AI/diffusers
1
0
Fork 0
mirror of https://github.com/huggingface/diffusers.git synced 2026-01-27 17:22:53 +03:00
Code Activity
5,193 Commits 740 Branches 94 Tags
fbf6b856cc61fd22ad8635547bff4aafe05723f3
Commit Graph

5193 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Célina
fbf6b856cc use style bot GH Action from huggingface_hub (#10970) 
use style bot GH action from hfh

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2025-03-05 23:39:50 +05:30
Linoy Tsaban
e031caf4ea [flux lora training] fix t5 training bug (#10845) 
* fix t5 training bug

* Apply style fixes

---------

Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
 2025-03-05 13:47:01 +02:00
hlky
08f74a8b92 Add VAE Decode endpoint slow test (#10946) 2025-03-05 11:28:06 +00:00
YiYi Xu
24c062aaa1 update check_input for cogview4 (#10966) 
fix
 2025-03-04 12:12:54 -10:00
Yuxuan Zhang
a74f02fb40 [Docs] CogView4 comment fix (#10957) 
* Update pipeline_cogview4.py

* Use GLM instead of T5 in doc
 2025-03-04 11:25:43 -10:00
Eliseu Silva
66bf7ea5be feat: add Mixture-of-Diffusers ControlNet Tile upscaler Pipeline for SDXL (#10951) 
* feat: add Mixture-of-Diffusers ControlNet Tile upscaler Pipeline for SDXL

* make style make quality
 2025-03-04 17:17:36 -03:00
Alexey Zolotenkov
b8215b1c06 Fix incorrect seed initialization when args.seed is 0 (#10964) 
* Fix seed initialization to handle args.seed = 0 correctly

* Apply style fixes

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
 2025-03-04 10:09:52 -10:00
Aryan
3ee899fa0c [LoRA] Support Wan (#10943) 
* update

* refactor image-to-video pipeline

* update

* fix copied from

* use FP32LayerNorm
 2025-03-05 01:27:34 +05:30
CyberVy
dcd77ce222 Fix the missing parentheses when calling is_torchao_available in quantization_config.py. (#10961) 
Update quantization_config.py
 2025-03-04 09:52:41 -03:00
a120092009
11d8e3ce2c [Quantization] support pass MappingType for TorchAoConfig (#10927) 
* [Quantization] support pass MappingType for TorchAoConfig

* Apply style fixes

---------

Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
 2025-03-04 16:40:50 +05:30
Sayak Paul
97fda1b75c [LoRA] feat: support non-diffusers lumina2 LoRAs. (#10909) 
* feat: support non-diffusers lumina2 LoRAs.

* revert ipynb changes (but I don't know why this is required ☹️)

* empty

---------

Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>
Co-authored-by: YiYi Xu <yixu310@gmail.com>
 2025-03-04 14:40:55 +05:30
Sayak Paul
cc22058324 Update evaluation.md (#10938) 
* Update evaluation.md

* Update docs/source/en/conceptual/evaluation.md

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

---------

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
 2025-03-04 13:58:16 +05:30
Fanli Lin
7855ac597e [tests] make tests device-agnostic (part 4) (#10508) 
* initial comit

* fix empty cache

* fix one more

* fix style

* update device functions

* update

* update

* Update src/diffusers/utils/testing_utils.py

Co-authored-by: hlky <hlky@hlky.ac>

* Update src/diffusers/utils/testing_utils.py

Co-authored-by: hlky <hlky@hlky.ac>

* Update src/diffusers/utils/testing_utils.py

Co-authored-by: hlky <hlky@hlky.ac>

* Update tests/pipelines/controlnet/test_controlnet.py

Co-authored-by: hlky <hlky@hlky.ac>

* Update src/diffusers/utils/testing_utils.py

Co-authored-by: hlky <hlky@hlky.ac>

* Update src/diffusers/utils/testing_utils.py

Co-authored-by: hlky <hlky@hlky.ac>

* Update tests/pipelines/controlnet/test_controlnet.py

Co-authored-by: hlky <hlky@hlky.ac>

* with gc.collect

* update

* make style

* check_torch_dependencies

* add mps empty cache

* add changes

* bug fix

* enable on xpu

* update more cases

* revert

* revert back

* Update test_stable_diffusion_xl.py

* Update tests/pipelines/stable_diffusion/test_stable_diffusion.py

Co-authored-by: hlky <hlky@hlky.ac>

* Update tests/pipelines/stable_diffusion/test_stable_diffusion.py

Co-authored-by: hlky <hlky@hlky.ac>

* Update tests/pipelines/stable_diffusion/test_stable_diffusion_img2img.py

Co-authored-by: hlky <hlky@hlky.ac>

* Update tests/pipelines/stable_diffusion/test_stable_diffusion_img2img.py

Co-authored-by: hlky <hlky@hlky.ac>

* Update tests/pipelines/stable_diffusion/test_stable_diffusion_img2img.py

Co-authored-by: hlky <hlky@hlky.ac>

* Apply suggestions from code review

Co-authored-by: hlky <hlky@hlky.ac>

* add test marker

---------

Co-authored-by: hlky <hlky@hlky.ac>
 2025-03-04 08:26:06 +00:00
CyberVy
30cef6bff3 Improve load_ip_adapter RAM Usage (#10948) 
* Update ip_adapter.py

