LLM/diffusers
1
0
Fork 0
mirror of https://github.com/huggingface/diffusers.git synced 2026-02-14 23:05:20 +08:00
Code Issues Packages Projects Releases Wiki Activity
4,913 Commits 743 Branches 94 Tags
4c5082ca685d1dd0a24907890da170e258e5cd01
Commit Graph

4913 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
RandomGamingDev
7f10257852 Added Code for Gradient Accumulation to work for basic_training (#8961) 
added line allowing gradient accumulation to work for basic_training example
 2024-12-23 13:02:14 +05:30
Sayak Paul
48ad9a9e93 [AuraFlow] fix long prompt handling (#8937) 
fix
 2024-12-23 13:02:14 +05:30
Dhruv Nair
d9a9cf4c49 [CI] Skip flaky download tests in PR CI (#8945) 
update
 2024-12-23 13:02:14 +05:30
Sayak Paul
edc20c3199 remove residual i from auraflow. (#8949) 
* remove residual i.

* rename to aura_flow in pipeline test
 2024-12-23 13:02:14 +05:30
Sayak Paul
c4c822b14b [Core] fix QKV fusion for attention (#8829) 
* start debugging the problem,

* start

* fix

* fix

* fix imports.

* handle hunyuan

* remove residuals.

* add a check for making sure there's appropriate procs.

* add more rigor to the tests.

* fix test

* remove redundant check

* fix-copies

* move check_qkv_fusion_matches_attn_procs_length and check_qkv_fusion_processors_exist.
 2024-12-23 13:02:14 +05:30
Dhruv Nair
df4e3f45c1 Fix name when saving text inversion embeddings in dreambooth advanced scripts (#8927) 
update
 2024-12-23 13:02:14 +05:30
Tolga Cangöz
5af8e68d97 Fix Colab and Notebook checks for diffusers-cli env (#8408) 
* chore: Update is_google_colab check to use environment variable

* Check Colab with all possible COLAB_* env variables

* Remove unnecessary word

* Make `_is_google_colab` more inclusive

* Revert "Make `_is_google_colab` more inclusive"

This reverts commit 6406db21ac.

* Make `_is_google_colab` more inclusive.

* chore: Update import_utils.py with notebook check improvement

* Refactor import_utils.py to improve notebook detection for VS Code's notebook

* chore: Remove `is_notebook()` function and related code

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-12-23 13:02:14 +05:30
Vinh H. Pham
0a6b9da6bb [Tests] Improve transformers model test suite coverage - Temporal Transformer (#8932) 
* add test for temporal transformer

* remove unused variable

* fix code quality

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-12-23 13:02:14 +05:30
akbaig
2d738e2c71 fix: checkpoint save issue in advanced dreambooth lora sdxl script (#8926) 
Co-authored-by: Linoy Tsaban <57615435+linoytsaban@users.noreply.github.com>
 2024-12-23 13:02:14 +05:30
Aritra Roy Gosthipaty
1c550bf64d [Tests] reduce the model size in the audioldm2 fast test (#7846) 
* chore: initial model size reduction

* chore: fixing expected values for failing tests

* requested edits

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-12-23 13:02:14 +05:30
Dhruv Nair
3cfd02a4c8 Update pipeline test fetcher (#8931) 
update
 2024-12-23 13:02:14 +05:30
Sayak Paul
a151876058 [Benchmarking] check if runner helps to restore benchmarking (#8929) 
* check if runner helps.

* remove caching

* gpus

* update runner group
 2024-12-23 13:02:14 +05:30
Vishnu V Jaddipal
ff7925a4de Add attentionless VAE support (#8769) 
* Add attentionless VAE support

* make style and quality, fix-copies

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-12-23 13:02:14 +05:30
Sayak Paul
94bc157cef [Tests] proper skipping of request caching test (#8908) 
proper skipping of request caching test
 2024-12-23 13:02:14 +05:30
Jiwook Han
eed4531f9c Reflect few contributions on ethical_guidelines.md that were not reflected on #8294 (#8914) 
fix_ethical_guidelines.md
 2024-12-23 13:02:14 +05:30
Sayak Paul
8e76f5b6b5 [Docs] small fixes to pag guide. (#8920) 
small fixes to pag guide.
 2024-12-23 13:02:14 +05:30
Seongsu Park
0e59db02d9 🌐 [i18n-KO] Translated docs to Korean (added 7 docs and etc) (#8804) 
* remove unused docs

* add ko-18n docs

* docs typo, edit etc

* reorder list, add `in translation` in toctree

* fix minor translation

* fix docs minor tone, etc
 2024-12-23 13:02:14 +05:30
Sayak Paul
1b5d74a9e3 [Training] SD3 training fixes (#8917) 
* SD3 training fixes

Co-authored-by: bghira <59658056+bghira@users.noreply.github.com>

* rewrite noise addition part to respect the eqn.

