LLM/diffusers
1
0
Fork 0
mirror of https://github.com/huggingface/diffusers.git synced 2026-02-17 00:06:20 +08:00
Code Issues Packages Projects Releases Wiki Activity
4,913 Commits 745 Branches 94 Tags
4c5082ca685d1dd0a24907890da170e258e5cd01
Commit Graph

4913 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Dhruv Nair
e649fad74d Remove unnecessary single file tests for SD Cascade UNet (#7996) 
update
 2024-12-23 13:02:12 +05:30
BootesVoid
68a94f25e8 fix: Attribute error in Logger object (logger.warning) (#8183) 2024-12-23 13:02:12 +05:30
Lucain
df6c15ea27 Use HF_TOKEN env var in CI (#7993) 2024-12-23 13:02:12 +05:30
Steven Liu
0212338ee4 [docs] VideoProcessor (#7965) 
* fix?

* fix?

* fix
 2024-12-23 13:02:12 +05:30
Vinh H. Pham
5353224d2f Make VAE compatible to torch.compile() (#7984) 
make VAE compatible to torch.compile()

Co-authored-by: YiYi Xu <yixu310@gmail.com>
 2024-12-23 13:02:12 +05:30
Sai-Suraj-27
2f6b1ecde2 fix: Fixed few docstrings according to the Google Style Guide (#7717) 
Fixed few docstrings according to the Google Style Guide.
 2024-12-23 13:02:12 +05:30
Aleksei Zhuravlev
8b08559244 Passing cross_attention_kwargs to StableDiffusionInstructPix2PixPipeline (#7961) 
* Update pipeline_stable_diffusion_instruct_pix2pix.py

Add `cross_attention_kwargs` to `__call__` method of `StableDiffusionInstructPix2PixPipeline`, which are passed to UNet.

* Update documentation for pipeline_stable_diffusion_instruct_pix2pix.py

* Update docstring

* Update docstring

* Fix typing import
 2024-12-23 13:02:12 +05:30
Junsong Chen
d7bbea7a89 [docs] add doc for PixArtSigmaPipeline (#7857) 
* 1. add doc for PixArtSigmaPipeline;

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
Co-authored-by: Guillaume LEGENDRE <glegendre01@gmail.com>
Co-authored-by: Álvaro Somoza <asomoza@users.noreply.github.com>
Co-authored-by: Bagheera <59658056+bghira@users.noreply.github.com>
Co-authored-by: bghira <bghira@users.github.com>
Co-authored-by: Hyoungwon Cho <jhw9811@korea.ac.kr>
Co-authored-by: yiyixuxu <yixu310@gmail.com>
Co-authored-by: Tolga Cangöz <46008593+standardAI@users.noreply.github.com>
Co-authored-by: Philip Pham <phillypham@google.com>
 2024-12-23 13:02:12 +05:30
Nikita
6da9e63a36 Update pipeline_controlnet_inpaint_sd_xl.py (#7983) 2024-12-23 13:02:12 +05:30
Jacob Marks
784352fff2 Fix typo in "attention" (#7977) 2024-12-23 13:02:12 +05:30
Sayak Paul
cfd25b6b3c [tests] fix Pixart Sigma tests (#7966) 
* checking tests

* checking ii.

* remove prints.

* test_pixart_1024

* fix 1024.
 2024-12-23 13:02:12 +05:30
Sayak Paul
e9eaea7502 remove unsafe workflow. (#7967) 2024-12-23 13:02:11 +05:30
Álvaro Somoza
03c3aaf6fe Consistent SDXL Controlnet callback tensor inputs (#7958) 
* make _callback_tensor_inputs consistent between sdxl pipelines

* forgot this one

* fix failing test

* fix test_components_function

* fix controlnet inpaint tests
 2024-12-23 13:02:11 +05:30
Alphin Jain
38475043b9 Fix AttributeError in train_lcm_distill_lora_sdxl_wds.py (#7923) 
Fix conditional teacher model check in train_lcm_distill_lora_sdxl_wds.py

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-12-23 13:02:11 +05:30
Liang Hou
fe3bbe8bb7 Fix the text tokenizer name in logger warning of PixArt pipelines (#7912) 
Fix CLIP to T5 in logger warning
 2024-12-23 13:02:11 +05:30
Sai-Suraj-27
ce6503f1d8 refactor: Refactored code by Merging isinstance calls (#7710) 
* Merged isinstance calls to make the code simpler.

