Skip to content

huggingface org 업데이트 #3

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 367 commits into from
Mar 23, 2023
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
367 commits
Select commit Hold shift + click to select a range
9d0d070
EMA: fix `state_dict()` and `load_state_dict()` & add `cur_decay_valu…
chenguolin Feb 8, 2023
1ed6b77
[Examples] Test all examples on CPU (#2289)
patrickvonplaten Feb 8, 2023
648090e
fix pix2pix docs (#2290)
patrickvonplaten Feb 8, 2023
fd5c3c0
misc fixes (#2282)
williamberman Feb 8, 2023
f3c8483
Run same number of DDPM steps in inference as training (#2263)
bencevans Feb 9, 2023
62a15ce
make style
patrickvonplaten Feb 9, 2023
1be7df0
[LoRA] Freezing the model weights (#2245)
erkams Feb 9, 2023
e83b436
make style
patrickvonplaten Feb 10, 2023
716286f
Fast CPU tests should also run on main (#2313)
patrickvonplaten Feb 10, 2023
96c2279
Correct fast tests (#2314)
patrickvonplaten Feb 10, 2023
beb59ab
remove ddpm test_full_inference (#2291)
williamberman Feb 10, 2023
1e7f965
convert ckpt script docstring fixes (#2293)
williamberman Feb 10, 2023
a688c7b
[Community Pipeline] UnCLIP Text Interpolation Pipeline (#2257)
Abhinay1997 Feb 13, 2023
120844a
[Tests] Refactor push tests (#2329)
patrickvonplaten Feb 13, 2023
f2eae16
Add ethical guidelines (#2330)
giadilli Feb 13, 2023
5d4f59e
Fix running LoRA with xformers (#2286)
bddppq Feb 13, 2023
0850b88
Fix typo in load_pipeline_from_original_stable_diffusion_ckpt() metho…
p1atdev Feb 13, 2023
98c1a8e
[Docs] Fix ethical guidelines docs (#2333)
patrickvonplaten Feb 13, 2023
1f5f17c
[Versatile Diffusion] Fix tests (#2336)
patrickvonplaten Feb 13, 2023
bc0cee9
[Latent Upscaling] Remove unused noise (#2298)
patrickvonplaten Feb 13, 2023
6cbd7b8
[Tests] Remove unnecessary tests (#2337)
patrickvonplaten Feb 13, 2023
f190714
karlo image variation use kakaobrain upload (#2338)
williamberman Feb 13, 2023
6782b70
github issue forum link (#2335)
williamberman Feb 13, 2023
9e8ee2a
dreambooth checkpointing tests and docs (#2339)
williamberman Feb 13, 2023
e55687e
unet check length inputs (#2327)
williamberman Feb 14, 2023
62b3c9e
unCLIP variant (#2297)
williamberman Feb 14, 2023
0db19da
Log Unconditional Image Generation Samples to W&B (#2287)
bencevans Feb 14, 2023
91925fb
Fix callback type hints - no optional function argument (#2357)
patrickvonplaten Feb 14, 2023
666d80a
fix some tests
patrickvonplaten Feb 15, 2023
51b61b6
[Docs] initial docs about KarrasDiffusionSchedulers (#2349)
kashif Feb 15, 2023
2a49fac
KarrasDiffusionSchedulers type note (#2365)
williamberman Feb 15, 2023
4c52982
[Tests] Add MPS skip decorator (#2362)
patrickvonplaten Feb 15, 2023
c613288
Funky spacing issue (#2368)
meg-huggingface Feb 16, 2023
a3ae466
schedulers add glide noising schedule (#2347)
williamberman Feb 16, 2023
296b01e
add total number checkpoints to training scripts (#2367)
williamberman Feb 16, 2023
46def72
checkpointing_steps_total_limit->checkpoints_total_limit (#2374)
williamberman Feb 16, 2023
e3ddbe2
Fix 3-way merging with the checkpoint_merger community pipeline (#2355)
damian0815 Feb 16, 2023
e5810e6
[Variant] Add "variant" as input kwarg so to have better UX when down…
patrickvonplaten Feb 16, 2023
fd3d550
[Pipelines] Adds pix2pix zero (#2334)
sayakpaul Feb 16, 2023
fa35750
Add Self-Attention-Guided (SAG) Stable Diffusion pipeline (#2193)
SusungHong Feb 16, 2023
de9ce9e
[SchedulingPNDM ] reset cur_model_output after each call (#2376)
patil-suraj Feb 16, 2023
