/deep-floyd/IF
- https://github.com/bentoml/BentoML
- https://github.com/bmaltais/kohya_ss
- +8000 other amazing GitHub repositories 💪
Thank you for using us ❤️.
## Credits
This library concretizes previous work by many different authors and would not have been possible without their great research and implementations. We'd like to thank, in particular, the following implementations which have helped us in our development and without which the API could not have been as polished today:
- @CompVis' latent diffusion models library, available [here](https://github.com/CompVis/latent-diffusion)
- @hojonathanho original DDPM implementation, available [here](https://github.com/hojonathanho/diffusion) as well as the extremely useful translation into PyTorch by @pesser, available [here](https://github.com/pesser/pytorch_diffusion)
- @ermongroup's DDIM implementation, available [here](https://github.com/ermongroup/ddim)
- @yang-song's Score-VE and Score-VP implementations, available [here](https://github.com/yang-song/score_sde_pytorch)
We also want to thank @heejkoo for the very helpful overview of papers, code and resources on diffusion models, available [here](https://github.com/heejkoo/Awesome-Diffusion-Models) as well as @crowsonkb and @rromb for useful discussions and insights.
## Citation
```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 Thomas Wolf},
title = {Diffusers: State-of-the-art diffusion models},
year = {2022},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://github.com/huggingface/diffusers}}
}
```
diffusers-0.27.0/_typos.toml 0 → 100755
View file @ e178cada
# Files for typos
# Instruction: https://github.com/marketplace/actions/typos-action#getting-started
[default.extend-identifiers]
[default.extend-words]
NIN="NIN" # NIN is used in scripts/convert_ncsnpp_original_checkpoint_to_diffusers.py
nd="np" # nd may be np (numpy)
parms="parms" # parms is used in scripts/convert_original_stable_diffusion_to_diffusers.py
[files]
extend-exclude = ["_typos.toml"]
diffusers-0.27.0/benchmarks/base_classes.py 0 → 100755
View file @ e178cada
import os
import sys
import torch
from diffusers import (
AutoPipelineForImage2Image,
AutoPipelineForInpainting,
AutoPipelineForText2Image,
ControlNetModel,
LCMScheduler,
StableDiffusionAdapterPipeline,
StableDiffusionControlNetPipeline,
StableDiffusionXLAdapterPipeline,
StableDiffusionXLControlNetPipeline,
T2IAdapter,
WuerstchenCombinedPipeline,
)
from diffusers.utils import load_image
sys.path.append(".")
from utils import ( # noqa: E402
BASE_PATH,
PROMPT,
BenchmarkInfo,
benchmark_fn,
bytes_to_giga_bytes,
flush,
generate_csv_dict,
write_to_csv,
)
RESOLUTION_MAPPING = {
"runwayml/stable-diffusion-v1-5": (512, 512),
"lllyasviel/sd-controlnet-canny": (512, 512),
"diffusers/controlnet-canny-sdxl-1.0": (1024, 1024),
"TencentARC/t2iadapter_canny_sd14v1": (512, 512),
"TencentARC/t2i-adapter-canny-sdxl-1.0": (1024, 1024),
"stabilityai/stable-diffusion-2-1": (768, 768),
"stabilityai/stable-diffusion-xl-base-1.0": (1024, 1024),
"stabilityai/stable-diffusion-xl-refiner-1.0": (1024, 1024),
"stabilityai/sdxl-turbo": (512, 512),
}
class BaseBenchmak:
pipeline_class = None
def __init__(self, args):
super().__init__()
def run_inference(self, args):
raise NotImplementedError
def benchmark(self, args):
raise NotImplementedError
def get_result_filepath(self, args):
pipeline_class_name = str(self.pipe.__class__.__name__)
name = (
args.ckpt.replace("/", "_")
+ "_"
+ pipeline_class_name
+ f"-bs@{args.batch_size}-steps@{args.num_inference_steps}-mco@{args.model_cpu_offload}-compile@{args.run_compile}.csv"
)
filepath = os.path.join(BASE_PATH, name)
return filepath
class TextToImageBenchmark(BaseBenchmak):
pipeline_class = AutoPipelineForText2Image
def __init__(self, args):
pipe = self.pipeline_class.from_pretrained(args.ckpt, torch_dtype=torch.float16)
pipe = pipe.to("cuda")
if args.run_compile:
if not isinstance(pipe, WuerstchenCombinedPipeline):
pipe.unet.to(memory_format=torch.channels_last)
print("Run torch compile")
pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
if hasattr(pipe, "movq") and getattr(pipe, "movq", None) is not None:
pipe.movq.to(memory_format=torch.channels_last)
pipe.movq = torch.compile(pipe.movq, mode="reduce-overhead", fullgraph=True)
else:
print("Run torch compile")
pipe.decoder = torch.compile(pipe.decoder, mode="reduce-overhead", fullgraph=True)
pipe.vqgan = torch.compile(pipe.vqgan, mode="reduce-overhead", fullgraph=True)
pipe.set_progress_bar_config(disable=True)
self.pipe = pipe
def run_inference(self, pipe, args):
_ = pipe(
prompt=PROMPT,
num_inference_steps=args.num_inference_steps,
num_images_per_prompt=args.batch_size,
)
def benchmark(self, args):
flush()
print(f"[INFO] {self.pipe.__class__.__name__}: Running benchmark with: {vars(args)}\n")
time = benchmark_fn(self.run_inference, self.pipe, args) # in seconds.