* Update ip_adapter.py

* Update ip_adapter.py

* Update ip_adapter.py

* Update ip_adapter.py

* Apply style fixes

---------

Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: hlky <hlky@hlky.ac>
 2025-03-04 07:21:23 +00:00
Ahmed Belgacem
8f15be169f Fix redundant prev_output_channel assignment in UNet2DModel (#10945) 2025-03-03 11:43:15 -10:00
Yuxuan Zhang
f92e599c70 Update pipeline_cogview4.py (#10944) 2025-03-03 09:42:01 -10:00
Parag Ekbote
982f9b38d6 Add Example of IPAdapterScaleCutoffCallback to Docs (#10934) 
* Add example of Ip-Adapter-Callback.

* Add image links from HF Hub.
 2025-03-03 08:32:45 -08:00
fancydaddy
c9a219b323 add from_single_file to animatediff (#10924) 
* Update pipeline_animatediff.py

* Update pipeline_animatediff_controlnet.py

* Update pipeline_animatediff_sparsectrl.py

* Update pipeline_animatediff_video2video.py

* Update pipeline_animatediff_video2video_controlnet.py

---------

Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>
 2025-03-03 19:11:54 +05:30
Teriks
9e910c4633 Fix SD2.X clip single file load projection_dim (#10770) 
* Fix SD2.X clip single file load projection_dim

Infer projection_dim from the checkpoint before loading
from pretrained, override any incorrect hub config.

Hub configuration for SD2.X specifies projection_dim=512
which is incorrect for SD2.X checkpoints loaded from civitai
and similar.

Exception was previously thrown upon attempting to
load_model_dict_into_meta for SD2.X single file checkpoints.

Such LDM models usually require projection_dim=1024

* convert_open_clip_checkpoint use hidden_size for text_proj_dim

* convert_open_clip_checkpoint, revert checkpoint[text_proj_key].shape[1] -> [0]

values are identical

---------

Co-authored-by: Teriks <Teriks@users.noreply.github.com>
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>
 2025-03-03 19:00:39 +05:30
Bubbliiiing
5e3b7d2d8a Add EasyAnimateV5.1 text-to-video, image-to-video, control-to-video generation model (#10626) 
* Update EasyAnimate V5.1

* Add docs && add tests && Fix comments problems in transformer3d and vae

* delete comments and remove useless import

* delete process

* Update EXAMPLE_DOC_STRING

* rename transformer file

* make fix-copies

* make style

* refactor pt. 1

* update toctree.yml

* add model tests

* Update layer_norm for norm_added_q and norm_added_k in Attention

* Fix processor problem

* refactor vae

* Fix problem in comments

* refactor tiling; remove einops dependency

* fix docs path

* make fix-copies

* Update src/diffusers/pipelines/easyanimate/pipeline_easyanimate_control.py

* update _toctree.yml

* fix test

* update

* update

* update

* make fix-copies

* fix tests

---------

Co-authored-by: Aryan <aryan@huggingface.co>
Co-authored-by: Aryan <contact.aryanvs@gmail.com>
Co-authored-by: YiYi Xu <yixu310@gmail.com>
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>
 2025-03-03 18:37:19 +05:30
Sayak Paul
7513162b8b [Tests] Remove more encode prompts tests (#10942) 
* fix-copies went uncaught it seems.

* remove more unneeded encode_prompt() tests

* Revert "fix-copies went uncaught it seems."

This reverts commit eefb302791.

* empty
 2025-03-03 16:55:01 +05:30
Sayak Paul
4aaa0d21ba [chore] fix-copies to flux pipelines (#10941) 
fix-copies went uncaught it seems.
 2025-03-03 11:21:57 +05:30
hlky
54043c3e2e Update VAE Decode endpoints (#10939) 2025-03-02 18:29:53 +00:00
hlky
fc4229a0c3 Add remote_decode to remote_utils (#10898) 
* Add `remote_decode` to `remote_utils`

* test dependency

* test dependency

* dependency

* dependency

* dependency

* docstrings

* changes

* make style

* apply

* revert, add new options

* Apply style fixes

* deprecate base64, headers not needed

* address comments

* add license header

* init test_remote_decode

* more

* more test

* more test

* skeleton for xl, flux

* more test

* flux test

* flux packed

* no scaling

* -save

* hunyuanvideo test

* Apply style fixes

* init docs

* Update src/diffusers/utils/remote_utils.py

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

* comments

* Apply style fixes

* comments

* hybrid_inference/vae_decode

* fix

* tip?