b214bb2
train_text_to_image EMAModel saving (#2341)
williamberman Feb 16, 2023
6eaebe8
[Utils] Adds `store()` and `restore()` methods to EMAModel (#2302)
sayakpaul Feb 16, 2023
2777264
`enable_model_cpu_offload` (#2285)
pcuenca Feb 16, 2023
aaaec06
add the UniPC scheduler (#2373)
wl-zhao Feb 16, 2023
d32e939
Replace torch.concat calls by torch.cat (#2378)
fxmarty Feb 16, 2023
90a624f
improve tests
patrickvonplaten Feb 16, 2023
a60f555
Make diffusers importable with transformers < 4.26 (#2380)
pcuenca Feb 16, 2023
ca980fd
[Examples] Make sure EMA works with any device (#2382)
patrickvonplaten Feb 16, 2023
f243282
[Dummy imports] Add missing if else statements for SD] (#2381)
patrickvonplaten Feb 16, 2023
2e7a286
Attend and excite 2 (#2369)
yiyixuxu Feb 16, 2023
857c04c
[Pix2Pix0] Add utility function to get edit vector (#2383)
patrickvonplaten Feb 16, 2023
8e1cae5
Revert "[Pix2Pix0] Add utility function to get edit vector" (#2384)
patrickvonplaten Feb 16, 2023
568b73f
Fix stable diffusion onnx pipeline error when batch_size > 1 (#2366)
tianleiwu Feb 16, 2023
d45bb93
[Docs] Fix UniPC docs (#2386)
wl-zhao Feb 17, 2023
abd5dcb
[Pix2Pix Zero] Fix slow tests (#2391)
sayakpaul Feb 17, 2023
2e0d489
[Pix2Pix] Add utility function (#2385)
patrickvonplaten Feb 17, 2023
351b37e
Fix UniPC tests and remove some test warnings (#2396)
pcuenca Feb 17, 2023
c5fa13a
[Pipelines] Add a section on generating captions and embeddings for P…
sayakpaul Feb 17, 2023
0c0bb08
Torch2.0 scaled_dot_product_attention processor (#2303)
patil-suraj Feb 17, 2023
867a217
add: inversion to pix2pix zero docs. (#2398)
sayakpaul Feb 17, 2023
350a510
fix docs
patil-suraj Feb 17, 2023
291ecda
quikc doc fix
patil-suraj Feb 17, 2023
01a8080
Add semantic guidance pipeline (#2223)
manuelbrack Feb 17, 2023
14b9507
Add ddim inversion pix2pix (#2397)
patrickvonplaten Feb 17, 2023
38de964
add MultiDiffusionPanorama pipeline (#2393)
omerbt Feb 17, 2023
b6b73d9
Fixing typos in documentation (#2389)
anagri Feb 17, 2023
d2e2c61
controlling generation docs (#2388)
williamberman Feb 17, 2023
0866e85
apply_forward_hook simply returns if no accelerate (#2387)
daquexian Feb 17, 2023
024c437
Release: v0.13.0
patrickvonplaten Feb 17, 2023
5979089
Revert "Release: v0.13.0" (#2405)
williamberman Feb 17, 2023
07547df
controlling generation doc nits (#2406)
williamberman Feb 17, 2023
780b3a4
Fix typo in AttnProcessor2_0 symbol (#2404)
pcuenca Feb 17, 2023
770d3b3
add index page (#2401)
yiyixuxu Feb 17, 2023
bfdffbe
add xformers 0.0.16 warning message (#2345)
williamberman Feb 17, 2023
b2c1e0d
Release: v0.13.0
patrickvonplaten Feb 17, 2023
3231712
Post release 0.14
patrickvonplaten Feb 17, 2023
55de509
make style
patrickvonplaten Feb 17, 2023
1e5eaca
stable unclip integration tests turn on memory saving (#2408)
williamberman Feb 19, 2023
c85efbb
Fix deprecation warning (#2426)
patrickvonplaten Feb 19, 2023
5f65ef4
remove author names. (#2428)
sayakpaul Feb 20, 2023
45572c2
fix the get_indices function (#2418)
yiyixuxu Feb 20, 2023
4135558
Update pipeline_utils.py (#2415)
haofanwang Feb 20, 2023
d7cfa0b
make style
patrickvonplaten Feb 20, 2023
2ab4fcd
fix transformers naming (#2430)
patrickvonplaten Feb 20, 2023
8f1fe75
[Docs] Add a note on SDEdit (#2433)
sayakpaul Feb 20, 2023
f3fac68
small bugfix at StableDiffusionDepth2ImgPipeline call to check_inputs…
mikegarts Feb 20, 2023
17ecf72
add demo (#2436)
yiyixuxu Feb 20, 2023
39a3c77
fix: code snippet of instruct pix2pix from the docs. (#2446)