* Corrected formatting errors using ruff.

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: YiYi Xu <yixu310@gmail.com>
 2024-12-23 13:02:11 +05:30
Sayak Paul
02559cc518 [Workflows] add a workflow that can be manually triggered on a PR. (#7942) 
* add a workflow that can be manually triggered on a PR.

* remove sudo

* add command

* small fixes.
 2024-12-23 13:02:11 +05:30
Guillaume LEGENDRE
a77a28bca7 move to GH hosted M1 runner (#7949) 2024-12-23 13:02:11 +05:30
Isamu Isozaki
d8e82de58f Adding VQGAN Training script (#5483) 
* Init commit

* Removed einops

* Added default movq config for training

* Update explanation of prompts

* Fixed inheritance of discriminator and init_tracker

* Fixed incompatible api between muse and here

* Fixed output

* Setup init training

* Basic structure done

* Removed attention for quick tests

* Style fixes

* Fixed vae/vqgan styles

* Removed redefinition of wandb

* Fixed log_validation and tqdm

* Nothing commit

* Added commit loss to lookup_from_codebook

* Update src/diffusers/models/vq_model.py

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* Adding perliminary README

* Fixed one typo

* Local changes

* Fixed main issues

* Merging

* Update src/diffusers/models/vq_model.py

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* Testing+Fixed bugs in training script

* Some style fixes

* Added wandb to docs

* Fixed timm test

* get testing suite ready.

* remove return loss

* remove return_loss

* Remove diffs

* Remove diffs

* fix ruff format

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>
 2024-12-23 13:02:11 +05:30
Sayak Paul
41939ef196 [tests] decorate StableDiffusion21PipelineSingleFileSlowTests with slow. (#7941) 
decorate StableDiffusion21PipelineSingleFileSlowTests with slow.
 2024-12-23 13:02:11 +05:30
Jingyang Zhang
7ae28c17ef [Pipeline] Adding BoxDiff to community examples (#7947) 
add boxdiff to community examples
 2024-12-23 13:02:11 +05:30
Nikita
a7f93f2475 Fix added_cond_kwargs when using IP-Adapter in StableDiffusionXLControlNetInpaintPipeline (#7924) 
Fix `added_cond_kwargs` when using IP-Adapter

Fix error when using IP-Adapter in pipeline and passing `ip_adapter_image_embeds` instead of `ip_adapter_image`

Co-authored-by: YiYi Xu <yixu310@gmail.com>
 2024-12-23 13:02:11 +05:30
Sayak Paul
41d49a70b9 [Core] separate the loading utilities in modeling similar to pipelines. (#7943) 
separate the loading utilities in modeling similar to pipelines.
 2024-12-23 13:02:11 +05:30
Sayak Paul
e63833dbf2 update to use hf-workflows for reporting the Docker build statuses (#7938) 
update to use hf-workflows for reporting
 2024-12-23 13:02:11 +05:30
Tolga Cangöz
a2c68aaa47 Expansion proposal of diffusers-cli env (#7403) 
* Expand `diffusers-cli env`

* SafeTensors -> Safetensors

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* Move `safetensors_version = "not installed"` to `else`

* Update `safetensors_version` checking

* Add GPU detection for Linux, Mac OS, and Windows

* Add accelerator detection to environment command

* Add is_peft_version to import_utils

* Update env.py

* Add `huggingface_hub` reference

* Add `transformers` reference

* Add reference for `huggingface_hub`

* Fix print statement in env.py for unusual OS

* Up

* Fix platform information in env.py

* up

* Fix import order in env.py

* ruff

* make style

* Fix platform system check in env.py

* Fix run method return type in env.py

* 🤗

* No need f-string

* Remove location info

* Remove accelerate config

* Refactor env.py to remove accelerate config

* feat: Add support for `bitsandbytes` library in environment command

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>
 2024-12-23 13:02:11 +05:30
bssrdf
fd5fe2da66 fix VAE loading issue in train_dreambooth (#7632) 
* fixed vae loading issue #7619

* rerun make style && make quality

* bring back model_has_vae and add change \ to / in config_file_name on windows os to make match work

* add missing import platform

* bring back import model_info

* make config_file_name OS independent

* switch to using Path.as_posix() to resolve OS dependence

* improve style

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: bssrdf <bssrdf@gmail.com>
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>
 2024-12-23 13:02:11 +05:30
dependabot[bot]
8802d5c9f6 Bump transformers from 4.36.0 to 4.38.0 in /examples/research_projects/realfill (#7635) 
Bump transformers in /examples/research_projects/realfill

Bumps [transformers](https://github.com/huggingface/transformers) from 4.36.0 to 4.38.0.
- [Release notes](https://github.com/huggingface/transformers/releases)
- [Commits](https://github.com/huggingface/transformers/compare/v4.36.0...v4.38.0)

---
updated-dependencies:
- dependency-name: transformers
  dependency-type: direct:production
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
 2024-12-23 13:02:11 +05:30
Kohei
a451bf4492 Update requirements.txt for text_to_image (#7892) 
Update requirements.txt

If the datasets library is old, it will not read the metadata.jsonl and the label will default to an integer of type int.

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-12-23 13:02:11 +05:30
rebel-kblee
dd39974f16 fix multicontrolnet save_pretrained logic for compatibility (#7821) 
fix multicontrolnet save_pretrained logic for compatibility

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-12-23 13:02:11 +05:30
Sayak Paul
525e4d54b8 [LoRA] Fix LoRA tests (side effects of RGB ordering) part ii (#7932) 
* check

* check 2.

* update slices
 2024-12-23 13:02:11 +05:30
Fabio Rigano
19370c69fd fix AnimateDiff creation with a unet loaded with IP Adapter (#7791) 
* Fix loading from_pipe

* Fix style

---------

Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>
 2024-12-23 13:02:11 +05:30
Álvaro Somoza
d6de291238 Official callbacks (#7761) 2024-12-23 13:02:11 +05:30
HelloWorldBeginner
23daad99b1 Add Ascend NPU support for SDXL. (#7916) 
Co-authored-by: mhh001 <mahonghao1@huawei.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-12-23 13:02:11 +05:30
Sayak Paul
8e327b65f5 [Core] fix offload behaviour when device_map is enabled. (#7919) 
fix offload behaviour when device_map is enabled.
 2024-12-23 13:02:11 +05:30
Sai-Suraj-27
b83880ef89 fix: Fixed a wrong link to supported python versions in contributing.md file (#7638) 
* Fixed a wrong link to python versions in contributing.md file.

* Updated the link to a permalink, so that it will permanently point to the specific line.
 2024-12-23 13:02:11 +05:30
momo
56be75f9a5 add custom sigmas and timesteps for StableDiffusionXLControlNet pipeline (#7913) 
add custom sigmas and timesteps
 2024-12-23 13:02:11 +05:30
HelloWorldBeginner
a4713733f6 fix bugs when using deepspeed in sdxl (#7917) 
fix bugs when using deepspeed

Co-authored-by: mhh001 <mahonghao1@huawei.com>
 2024-12-23 13:02:11 +05:30
Mark Van Aken
2243c67f09 #7535 Update FloatTensor type hints to Tensor (#7883) 
* find & replace all FloatTensors to Tensor

* apply formatting

* Update torch.FloatTensor to torch.Tensor in the remaining files

* formatting

* Fix the rest of the places where FloatTensor is used as well as in documentation

* formatting

* Update new file from FloatTensor to Tensor
 2024-12-23 13:02:11 +05:30
Sayak Paul
985cd2f174 [Core] introduce videoprocessor. (#7776) 
* introduce videoprocessor.

* fix quality

* address yiyi's feedback

* fix preprocess_video call.

* video_processor -> image_processor

* fix

* fix more.

* quality

* image_processor -> video_processor

* support List[List[PIL.Image.Image]]

* change to video_processor.

* documentation

* Apply suggestions from code review

* changes

* remove print.