* tip

* api reference autodoc

* install tip

---------

Co-authored-by: sayakpaul <spsayakpaul@gmail.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
 2025-03-02 17:10:01 +00:00
hlky
694f9658c1 Support IPAdapter for more Flux pipelines (#10708) 
* Support IPAdapter for more Flux pipelines

* -copied from

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2025-03-02 15:04:12 +00:00
YiYi Xu
2d8a41cae8 [Alibaba Wan Team] continue on #10921 Wan2.1 (#10922) 
* Add wanx pipeline, model and example

* wanx_merged_v1

* change WanX into Wan

* fix i2v fp32 oom error

Link: https://code.alibaba-inc.com/open_wanx2/diffusers/codereview/20607813

* support t2v load fp32 ckpt

* add example

* final merge v1

* Update autoencoder_kl_wan.py

* up

* update middle, test up_block

* up up

* one less nn.sequential

* up more

* up

* more

* [refactor] [wip] Wan transformer/pipeline (#10926)

* update

* update

* refactor rope

* refactor pipeline

* make fix-copies

* add transformer test

* update

* update

* make style

* update tests

* tests

* conversion script

* conversion script

* update

* docs

* remove unused code

* fix _toctree.yml

* update dtype

* fix test

* fix tests: scale

* up

* more

* Apply suggestions from code review

* Apply suggestions from code review

* style

* Update scripts/convert_wan_to_diffusers.py

* update docs

* fix

---------

Co-authored-by: Yitong Huang <huangyitong.hyt@alibaba-inc.com>
Co-authored-by: 亚森 <wangjiayu.wjy@alibaba-inc.com>
Co-authored-by: Aryan <aryan@huggingface.co>
 2025-03-02 17:24:26 +05:30
Dhruv Nair
7007febae5 [CI] Update Stylebot Permissions (#10931) 
update
 2025-03-01 09:43:05 +05:30
Sayak Paul
d230ecc570 [style bot] improve security for the stylebot. (#10908) 
* improve security for the stylebot.

* ❌
 2025-02-28 22:01:31 +05:30
hlky
37a5f1b3b6 Experimental per control type scale for ControlNet Union (#10723) 
* ControlNet Union scale

* fix

* universal interface

* from_multi

* from_multi
 2025-02-27 10:23:38 +00:00
Dhruv Nair
501d9de701 [CI] Fix for failing IP Adapter test in Fast GPU PR tests (#10915) 
* update

* update

* update

* update
 2025-02-27 14:22:28 +05:30
Dhruv Nair
e5c43b8af7 [CI] Fix Fast GPU tests on PR (#10912) 
* update

* update

* update

* update

* update

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2025-02-27 14:21:50 +05:30
CyberVy
9a8e8db79f Fix Callback Tensor Inputs of the SD Controlnet Pipelines are missing some elements. (#10907) 
* Update pipeline_controlnet_img2img.py

* Update pipeline_controlnet_inpaint.py

* Update pipeline_controlnet.py

---------
 2025-02-26 15:36:47 -03:00
Sayak Paul
764d7ed49a [Tests] fix: lumina2 lora fuse_nan test (#10911) 
fix: lumina2 lora fuse_nan test
 2025-02-26 22:44:49 +05:30
Anton Obukhov
3fab6624fd Marigold Update: v1-1 models, Intrinsic Image Decomposition pipeline, documentation (#10884) 
* minor documentation fixes of the depth and normals pipelines

* update license headers

* update model checkpoints in examples
fix missing prediction_type in register_to_config in the normals pipeline

* add initial marigold intrinsics pipeline
update comments about num_inference_steps and ensemble_size
minor fixes in comments of marigold normals and depth pipelines

* update uncertainty visualization to work with intrinsics

* integrate iid


---------

Co-authored-by: YiYi Xu <yixu310@gmail.com>
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
 2025-02-25 14:13:02 -10:00
Yih-Dar
f0ac7aaafc Security fix (#10905) 
fix

Co-authored-by: ydshieh <ydshieh@users.noreply.github.com>
 2025-02-25 23:25:37 +05:30
CyberVy
613e77f8be Fix Callback Tensor Inputs of the SDXL Controlnet Inpaint and Img2img Pipelines are missing "controlnet_image". (#10880) 
* Update pipeline_controlnet_inpaint_sd_xl.py