memory = bytes_to_giga_bytes(torch.cuda.max_memory_allocated()) # in GBs.
benchmark_info = BenchmarkInfo(time=time, memory=memory)
pipeline_class_name = str(self.pipe.__class__.__name__)
flush()
csv_dict = generate_csv_dict(
pipeline_cls=pipeline_class_name, ckpt=args.ckpt, args=args, benchmark_info=benchmark_info
)
filepath = self.get_result_filepath(args)
write_to_csv(filepath, csv_dict)
print(f"Logs written to: {filepath}")
flush()
class TurboTextToImageBenchmark(TextToImageBenchmark):
def __init__(self, args):
super().__init__(args)
def run_inference(self, pipe, args):
_ = pipe(
prompt=PROMPT,
num_inference_steps=args.num_inference_steps,
num_images_per_prompt=args.batch_size,
guidance_scale=0.0,
)
class LCMLoRATextToImageBenchmark(TextToImageBenchmark):
lora_id = "latent-consistency/lcm-lora-sdxl"
def __init__(self, args):
super().__init__(args)
self.pipe.load_lora_weights(self.lora_id)
self.pipe.fuse_lora()
self.pipe.unload_lora_weights()
self.pipe.scheduler = LCMScheduler.from_config(self.pipe.scheduler.config)
def get_result_filepath(self, args):
pipeline_class_name = str(self.pipe.__class__.__name__)
name = (
self.lora_id.replace("/", "_")
+ "_"
+ pipeline_class_name
+ f"-bs@{args.batch_size}-steps@{args.num_inference_steps}-mco@{args.model_cpu_offload}-compile@{args.run_compile}.csv"
)
filepath = os.path.join(BASE_PATH, name)
return filepath
def run_inference(self, pipe, args):
_ = pipe(
prompt=PROMPT,
num_inference_steps=args.num_inference_steps,
num_images_per_prompt=args.batch_size,
guidance_scale=1.0,
)
def benchmark(self, args):
flush()
print(f"[INFO] {self.pipe.__class__.__name__}: Running benchmark with: {vars(args)}\n")
time = benchmark_fn(self.run_inference, self.pipe, args) # in seconds.
memory = bytes_to_giga_bytes(torch.cuda.max_memory_allocated()) # in GBs.
benchmark_info = BenchmarkInfo(time=time, memory=memory)
pipeline_class_name = str(self.pipe.__class__.__name__)
flush()
csv_dict = generate_csv_dict(
pipeline_cls=pipeline_class_name, ckpt=self.lora_id, args=args, benchmark_info=benchmark_info
)
filepath = self.get_result_filepath(args)
write_to_csv(filepath, csv_dict)
print(f"Logs written to: {filepath}")
flush()
class ImageToImageBenchmark(TextToImageBenchmark):
pipeline_class = AutoPipelineForImage2Image
url = "https://huggingface.co/datasets/diffusers/docs-images/resolve/main/benchmarking/1665_Girl_with_a_Pearl_Earring.jpg"
image = load_image(url).convert("RGB")
def __init__(self, args):
super().__init__(args)
self.image = self.image.resize(RESOLUTION_MAPPING[args.ckpt])
def run_inference(self, pipe, args):
_ = pipe(
prompt=PROMPT,
image=self.image,
num_inference_steps=args.num_inference_steps,
num_images_per_prompt=args.batch_size,
)
class TurboImageToImageBenchmark(ImageToImageBenchmark):
def __init__(self, args):
super().__init__(args)
def run_inference(self, pipe, args):
_ = pipe(
prompt=PROMPT,
image=self.image,
num_inference_steps=args.num_inference_steps,
num_images_per_prompt=args.batch_size,
guidance_scale=0.0,
strength=0.5,
)
class InpaintingBenchmark(ImageToImageBenchmark):
pipeline_class = AutoPipelineForInpainting
mask_url = "https://huggingface.co/datasets/diffusers/docs-images/resolve/main/benchmarking/overture-creations-5sI6fQgYIuo_mask.png"
mask = load_image(mask_url).convert("RGB")
def __init__(self, args):
super().__init__(args)
self.image = self.image.resize(RESOLUTION_MAPPING[args.ckpt])
self.mask = self.mask.resize(RESOLUTION_MAPPING[args.ckpt])
def run_inference(self, pipe, args):
_ = pipe(
prompt=PROMPT,
image=self.image,
mask_image=self.mask,
num_inference_steps=args.num_inference_steps,
num_images_per_prompt=args.batch_size,
)
class IPAdapterTextToImageBenchmark(TextToImageBenchmark):
url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/load_neg_embed.png"
image = load_image(url)
def __init__(self, args):
pipe = self.pipeline_class.from_pretrained(args.ckpt, torch_dtype=torch.float16).to("cuda")
pipe.load_ip_adapter(
args.ip_adapter_id[0],
subfolder="models" if "sdxl" not in args.ip_adapter_id[1] else "sdxl_models",