* refactor video processor (part # 7776) (#7861)

* update

* update remove deprecate

* Update src/diffusers/video_processor.py

* update

* Apply suggestions from code review

* deprecate list of 5d for video and list of 4d for image + apply other feedbacks

* up

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* add doc.

* tensor2vid -> postprocess_video.

* refactor preprocess with preprocess_video

* set default values.

* empty commit

* more refactoring of prepare_latents in animatediff vid2vid

* checking documentation

* remove documentation for now.

* fix animatediff sdxl

* fix test failure [part of video processor PR] (#7905)

up

* remove preceed_with_frames.

* doc

* fix

* fix

* remove video input as a single-frame video.

---------

Co-authored-by: YiYi Xu <yixu310@gmail.com>
 2024-12-23 13:02:11 +05:30
Sayak Paul
0d6df07890 add missing image processors to the docs (#7910) 
add missing processors.
 2024-12-23 13:02:11 +05:30
Sayak Paul
1bed93f358 upgrade to python 3.10 in the Dockerfiles (#7893) 
* upgrade to python 3.10

* fix

* try https://askubuntu.com/questions/1459694/can-not-find-python3-10-after-apt-get-installation

* fix

* up

* yes

* okay

* up

* up

* up

* up

* up

* check

* okay

* up

* i[

* fix
 2024-12-23 13:02:11 +05:30
YiYi Xu
0404c72b15 [scheduler] support custom timesteps and sigmas (#7817) 
* support custom sigmas and timesteps, dpm euler

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: Benjamin Bossan <BenjaminBossan@users.noreply.github.com>
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
 2024-12-23 13:02:11 +05:30
YiYi Xu
2274fc4615 fix _optional_components in StableCascadeCombinedPipeline (#7894) 
* fix

* up
 2024-12-23 13:02:11 +05:30
Dhruv Nair
7563ad6faa Set max parallel jobs on slow test runners (#7878) 
* set max parallel

* update

* update

* update
 2024-12-23 13:02:11 +05:30
Sayak Paul
582071f3e9 [Tests] fix things after #7013 (#7899) 
* debugging

* save the resulting image

* check if order reversing works.

* checking values.

* up

* okay

* checking

* fix

* remove print
 2024-12-23 13:02:11 +05:30
Dhruv Nair
e931befdbf [Refactor] Better align from_single_file logic with from_pretrained (#7496) 
* refactor unet single file loading a bit.

* retrieve the unet from create_diffusers_unet_model_from_ldm

* update

* update

* updae

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* tests

* update

* update

* update

* Update docs/source/en/api/single_file.md

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* Update docs/source/en/api/single_file.md

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* Update docs/source/en/api/loaders/single_file.md

Co-authored-by: YiYi Xu <yixu310@gmail.com>

* Update src/diffusers/loaders/single_file.py

Co-authored-by: YiYi Xu <yixu310@gmail.com>

* Update docs/source/en/api/loaders/single_file.md

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* Update docs/source/en/api/loaders/single_file.md

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* Update docs/source/en/api/loaders/single_file.md

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* Update docs/source/en/api/loaders/single_file.md

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

---------

Co-authored-by: sayakpaul <spsayakpaul@gmail.com>
Co-authored-by: YiYi Xu <yixu310@gmail.com>
 2024-12-23 13:02:11 +05:30
Tolga Cangöz
8bc357be91 Fix several imports (#7712) 
Fix imports
 2024-12-23 13:02:11 +05:30
Tolga Cangöz
01d03e3020 Remove dead code and fix f-string issue (#7720) 
* Remove dead code

* PylancereportGeneralTypeIssues: Strings nested within an f-string cannot use the same quote character as the f-string prior to Python 3.12.

* Remove dead code
 2024-12-23 13:02:11 +05:30
Pierre Dulac
174b93a5eb Allow users to save SDXL LoRA weights for only one text encoder (#7607) 
SDXL LoRA weights for text encoders should be decoupled on save

The method checks if at least one of unet, text_encoder and
text_encoder_2 lora weights are passed, which was not reflected in the
implentation.

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: YiYi Xu <yixu310@gmail.com>
 2024-12-23 13:02:11 +05:30
YiYi Xu
79a48eb53b fix offload test (#7868) 
fix

Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>
 2024-12-23 13:02:11 +05:30