sayakpaul Feb 21, 2023
589faa8
Update train_text_to_image_lora.py (#2464)
haofanwang Feb 23, 2023
54bc882
`mps` test fixes (#2470)
pcuenca Feb 24, 2023
5de4347
Fix test `train_unconditional` (#2481)
pcuenca Feb 24, 2023
6960e72
add MultiDiffusion to controlling generation (#2490)
omerbt Feb 25, 2023
7f43f65
image_noiser -> image_normalizer comment (#2496)
williamberman Feb 27, 2023
0e975e5
[Safetensors] Make sure metadata is saved (#2506)
patrickvonplaten Feb 27, 2023
48a2eb3
Add 4090 benchmark (PyTorch 2.0) (#2503)
pcuenca Feb 27, 2023
1c36a12
[Docs] Improve safetensors (#2508)
patrickvonplaten Feb 27, 2023
a0549fe
Disable ONNX tests (#2509)
patrickvonplaten Feb 27, 2023
824cb53
attend and excite batch test causing timeouts (#2498)
williamberman Feb 27, 2023
42beaf1
move pipeline based test skips out of pipeline mixin (#2486)
williamberman Feb 27, 2023
1586186
pix2pix tests no write to fs (#2497)
williamberman Feb 27, 2023
e3a2c7f
[Docs] Include more information in the "controlling generation" doc (…
sayakpaul Feb 28, 2023
477aaa9
Use "hub" directory for cache instead of "diffusers" (#2005)
pcuenca Feb 28, 2023
a75ac3f
Sequential cpu offload: require accelerate 0.14.0 (#2517)
pcuenca Feb 28, 2023
856dad5
is_safetensors_compatible refactor (#2499)
williamberman Mar 1, 2023
eadf0e2
[Copyright] 2023 (#2524)
patrickvonplaten Mar 1, 2023
e4a9fb3
Bring Flax attention naming in sync with PyTorch (#2511)
pcuenca Mar 1, 2023
664b4de
[Tests] Fix slow tests (#2526)
patrickvonplaten Mar 1, 2023
1a6fa69
PipelineTesterMixin parameter configuration refactor (#2502)
williamberman Mar 1, 2023
8dfff7c
Add a ControlNet model & pipeline (#2407)
takuma104 Mar 2, 2023
8014848
8k Stable Diffusion with tiled VAE (#1441)
kig Mar 2, 2023
d9b9533
Textual inv make save log both steps (#2178)
isamu-isozaki Mar 2, 2023
8f21a9f
Fix convert SD to diffusers error (#1979) (#2529)
fkunn1326 Mar 2, 2023
1021929
Small fixes for controlnet (#2542)
patrickvonplaten Mar 3, 2023
4f0141a
Fix ONNX checkpoint loading (#2544)
anton-l Mar 3, 2023
5b6582c
[Model offload] Add nice warning (#2543)
patrickvonplaten Mar 3, 2023
f20c8f5
Release: v0.14.0
patrickvonplaten Mar 3, 2023
1f4deb6
Adding support for `safetensors` and LoRa. (#2448)
Narsil Mar 3, 2023
3d2648d
[Post release] Push post release (#2546)
patrickvonplaten Mar 3, 2023
7f0f7e1
Correct section docs (#2540)
patrickvonplaten Mar 3, 2023
5e5ce13
adds `xformers` support to `train_unconditional.py` (#2520)
vvvm23 Mar 3, 2023
e75eae3
Bug Fix: Remove explicit message argument in deprecate (#2421)
alvanli Mar 3, 2023
2f48957
Update pipeline_stable_diffusion_inpaint_legacy.py resize to integer …
Laveraaa Mar 3, 2023
a72a057
move test num_images_per_prompt to pipeline mixin (#2488)
williamberman Mar 3, 2023
fa6d52d
Training tutorial (#2473)
stevhliu Mar 3, 2023
2ea1da8
Fix regression introduced in #2448 (#2551)
Narsil Mar 4, 2023
e4c356d
Fix for InstructPix2PixPipeline to allow for prompt embeds to be pass…
DN6 Mar 5, 2023
2b4f849
[PipelineTesterMixin] Handle non-image outputs for attn slicing test …
sanchit-gandhi Mar 5, 2023
2e3541d
[Community Pipeline] Unclip Image Interpolation (#2400)
Abhinay1997 Mar 6, 2023
b36cbd4
Fix: controlnet docs format (#2559)
vicoooo26 Mar 6, 2023
f727863
ema step, don't empty cuda cache (#2563)
williamberman Mar 6, 2023
5f826a3
Add custom vae (diffusers type) to onnx converter (#2325)
ForserX Mar 6, 2023
f38e362
make style
patrickvonplaten Mar 6, 2023
9920c33
add OnnxStableDiffusionUpscalePipeline pipeline (#2158)