weight_name=args.ip_adapter_id[1],
)
if args.run_compile:
pipe.unet.to(memory_format=torch.channels_last)
print("Run torch compile")
pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
pipe.set_progress_bar_config(disable=True)
self.pipe = pipe
def run_inference(self, pipe, args):
_ = pipe(
prompt=PROMPT,
ip_adapter_image=self.image,
num_inference_steps=args.num_inference_steps,
num_images_per_prompt=args.batch_size,
)
class ControlNetBenchmark(TextToImageBenchmark):
pipeline_class = StableDiffusionControlNetPipeline
aux_network_class = ControlNetModel
root_ckpt = "runwayml/stable-diffusion-v1-5"
url = "https://huggingface.co/datasets/diffusers/docs-images/resolve/main/benchmarking/canny_image_condition.png"
image = load_image(url).convert("RGB")
def __init__(self, args):
aux_network = self.aux_network_class.from_pretrained(args.ckpt, torch_dtype=torch.float16)
pipe = self.pipeline_class.from_pretrained(self.root_ckpt, controlnet=aux_network, torch_dtype=torch.float16)
pipe = pipe.to("cuda")
pipe.set_progress_bar_config(disable=True)
self.pipe = pipe
if args.run_compile:
pipe.unet.to(memory_format=torch.channels_last)
pipe.controlnet.to(memory_format=torch.channels_last)
print("Run torch compile")
pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
pipe.controlnet = torch.compile(pipe.controlnet, mode="reduce-overhead", fullgraph=True)
self.image = self.image.resize(RESOLUTION_MAPPING[args.ckpt])
def run_inference(self, pipe, args):
_ = pipe(
prompt=PROMPT,
image=self.image,
num_inference_steps=args.num_inference_steps,
num_images_per_prompt=args.batch_size,
)
class ControlNetSDXLBenchmark(ControlNetBenchmark):
pipeline_class = StableDiffusionXLControlNetPipeline
root_ckpt = "stabilityai/stable-diffusion-xl-base-1.0"
def __init__(self, args):
super().__init__(args)
class T2IAdapterBenchmark(ControlNetBenchmark):
pipeline_class = StableDiffusionAdapterPipeline
aux_network_class = T2IAdapter
root_ckpt = "CompVis/stable-diffusion-v1-4"
url = "https://huggingface.co/datasets/diffusers/docs-images/resolve/main/benchmarking/canny_for_adapter.png"
image = load_image(url).convert("L")
def __init__(self, args):
aux_network = self.aux_network_class.from_pretrained(args.ckpt, torch_dtype=torch.float16)
pipe = self.pipeline_class.from_pretrained(self.root_ckpt, adapter=aux_network, torch_dtype=torch.float16)
pipe = pipe.to("cuda")
pipe.set_progress_bar_config(disable=True)
self.pipe = pipe
if args.run_compile:
pipe.unet.to(memory_format=torch.channels_last)
pipe.adapter.to(memory_format=torch.channels_last)
print("Run torch compile")
pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
pipe.adapter = torch.compile(pipe.adapter, mode="reduce-overhead", fullgraph=True)
self.image = self.image.resize(RESOLUTION_MAPPING[args.ckpt])
class T2IAdapterSDXLBenchmark(T2IAdapterBenchmark):
pipeline_class = StableDiffusionXLAdapterPipeline
root_ckpt = "stabilityai/stable-diffusion-xl-base-1.0"
url = "https://huggingface.co/datasets/diffusers/docs-images/resolve/main/benchmarking/canny_for_adapter_sdxl.png"
image = load_image(url)
def __init__(self, args):
super().__init__(args)
diffusers-0.27.0/benchmarks/benchmark_controlnet.py 0 → 100755
View file @ e178cada
import argparse
import sys
sys.path.append(".")
from base_classes import ControlNetBenchmark, ControlNetSDXLBenchmark # noqa: E402
if __name__ == "__main__":
parser = argparse.ArgumentParser()
parser.add_argument(
"--ckpt",
type=str,
default="lllyasviel/sd-controlnet-canny",
choices=["lllyasviel/sd-controlnet-canny", "diffusers/controlnet-canny-sdxl-1.0"],
)
parser.add_argument("--batch_size", type=int, default=1)
parser.add_argument("--num_inference_steps", type=int, default=50)
parser.add_argument("--model_cpu_offload", action="store_true")
parser.add_argument("--run_compile", action="store_true")
args = parser.parse_args()
benchmark_pipe = (
ControlNetBenchmark(args) if args.ckpt == "lllyasviel/sd-controlnet-canny" else ControlNetSDXLBenchmark(args)
)
benchmark_pipe.benchmark(args)
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment