AI/diffusers
1
0
Fork 0
mirror of https://github.com/huggingface/diffusers.git synced 2026-01-29 07:22:12 +03:00
Code Activity
6,178 Commits 742 Branches 94 Tags
modular-doc
Commit Graph

6178 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Aryan
f19421e27c Helper functions to return skip-layer compatible layers (#12048) 
update

Co-authored-by: Álvaro Somoza <asomoza@users.noreply.github.com>
 2025-08-06 07:55:16 -10:00
Aryan
69cdc25746 Fix group offloading synchronization bug for parameter-only GroupModule's (#12077) 
* update

* update

* refactor

* fuck yeah

* make style

* Update src/diffusers/hooks/group_offloading.py

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

* Update src/diffusers/hooks/group_offloading.py

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2025-08-06 21:11:00 +05:30
Aryan
cfd6ec7465 [refactor] condense group offloading (#11990) 
* update

* update

* refactor

* add test

* address review comment

* nit
 2025-08-06 20:01:02 +05:30
jiqing-feng
1082c46afa fix input shape for WanGGUFTexttoVideoSingleFileTests (#12081) 
Signed-off-by: jiqing-feng <jiqing.feng@intel.com>
 2025-08-06 14:12:40 +05:30
Isotr0py
ba2ba9019f Add cuda kernel support for GGUF inference (#11869) 
* add gguf kernel support

Signed-off-by: Isotr0py <2037008807@qq.com>

* fix

Signed-off-by: Isotr0py <2037008807@qq.com>

* optimize

Signed-off-by: Isotr0py <2037008807@qq.com>

* update

* update

* update

* update

* update

---------

Signed-off-by: Isotr0py <2037008807@qq.com>
Co-authored-by: DN6 <dhruv.nair@gmail.com>
 2025-08-05 21:36:48 +05:30
C
fa4c0e5e2e optimize QwenImagePipeline to reduce unnecessary CUDA synchronization (#12072) 2025-08-05 04:12:47 -10:00
Sayak Paul
b793debd9d [tests] deal with the failing AudioLDM2 tests (#12069) 
up
 2025-08-05 15:54:25 +05:30
Aryan
377057126c [tests] Fix Qwen test_inference slices (#12070) 
update
 2025-08-05 14:10:22 +05:30
Sayak Paul
5937e11d85 [docs] small corrections to the example in the Qwen docs (#12068) 
* up

* up
 2025-08-05 09:47:21 +05:30
Sayak Paul
9c1d4e3be1 [wip] feat: support lora in qwen image and training script (#12056) 
* feat: support lora in qwen image and training script

* up

* up

* up

* up

* up

* up

* add lora tests

* fix

* add tests

* fix

* reviewer feedback

* up[

* Apply suggestions from code review

Co-authored-by: Aryan <aryan@huggingface.co>

---------

Co-authored-by: Aryan <aryan@huggingface.co>
 2025-08-05 07:06:02 +05:30
Steven Liu
7ea065c507 [docs] Install (#12026) 
* initial

* init
 2025-08-04 10:13:36 -07:00
Sayak Paul
7a7a487396 fix the rest for all GPUs in CI (#12064) 
fix the rest
 2025-08-04 21:03:33 +05:30
Sayak Paul
4efb4db9d0 enable all gpus when running ci. (#12062) 2025-08-04 20:17:34 +05:30
Pauline Bailly-Masson
639fd12a20 CI fixing (#12059) 
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2025-08-04 19:09:17 +05:30
naykun
69a9828f4d fix(qwen-image): update vae license (#12063) 
* fix(qwen-image):
- update vae license

* Apply style fixes

---------

Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Aryan <aryan@huggingface.co>
 2025-08-04 17:08:47 +05:30
Samuel Tesfai
11d22e0e80 Cross attention module to Wan Attention (#12058) 
* Cross attention module to Wan Attention

* Apply style fixes

---------

Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Aryan <aryan@huggingface.co>
 2025-08-04 16:35:06 +05:30
Aryan
9a38fab5ae tests + minor refactor for QwenImage (#12057) 
* update

* update

* update

* add docs
 2025-08-04 16:28:42 +05:30
YiYi Xu
cb8e61ed2f [wan2.2] follow-up (#12024) 
* up

---------

Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
 2025-08-03 23:06:22 -10:00
naykun
8e53cd959e Qwen-Image (#12055) 
* (feat): qwen-image integration