* Update pipeline_controlnet_sd_xl_img2img.py

* Update pipeline_controlnet_union_inpaint_sd_xl.py

* Update pipeline_controlnet_union_sd_xl_img2img.py

* Update pipeline_controlnet_inpaint_sd_xl.py

* Update pipeline_controlnet_sd_xl_img2img.py

* Update pipeline_controlnet_union_inpaint_sd_xl.py

* Update pipeline_controlnet_union_sd_xl_img2img.py

* Apply make style and make fix-copies fixes

* Update geodiff_molecule_conformation.ipynb

* Delete examples/research_projects/geodiff/geodiff_molecule_conformation.ipynb

* Delete examples/research_projects/gligen/demo.ipynb

* Create geodiff_molecule_conformation.ipynb

* Create demo.ipynb

* Update geodiff_molecule_conformation.ipynb

* Update geodiff_molecule_conformation.ipynb

* Delete examples/research_projects/geodiff/geodiff_molecule_conformation.ipynb

* Add files via upload

* Delete src/diffusers/pipelines/controlnet/pipeline_controlnet_inpaint.py

* Add files via upload
 2025-02-25 12:53:03 -03:00
Daniel Regado
1450c2ac4f Multi IP-Adapter for Flux pipelines (#10867) 
* Initial implementation of Flux multi IP-Adapter

* Update src/diffusers/pipelines/flux/pipeline_flux.py

Co-authored-by: hlky <hlky@hlky.ac>

* Update src/diffusers/pipelines/flux/pipeline_flux.py

Co-authored-by: hlky <hlky@hlky.ac>

* Changes for ipa image embeds

* Update src/diffusers/pipelines/flux/pipeline_flux.py

Co-authored-by: hlky <hlky@hlky.ac>

* Update src/diffusers/pipelines/flux/pipeline_flux.py

Co-authored-by: hlky <hlky@hlky.ac>

* make style && make quality

* Updated ip_adapter test

* Created typing_utils.py

---------

Co-authored-by: hlky <hlky@hlky.ac>
 2025-02-25 09:51:15 +00:00
Dhruv Nair
cc7b5b873a [CI] Improvements to conditional GPU PR tests (#10859) 
* update

* update

* update

* update

* update

* update

* test

* test

* test

* test

* test

* test

* test

* test

* test

* test

* test

* test

* update
 2025-02-25 09:49:29 +05:30
Aryan
0404703237 [refactor] Remove additional Flux code (#10881) 
* update

* apply review suggestions

---------

Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>
 2025-02-24 14:56:30 -10:00
Aryan
13f20c7fe8 [refactor] SD3 docs & remove additional code (#10882) 
* update

* update

* update
 2025-02-25 03:08:47 +05:30
Dhruv Nair
87599691b9 [Docs] Fix toctree sorting (#10894) 
update
 2025-02-24 10:05:32 -10:00
Sayak Paul
36517f6124 [chore] correct qk norm list. (#10876) 
correct qk norm list.
 2025-02-24 07:49:14 -10:00
Aryan
64af74fc58 [docs] Add CogVideoX Schedulers (#10885) 
update
 2025-02-24 07:02:59 -10:00
SahilCarterr
170833c22a [Fix] fp16 unscaling in train_dreambooth_lora_sdxl (#10889) 
Fix fp16 bug

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2025-02-24 06:49:23 -10:00
Steven Liu
db21c97043 [docs] Flux group offload (#10847) 
* flux group-offload

* feedback
 2025-02-24 08:47:08 -08:00
Steven Liu
3fdf173084 [docs] Update prompt weighting docs (#10843) 
* sd_embed

* feedback
 2025-02-24 08:46:26 -08:00
hlky
aba4a5799a Add SD3 ControlNet to AutoPipeline (#10888) 
Co-authored-by: puhuk <wetr235@gmail.com>
 2025-02-24 06:21:02 -10:00
Sayak Paul
b0550a66cc [LoRA] restrict certain keys to be checked for peft config update. (#10808) 
* restruct certain keys to be checked for peft config update.

* updates

* finish./

* finish 2.

* updates
 2025-02-24 16:54:38 +05:30
hlky
6f74ef550d Fix torch_dtype in Kolors text encoder with transformers v4.49 (#10816) 
* Fix `torch_dtype` in Kolors text encoder with `transformers` v4.49

* Default torch_dtype and warning
 2025-02-24 13:37:54 +05:30
Daniel Regado
9c7e205176 Comprehensive type checking for from_pretrained kwargs (#10758) 
* More robust from_pretrained init_kwargs type checking

* Corrected for Python 3.10

* Type checks subclasses and fixed type warnings

* More type corrections and skip tokenizer type checking

* make style && make quality

* Updated docs and types for Lumina pipelines

* Fixed check for empty signature

* changed location of helper functions

* make style

---------

Co-authored-by: hlky <hlky@hlky.ac>
 2025-02-22 13:15:19 +00:00