ssube Mar 6, 2023
63805f8
Support convert LoRA safetensors into diffusers format (#2403)
haofanwang Mar 6, 2023
1598a57
make style
patrickvonplaten Mar 6, 2023
ec02192
[Unet1d] correct docs (#2565)
patrickvonplaten Mar 6, 2023
56958e1
[Training] Fix tensorboard typo (#2566)
patrickvonplaten Mar 6, 2023
b7b4683
allow Attend-and-excite pipeline work with different image sizes (#2476)
yiyixuxu Mar 6, 2023
f3f626d
Allow textual_inversion_flax script to use save_steps and revision fl…
Mar 6, 2023
b8bfef2
make style
patrickvonplaten Mar 6, 2023
c7da8fd
add intermediate logging for dreambooth training script (#2557)
yiyixuxu Mar 6, 2023
ca7ca11
community controlnet inpainting pipelines (#2561)
williamberman Mar 6, 2023
7004ff5
[docs] Move relevant code for text2image to docs (#2537)
stevhliu Mar 6, 2023
9136be1
[docs] Move DreamBooth training materials to docs (#2547)
stevhliu Mar 6, 2023
62bea2d
[docs] Move text-to-image LoRA training from blog to docs (#2527)
stevhliu Mar 6, 2023
ff91f15
Update quicktour (#2463)
stevhliu Mar 6, 2023
d3ce6f4
Support revision in Flax text-to-image training (#2567)
pcuenca Mar 7, 2023
e09a7d0
fix the default value of doc (#2539)
xiaohu2015 Mar 7, 2023
8552fd7
Added multitoken training for textual inversion. Issue 369 (#661)
isamu-isozaki Mar 7, 2023
f0b661b
[Docs]Fix invalid link to Pokemons dataset (#2583)
zxypro1 Mar 7, 2023
22a3176
[Docs] Weight prompting using compel (#2574)
patrickvonplaten Mar 7, 2023
46bef6e
community stablediffusion controlnet img2img pipeline (#2584)
mikegarts Mar 7, 2023
55660cf
Improve dynamic thresholding and extend to DDPM and DDIM Schedulers (…
clarencechen Mar 7, 2023
b285d94
[docs] Move Textual Inversion training examples to docs (#2576)
stevhliu Mar 7, 2023
309d8cf
add deps table check updated to ci (#2590)
williamberman Mar 7, 2023
d2a5247
Add notebook doc img2img (#2472)
yiyixuxu Mar 8, 2023
78507bd
[docs] Build notebooks from Markdown (#2570)
stevhliu Mar 8, 2023
445a176
[Docs] Fix link to colab (#2604)
patrickvonplaten Mar 8, 2023
68545a1
[docs] Update unconditional image generation docs (#2592)
stevhliu Mar 8, 2023
a5d2ee9
Add OpenVINO documentation (#2569)
echarlaix Mar 8, 2023
00132de
Support LoRA for text encoder (#2588)
haofanwang Mar 8, 2023
cbbad0a
correct example
patrickvonplaten Mar 8, 2023
186689a
fix: un-existing tmp config file in linux, avoid unnecessary disk IO …
knoopx Mar 8, 2023
75f1210
Fixed incorrect width/height assignment in StableDiffusionDepth2ImgPi…
antoche Mar 9, 2023
a062e47
add flax pipelines to api doc + doc string examples (#2600)
yiyixuxu Mar 9, 2023
ef504c7
make style
patrickvonplaten Mar 9, 2023
ded3174
Fix typos (#2608)
tolgacangoz Mar 9, 2023
251a34a
Migrate blog content to docs (#2477)
stevhliu Mar 9, 2023
24d624a
Add cache_dir to docs (#2624)
patrickvonplaten Mar 9, 2023
5d550cf
Make sure that DEIS, DPM and UniPC can correctly be switched in & out…
patrickvonplaten Mar 9, 2023
0650d64
Revert "[docs] Build notebooks from Markdown" (#2625)
patrickvonplaten Mar 9, 2023
6a7a546
Up vesion at which we deprecate "revision='fp16'" since `transformers…
patrickvonplaten Mar 9, 2023
c5f6c53
[Tests] Split scheduler tests (#2630)
patrickvonplaten Mar 9, 2023
c812d97
Improve ddim scheduler and fix bug when prediction type is "sample" (…
PeterL1n Mar 9, 2023
7fe638c
update paint by example docs (#2598)
williamberman Mar 9, 2023
d761b58
[From pretrained] Speed-up loading from cache (#2515)
patrickvonplaten Mar 10, 2023
4aa6829
add translated docs (#2587)
