Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
34 commits
Select commit Hold shift + click to select a range
326f326
Replace deprecated command with environment file (#3409)
jongwooo May 16, 2023
d2285f5
fix warning message pipeline loading (#3446)
patrickvonplaten May 16, 2023
9d44e2f
add stable diffusion tensorrt img2img pipeline (#3419)
asfiyab-nvidia May 16, 2023
886575e
Refactor controlnet and add img2img and inpaint (#3386)
patrickvonplaten May 16, 2023
17f9aed
[Scheduler] DPM-Solver (++) Inverse Scheduler (#3335)
clarencechen May 16, 2023
754fac8
[Docs] Fix incomplete docstring for resnet.py (#3438)
Laurent2916 May 16, 2023
92ea5ba
fix tiled vae blend extent range (#3384)
superlabs-dev May 16, 2023
0392ece
Small update to "Next steps" section (#3443)
pcuenca May 16, 2023
6070b32
Allow arbitrary aspect ratio in IFSuperResolutionPipeline (#3298)
devxpy May 17, 2023
c09c4f3
Adding 'strength' parameter to StableDiffusionInpaintingPipeline (#3…
rupertmenneer May 17, 2023
415c616
[WIP] Bugfix - Pipeline.from_pretrained is broken when the pipeline i…
vimarshc May 17, 2023
15f1bab
Fix gradient checkpointing bugs in freezing part of models (requires_…
IrisRainbowNeko May 17, 2023
3ebd2d1
Make dreambooth lora more robust to orig unet (#3462)
patrickvonplaten May 17, 2023
bd78f63
Reduce peak VRAM by releasing large attention tensors (as soon as the…
cmdr2 May 17, 2023
2faf91d
Add min snr to text2img lora training script (#3459)
wfng92 May 17, 2023
88295f9
Add inpaint lora scale support (#3460)
Glaceon-Hyy May 17, 2023
2858d7e
[From ckpt] Fix from_ckpt (#3466)
patrickvonplaten May 17, 2023
c9f939b
Update full dreambooth script to work with IF (#3425)
williamberman May 17, 2023
7200985
Add IF dreambooth docs (#3470)
williamberman May 17, 2023
49b7ccf
parameterize pass single args through tuple (#3477)
williamberman May 18, 2023
8917769
attend and excite tests disable determinism on the class level (#3478)
williamberman May 18, 2023
8d646f2
dreambooth docs torch.compile note (#3471)
williamberman May 19, 2023
e343443
add: if entry in the dreambooth training docs. (#3472)
sayakpaul May 19, 2023
00c76f6
[docs] Textual inversion inference (#3473)
stevhliu May 19, 2023
e589bdb
[docs] Distributed inference (#3376)
stevhliu May 19, 2023
85eff63
[{Up,Down}sample1d] explicit view kernel size as number elements in f…
williamberman May 19, 2023
f7b4f51
mps & onnx tests rework (#3449)
pcuenca May 20, 2023
4bbc51d
[Attention processor] Better warning message when shifting to `AttnPr…
sayakpaul May 21, 2023
49ad61c
[Docs] add note on local directory path. (#3397)
sayakpaul May 21, 2023
37e1895
Merge branch 'main2' into consistency_unet
May 22, 2023
7c1e81f
Add Unet blocks for consistency models
May 22, 2023
3a151bd
Add conversion script for Unet
May 22, 2023
b6c5e15
Fix bug in new unet blocks
May 22, 2023
4e93f09
Fix attention weight loading
May 23, 2023
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions .github/actions/setup-miniconda/action.yml
Original file line number Diff line number Diff line change
Expand Up @@ -27,7 +27,7 @@ runs:
- name: Get date
id: get-date
shell: bash
run: echo "::set-output name=today::$(/bin/date -u '+%Y%m%d')d"
run: echo "today=$(/bin/date -u '+%Y%m%d')d" >> $GITHUB_OUTPUT
- name: Setup miniconda cache
id: miniconda-cache
uses: actions/cache@v2
Expand Down Expand Up @@ -143,4 +143,4 @@ runs:
echo "There is ${AVAIL}KB free space left in $MOUNT, continue"
fi
fi
done
done
66 changes: 0 additions & 66 deletions .github/workflows/pr_tests.yml
Original file line number Diff line number Diff line change
Expand Up @@ -36,11 +36,6 @@ jobs:
runner: docker-cpu
image: diffusers/diffusers-flax-cpu
report: flax_cpu
- name: Fast ONNXRuntime CPU tests
framework: onnxruntime
runner: docker-cpu
image: diffusers/diffusers-onnxruntime-cpu
report: onnx_cpu
- name: PyTorch Example CPU tests
framework: pytorch_examples
runner: docker-cpu
Expand Down Expand Up @@ -98,14 +93,6 @@ jobs:
--make-reports=tests_${{ matrix.config.report }} \
tests