* styler

* Update examples/dreambooth/README_sd3.md

Co-authored-by: Kashif Rasul <kashif.rasul@gmail.com>

---------

Co-authored-by: bghira <59658056+bghira@users.noreply.github.com>
Co-authored-by: Kashif Rasul <kashif.rasul@gmail.com>
 2024-12-23 13:02:14 +05:30
Lucain
26ade526bc Use model_info.id instead of model_info.modelId (#8912) 
Mention model_info.id instead of model_info.modelId
 2024-12-23 13:02:14 +05:30
Pierre Chapuis
4379675ecb allow tensors in several schedulers step() call (#8905) 2024-12-23 13:02:14 +05:30
王奇勋
8526d0f150 [fix code annotation] Adjust the dimensions of the rotary positional embedding. (#8890) 
* 2d rotary pos emb dim

* make style

---------

Co-authored-by: haofanwang <haofanwang.ai@gmail.com>
 2024-12-23 13:02:14 +05:30
shinetzh
e86164fd01 fix loop bug in SlicedAttnProcessor (#8836) 
* fix loop bug in SlicedAttnProcessor


---------

Co-authored-by: neoshang <neoshang@tencent.com>
 2024-12-23 13:02:14 +05:30
Álvaro Somoza
0d8ef572d9 [SDXL] Fix uncaught error with image to image (#8856) 
* initial commit

* apply suggestion to sdxl pipelines

* apply fix to sd pipelines
 2024-12-23 13:02:14 +05:30
Dhruv Nair
6c1bec49a4 SSH into cpu runner additional fix (#8893) 
* update

* update

* update
 2024-12-23 13:02:14 +05:30
Dhruv Nair
909ef85464 SSH into cpu runner fix (#8888) 
* update

* update
 2024-12-23 13:02:14 +05:30
Dhruv Nair
c6dd95ae8d Add option to SSH into CPU runner. (#8884) 
update
 2024-12-23 13:02:14 +05:30
Sayak Paul
11307ce964 [Core] remove resume_download from Hub related stuff (#8648) 
* remove resume_download

* fix: _fetch_index_file call.

* remove resume_download from docs.
 2024-12-23 13:02:14 +05:30
Sayak Paul
8234c03701 [Chore] add disable forward chunking to SD3 transformer. (#8838) 
add disable forward chunking to SD3 transformer.
 2024-12-23 13:02:14 +05:30
Aryan
0f2c512fb6 [docs] pipeline docs for latte (#8844) 
* add pipeline docs for latte

* add inference time to latte docs

* apply review suggestions
 2024-12-23 13:02:14 +05:30
Tolga Cangöz
a4a5a43ef9 Fix multi-gpu case for train_cm_ct_unconditional.py (#8653) 
* Fix multi-gpu case

* Prefer previously created `unwrap_model()` function

For `torch.compile()` generalizability

* `chore: update unwrap_model() function to use accelerator.unwrap_model()`
 2024-12-23 13:02:14 +05:30
Beinsezii
387a804b3b Add AuraFlowPipeline and KolorsPipeline to auto map (#8849) 
* Add AuraFlowPipeline and KolorsPipeline to auto map

Just T2I. Validated using `quickdif`

* Add Kolors I2I and SD3 Inpaint auto maps

* style

---------

Co-authored-by: yiyixuxu <yixu310@gmail.com>
 2024-12-23 13:02:14 +05:30
Sayak Paul
8e89a32db7 [Chore] allow auraflow latest to be torch compile compatible. (#8859) 
* allow auraflow latest to be torch compile compatible.

* default to 1024 1024.
 2024-12-23 13:02:14 +05:30
Sayak Paul
07d45f95bf [Core] fix: shard loading and saving when variant is provided. (#8869) 
fix: shard loading and saving when variant is provided.
 2024-12-23 13:02:14 +05:30
Sayak Paul
503697db23 modify pocs. (#8867) 2024-12-23 13:02:14 +05:30
Tolga Cangöz
1074a46a67 [Cont'd] Add the SDE variant of ~~DPM-Solver~~ and DPM-Solver++ to DPM Single Step (#8269) 
* Add the SDE variant of DPM-Solver and DPM-Solver++ to DPM Single Step


---------

Co-authored-by: cmdr2 <secondary.cmdr2@gmail.com>
 2024-12-23 13:02:14 +05:30
Sayak Paul
ebcab060cd [Docker] include python3.10 dev and solve header missing problem (#8865) 
include python3.10 dev and solve header missing problem
 2024-12-23 13:02:14 +05:30
Aryan
10d33cda44 [tests] fix typo in pag tests (#8845) 
* fix typo in pag tests