LolitaSian Mar 10, 2023
ce08cb7
[Dreambooth] Editable number of class images (#2251)
Mr-Philo Mar 10, 2023
9360bb9
Update quicktour.mdx (#2637)
tolgacangoz Mar 10, 2023
f1ab955
Update basic_training.mdx (#2639)
tolgacangoz Mar 10, 2023
a28acb5
controlnet sd 2.1 checkpoint conversions (#2593)
williamberman Mar 10, 2023
c460ef6
[docs] Update readme (#2612)
stevhliu Mar 10, 2023
1a7e9f1
[Pipeline loading] Remove send_telemetry (#2640)
patrickvonplaten Mar 10, 2023
d5ce552
[docs] Build Jax notebooks for real (#2641)
stevhliu Mar 11, 2023
bbab855
Update loading.mdx (#2642)
tolgacangoz Mar 11, 2023
6766a81
Support non square image generation for StableDiffusionSAGPipeline (#…
AkiSakurai Mar 13, 2023
fa7a576
Update schedulers.mdx (#2647)
tolgacangoz Mar 13, 2023
4ae54b3
[attention] Fix attention (#2656)
patrickvonplaten Mar 13, 2023
d9b8adc
Add support for Multi-ControlNet to StableDiffusionControlNetPipeline…
takuma104 Mar 13, 2023
f9cfb5a
[Tests] Adds a test suite for `EMAModel` (#2530)
sayakpaul Mar 14, 2023
e2d9a9b
fix the in-place modification in unet condition when using controlnet…
andrehuang Mar 14, 2023
ebd4495
image generation main process checks (#2631)
williamberman Mar 14, 2023
07a0c1c
[Hub] Upgrade to 0.13.2 (#2670)
patrickvonplaten Mar 14, 2023
a7cc468
AutoencoderKL: clamp indices of blend_h and blend_v to input size (#2…
kig Mar 14, 2023
7c1b347
Update README.md (#2653)
qwjaskzxl Mar 14, 2023
d185c0d
[Lora] correct lora saving & loading (#2655)
patrickvonplaten Mar 14, 2023
268ebcb
Add ddim noise comparative analysis pipeline (#2665)
aengusng8 Mar 14, 2023
ee71d9d
Add support for different model prediction types in DDIMInverseSchedu…
clarencechen Mar 14, 2023
279f744
controlnet integration tests num_inference_steps=3 (#2672)
williamberman Mar 14, 2023
79eb3d0
Controlnet training (#2545)
Ttl Mar 15, 2023
c9477bf
[Docs] Adds a documentation page for evaluating diffusion models (#2516)
sayakpaul Mar 15, 2023
4553c29
[Tests] fix: slow serialization test (#2678)
sayakpaul Mar 15, 2023
9d1341d
Update Dockerfile CUDA (#2682)
patrickvonplaten Mar 15, 2023
cf4227c
T5Attention support for cross-attention (#2654)
kashif Mar 15, 2023
e71f73d
Update custom_pipeline_overview.mdx (#2684)
tolgacangoz Mar 15, 2023
b4bb534
Update kerascv.mdx (#2685)
tolgacangoz Mar 15, 2023
3584f6b
Update img2img.mdx (#2688)
tolgacangoz Mar 15, 2023
91570b2
Update conditional_image_generation.mdx (#2687)
tolgacangoz Mar 15, 2023
78afb84
Update controlling_generation.mdx (#2690)
tolgacangoz Mar 15, 2023
c0b4d72
Update unconditional_image_generation.mdx (#2686)
tolgacangoz Mar 15, 2023
e52cd55
Add image_processor (#2617)
yiyixuxu Mar 15, 2023
1c2c594
[docs] Add overviews to each section (#2657)
stevhliu Mar 15, 2023
a72d14f
[docs] Create better navigation on index (#2658)
stevhliu Mar 15, 2023
588e50b
[docs] Reorganize table of contents (#2671)
stevhliu Mar 15, 2023
e828232
Rename attention (#2691)
patrickvonplaten Mar 15, 2023
d9227cf
Adding `use_safetensors` argument to give more control to users (#2123)
Narsil Mar 16, 2023
77e0ea8
[docs] Add safety checker to ethical guidelines (#2699)
stevhliu Mar 16, 2023
a4b2c2f
train_unconditional save restore unet parameters (#2706)
williamberman Mar 16, 2023
a41850a
Improve deprecation error message when using cross_attention import (…
patrickvonplaten Mar 16, 2023
f4bbcb2
fix image link in inpaint doc (#2693)
yiyixuxu Mar 17, 2023
a169571
[docs] Update ONNX doc to use `optimum` (#2702)
sayakpaul Mar 17, 2023