- name: Run fast ONNXRuntime CPU tests
if: ${{ matrix.config.framework == 'onnxruntime' }}
run: |
python -m pytest -n 2 --max-worker-restart=0 --dist=loadfile \
-s -v -k "Onnx" \
--make-reports=tests_${{ matrix.config.report }} \
tests/

- name: Run example PyTorch CPU tests
if: ${{ matrix.config.framework == 'pytorch_examples' }}
run: |
Expand All @@ -123,56 +110,3 @@ jobs:
with:
name: pr_${{ matrix.config.report }}_test_reports
path: reports

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
${CONDA_RUN} python -m pip install -e .[quality,test]
${CONDA_RUN} python -m pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cpu
${CONDA_RUN} python -m pip install accelerate --upgrade
${CONDA_RUN} python -m 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
55 changes: 1 addition & 54 deletions .github/workflows/push_tests_fast.yml
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
name: Slow tests on main
name: Fast tests on main

on:
push:
Expand Down Expand Up @@ -108,56 +108,3 @@ jobs:
with:
name: pr_${{ matrix.config.report }}_test_reports
path: reports

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
${CONDA_RUN} python -m pip install -e .[quality,test]
${CONDA_RUN} python -m pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cpu
${CONDA_RUN} python -m pip install accelerate --upgrade
${CONDA_RUN} python -m 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
68 changes: 68 additions & 0 deletions .github/workflows/push_tests_mps.yml
Original file line number Diff line number Diff line change
@@ -0,0 +1,68 @@
name: Fast mps tests on main

on:
push:
branches:
- main

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_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
${CONDA_RUN} python -m pip install -e .[quality,test]
${CONDA_RUN} python -m pip install torch torchvision torchaudio
${CONDA_RUN} python -m pip install accelerate --upgrade
${CONDA_RUN} python -m 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
10 changes: 8 additions & 2 deletions docs/source/en/_toctree.yml
Original file line number Diff line number Diff line change
Expand Up @@ -44,6 +44,10 @@
title: Text-guided image-inpainting
- local: using-diffusers/depth2img
title: Text-guided depth-to-image
- local: using-diffusers/textual_inversion_inference
title: Textual inversion
- local: training/distributed_inference
title: Distributed inference with multiple GPUs
- local: using-diffusers/reusing_seeds
title: Improve image quality with deterministic generation
- local: using-diffusers/reproducibility
Expand Down Expand Up @@ -148,6 +152,8 @@
title: Audio Diffusion
- local: api/pipelines/audioldm
title: AudioLDM
- local: api/pipelines/controlnet
title: ControlNet
- local: api/pipelines/cycle_diffusion
title: Cycle Diffusion
- local: api/pipelines/dance_diffusion
Expand Down Expand Up @@ -203,8 +209,6 @@
title: Self-Attention Guidance
- local: api/pipelines/stable_diffusion/panorama
title: MultiDiffusion Panorama
- local: api/pipelines/stable_diffusion/controlnet
title: Text-to-Image Generation with ControlNet Conditioning
- local: api/pipelines/stable_diffusion/model_editing
title: Text-to-Image Model Editing
- local: api/pipelines/stable_diffusion/diffedit
Expand Down Expand Up @@ -252,6 +256,8 @@
title: Euler scheduler
- local: api/schedulers/heun
title: Heun Scheduler
- local: api/schedulers/multistep_dpm_solver_inverse
title: Inverse Multistep DPM-Solver
- local: api/schedulers/ipndm
title: IPNDM
- local: api/schedulers/lms_discrete
Expand Down
Loading