* fix typo
 2024-12-23 13:02:14 +05:30
Nguyễn Công Tú Anh
adcd3682bf add PAG support sd15 controlnet (#8820) 
* add pag support sd15 controlnet

* fix quality import

* remove unecessary import

* remove if state

* fix tests

* remove useless function

* add sd1.5 controlnet pag docs

---------

Co-authored-by: anhnct8 <anhnct8@fpt.com>
 2024-12-23 13:02:14 +05:30
ustcuna
82a13745a0 [Community Pipelines] Accelerate inference of AnimateDiff by IPEX on CPU (#8643) 
* add animatediff_ipex community pipeline

* address the 1st round review comments
 2024-12-23 13:02:14 +05:30
Sayak Paul
0ace726d8a [Docs] add AuraFlow docs (#8851) 
* add pipeline documentation.

* add api spec for pipeline

* model documentation

* model spec
 2024-12-23 13:02:14 +05:30
Dhruv Nair
c166a0a90d Add single file loading support for AnimateDiff (#8819) 
* update

* update

* update

* update
 2024-12-23 13:02:14 +05:30
Dhruv Nair
ca5b144e23 Add VAE tiling option for SD3 (#8791) 
update
 2024-12-23 13:02:14 +05:30
Sayak Paul
824ed25cca [Core] Add AuraFlow (#8796) 
* add lavender flow transformer

---------

Co-authored-by: YiYi Xu <yixu310@gmail.com>
 2024-12-23 13:02:14 +05:30
Álvaro Somoza
1028de9d9d [Core] Add Kolors (#8812) 
* initial draft
 2024-12-23 13:02:14 +05:30
Xin Ma
b8742cb946 Latte: Latent Diffusion Transformer for Video Generation (#8404) 
* add Latte to diffusers

* remove print

* remove print

* remove print

* remove unuse codes

* remove layer_norm_latte and add a flag

* remove layer_norm_latte and add a flag

* update latte_pipeline

* update latte_pipeline

* remove unuse squeeze

* add norm_hidden_states.ndim == 2: # for Latte

* fixed test latte pipeline bugs

* fixed test latte pipeline bugs

* delete sh

* add doc for latte

* add licensing

* Move Transformer3DModelOutput to modeling_outputs

* give a default value to sample_size

* remove the einops dependency

* change norm2 for latte

* modify pipeline of latte

* update test for Latte

* modify some codes for latte

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* video_length -> num_frames; update prepare_latents copied from

* make fix-copies

* make style

* typo: videe -> video

* update

* modify for Latte pipeline

* modify latte pipeline

* modify latte pipeline

* modify latte pipeline

* modify latte pipeline

* modify for Latte pipeline

* Delete .vscode directory

* make style

* make fix-copies

* add latte transformer 3d to docs _toctree.yml

* update example

* reduce frames for test

* fixed bug of _text_preprocessing

* set num frame to 1 for testing

* remove unuse print

* add text = self._clean_caption(text) again

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: YiYi Xu <yixu310@gmail.com>
Co-authored-by: Aryan <contact.aryanvs@gmail.com>
Co-authored-by: Aryan <aryan@huggingface.co>
 2024-12-23 13:02:14 +05:30
Alan Du
8ee50300ee Reformat docstring for get_timestep_embedding (#8811) 
* Reformat docstring for `get_timestep_embedding`


---------

Co-authored-by: YiYi Xu <yixu310@gmail.com>
 2024-12-23 13:02:14 +05:30
Sayak Paul
5923ad9c0d [Tests] fix more sharding tests (#8797) 
* fix

* fix

* ugly

* okay

* fix more

* fix oops
 2024-12-23 13:02:14 +05:30
Xu Cao
e5108197fe Add pipeline_stable_diffusion_3_inpaint.py for SD3 Inference (#8709) 
* Add pipeline_stable_diffusion_3_inpaint


---------

Co-authored-by: Xu Cao <xucao2@jrehg-work-01.cs.illinois.edu>
Co-authored-by: IrohXu <irohcao@gmail.com>
Co-authored-by: YiYi Xu <yixu310@gmail.com>
 2024-12-23 13:02:14 +05:30
Tolga Cangöz
8e64c7f9a5 Remove unnecessary lines (#8569) 
* Remove unused line


---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-12-23 13:02:14 +05:30
Zhuoqun(Jack) Chen
043d98f08d Fix static typing and doc typos (#8807) 
* Fix static typing and doc typos

* Fix more same type hint typos with make fix-copies
 2024-12-23 13:02:14 +05:30