116f70c
Enabling gradient checkpointing for VAE (#2536)
aandyw Mar 17, 2023
9ecd924
[Tests] Correct PT2 (#2724)
patrickvonplaten Mar 18, 2023
ec2c1bc
Update README.md
patrickvonplaten Mar 18, 2023
fdcff56
Fix more slow tests
patrickvonplaten Mar 18, 2023
d91dc57
Update mps.mdx (#2749)
tolgacangoz Mar 20, 2023
a9f28b6
Update torch2.0.mdx (#2748)
tolgacangoz Mar 20, 2023
af86b0c
Update fp16.mdx (#2746)
tolgacangoz Mar 20, 2023
25ed7cb
Update dreambooth.mdx (#2742)
tolgacangoz Mar 20, 2023
afe59a9
Update philosophy.mdx (#2752)
tolgacangoz Mar 20, 2023
ba87c16
Update text_inversion.mdx (#2751)
tolgacangoz Mar 20, 2023
73bdad0
add: controlnet entry to training section in the docs. (#2677)
sayakpaul Mar 21, 2023
c10d685
Update numbers for Habana Gaudi in documentation (#2734)
regisss Mar 21, 2023
2120b4e
Improve Contribution Doc (#2043)
patrickvonplaten Mar 21, 2023
f024e00
Fix typos (#2715)
apivovarov Mar 21, 2023
0042efd
[1929]: Add CLIP guidance for Img2Img stable diffusion pipeline (#2723)
nipunjindal Mar 21, 2023
58bcf46
Add guidance start/end parameters to StableDiffusionControlNetImg2Img…
hyowon-ha Mar 21, 2023
1fcf279
Fix mps tests on torch 2.0 (#2766)
pcuenca Mar 21, 2023
b33bd91
Add option to set dtype in pipeline.to() method (#2317)
1lint Mar 21, 2023
ca1e407
stable diffusion depth batching fix (#2757)
williamberman Mar 21, 2023
a39d42b
[docs] update torch 2 benchmark (#2764)
pcuenca Mar 21, 2023
7fe8861
[docs] Clarify purpose of reproducibility docs (#2756)
stevhliu Mar 22, 2023
ca1a222
[MS Text To Video] Add first text to video (#2738)
patrickvonplaten Mar 22, 2023
92e1164
`mps`: remove warmup passes (#2771)
pcuenca Mar 22, 2023
e0d8c9e
Support for Offset Noise in examples (#2753)
haofanwang Mar 23, 2023
c681ad1
add: section on multiple controlnets. (#2762)
sayakpaul Mar 23, 2023
9dc8444
[Examples] InstructPix2Pix instruct training script (#2478)
sayakpaul Mar 23, 2023
0d633a4
deduplicate training section in the docs. (#2788)
sayakpaul Mar 23, 2023
a8315ce
[UNet3DModel] Fix with attn processor (#2790)
patrickvonplaten Mar 23, 2023
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
The table of contents is too big for display.
Diff view
Diff view
  •  
  •  
  •  
5 changes: 4 additions & 1 deletion .github/ISSUE_TEMPLATE/config.yml
Original file line number Diff line number Diff line change
@@ -1,4 +1,7 @@
contact_links:
- name: Blank issue
url: https://github.com/huggingface/diffusers/issues/new
about: General usage questions and community discussions
about: Other
- name: Forum
url: https://discuss.huggingface.co/
about: General usage questions and community discussions
1 change: 1 addition & 0 deletions .github/workflows/build_documentation.yml
Original file line number Diff line number Diff line change
Expand Up @@ -13,6 +13,7 @@ jobs:
with:
commit_sha: ${{ github.sha }}
package: diffusers
notebook_folder: diffusers_doc
languages: en ko
secrets:
token: ${{ secrets.HUGGINGFACE_PUSH }}
6 changes: 3 additions & 3 deletions .github/workflows/pr_quality.yml
Original file line number Diff line number Diff line change
Expand Up @@ -27,9 +27,8 @@ jobs:
pip install .[quality]
- name: Check quality
run: |
black --check --preview examples tests src utils scripts
isort --check-only examples tests src utils scripts
flake8 examples tests src utils scripts
black --check examples tests src utils scripts
ruff examples tests src utils scripts
doc-builder style src/diffusers docs/source --max_len 119 --check_only --path_to_docs docs/source

check_repository_consistency:
Expand All @@ -48,3 +47,4 @@ jobs:
run: |
python utils/check_copies.py
python utils/check_dummies.py
make deps_table_check_updated
12 changes: 12 additions & 0 deletions .github/workflows/pr_tests.yml
Original file line number Diff line number Diff line change
Expand Up @@ -36,6 +36,11 @@ jobs:
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_cpu

name: ${{ matrix.config.name }}

Expand Down Expand Up @@ -90,6 +95,13 @@ jobs:
--make-reports=tests_${{ matrix.config.report }} \
tests/

- name: Run example PyTorch CPU tests
if: ${{ matrix.config.framework == 'pytorch_examples' }}
run: |
python -m pytest -n 2 --max-worker-restart=0 --dist=loadfile \
--make-reports=tests_${{ matrix.config.report }} \
examples/test_examples.py

- name: Failure short reports
if: ${{ failure() }}
run: cat reports/tests_${{ matrix.config.report }}_failures_short.txt
Expand Down
165 changes: 165 additions & 0 deletions .github/workflows/push_tests_fast.yml
Original file line number Diff line number Diff line change
@@ -0,0 +1,165 @@
name: Slow 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:
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_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 -y
python -m pip install -e .[quality,test]
python -m pip install -U git+https://github.com/huggingface/transformers
python -m pip install git+https://github.com/huggingface/accelerate

- name: Environment
run: |
python utils/print_env.py

- name: Run fast PyTorch CPU tests
if: ${{ matrix.config.framework == 'pytorch' }}
run: |
python -m pytest -n 2 --max-worker-restart=0 --dist=loadfile \
-s -v -k "not Flax and not Onnx" \
--make-reports=tests_${{ matrix.config.report }} \
tests/

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

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

- name: Run example PyTorch CPU tests
if: ${{ matrix.config.framework == 'pytorch_examples' }}
run: |
python -m pytest -n 2 --max-worker-restart=0 --dist=loadfile \
--make-reports=tests_${{ matrix.config.report }} \
examples/test_examples.py

- 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

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 git+https://github.com/huggingface/accelerate
${CONDA_RUN} python -m pip install -U git+https://github.com/huggingface/transformers

- 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
5 changes: 5 additions & 0 deletions .gitignore
Original file line number Diff line number Diff line change
Expand Up @@ -169,3 +169,8 @@ tags

# dependencies
/transformers

# ruff
.ruff_cache

wandb
40 changes: 40 additions & 0 deletions CITATION.cff
Original file line number Diff line number Diff line change
@@ -0,0 +1,40 @@
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
- diffusion
- text2image
- image2image
- score-based-generative-modeling
- stable-diffusion
license: Apache-2.0
version: 0.12.1
3 changes: 2 additions & 1 deletion CODE_OF_CONDUCT.md
Original file line number Diff line number Diff line change
Expand Up @@ -24,7 +24,7 @@ community include:
* 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 community
overall diffusers community

Examples of unacceptable behavior include:

Expand All @@ -34,6 +34,7 @@ Examples of unacceptable behavior include:
* 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

Expand Down
Loading