* fix(qwen-image):
- remove unused logics related to controlnet/ip-adapter

* fix(qwen-image):
- compatible with attention dispatcher
- cond cache support

* fix(qwen-image):
- cond cache registry
- attention backend argument
- fix copies

* fix(qwen-image):
- remove local test

* Update src/diffusers/models/transformers/transformer_qwenimage.py

---------

Co-authored-by: YiYi Xu <yixu310@gmail.com>
 2025-08-03 08:20:35 -10:00
Tanuj Rai
359b605f4b Update autoencoder_kl_cosmos.py (#12045) 
* Update autoencoder_kl_cosmos.py

* Apply style fixes

---------

Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Aryan <aryan@huggingface.co>
 2025-08-02 20:24:01 +05:30
Bernd Doser
6febc08bfc Fix type of force_upcast to bool (#12046) 2025-08-02 19:03:13 +05:30
Sayak Paul
9a2eaed002 [LoRA] support lightx2v lora in wan (#12040) 
* support lightx2v lora in wan

* add docsa.

* reviewer feedback

* empty
 2025-08-02 11:43:26 +05:30
Philip Brown
0c71189abe Allow SD pipeline to use newer schedulers, eg: FlowMatch (#12015) 
Allow SD pipeline to use newer schedulers, eg: FlowMatch,
by skipping attribute that doesnt exist there
(scale_model_input)
 Lines starting
 2025-07-31 23:59:40 -10:00
YiYi Xu
58d2b10a2e [wan2.2] fix vae patches (#12041) 
up
 2025-07-31 23:43:42 -10:00
Sayak Paul
20e0740b88 [training-scripts] Make pytorch examples UV-compatible (#12000) 
* add uv dependencies on top of scripts.

* add uv deps.
 2025-07-31 22:09:52 +05:30
Álvaro Somoza
9d313fc718 [Fix] huggingface-cli to hf missed files (#12008) 
fix
 2025-07-30 14:25:43 -04:00
Steven Liu
f83dd5c984 [docs] Update index (#12020) 
initial

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2025-07-30 08:31:01 -07:00
Sayak Paul
c052791b5f [core] support attention backends for LTX (#12021) 
* support attention backends for lTX

* Apply suggestions from code review

Co-authored-by: Aryan <aryan@huggingface.co>

* reviewer feedback.

---------

Co-authored-by: Aryan <aryan@huggingface.co>
 2025-07-30 16:35:11 +05:30
Ömer Karışman
843e3f9346 wan2.2 i2v FirstBlockCache fix (#12013) 
* enable caching for WanImageToVideoPipeline

* ruff format
 2025-07-30 15:44:53 +05:30
YiYi Xu
d8854b8d54 [wan2.2] add 5b i2v (#12006) 
* add 5b ti2v

* remove a copy

* Update src/diffusers/pipelines/wan/pipeline_wan_i2v.py

Co-authored-by: Aryan <aryan@huggingface.co>

* Apply suggestions from code review

---------

Co-authored-by: Aryan <aryan@huggingface.co>
 2025-07-29 17:34:05 -10:00
Steven Liu
327e251b81 [docs] Fix link (#12018) 
fix link
 2025-07-29 11:45:15 -07:00
Steven Liu
dfa48831e2 [docs] quant_kwargs (#11712) 
* draft

* update
 2025-07-29 10:23:16 -07:00
Sayak Paul
94df8ef68a [docs] include lora fast post. (#11993) 
* include lora fast post.

* include details.

* Apply suggestions from code review

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

---------

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
 2025-07-29 22:36:50 +05:30
Sayak Paul
203dc520a7 [modular] add Modular flux for text-to-image (#11995) 
* start flux.

* more

* up

* up

* up

* up

* get back the deleted files.

* up

* empathy
 2025-07-29 22:06:39 +05:30
jlonge4
56d4387270 feat: add flux kontext (#11985) 
* add flux kontext

* add kontext to img2img

* Apply style fixes
 2025-07-29 03:00:34 -04:00
Álvaro Somoza
edcbe8038b Fix huggingface-hub failing tests (#11994) 
* login

* more logins

* uploads

* missed login

* another missed login

* downloads

* examples and more logins

* fix

* setup

* Apply style fixes

* fix

* Apply style fixes
 2025-07-29 02:34:58 -04:00
Aryan
c02c4a6d27 [refactor] Wan single file implementation (#11918) 
* update

* update

* update

* add coauthor

Co-Authored-By: Dhruv Nair <dhruv.nair@gmail.com>

* improve test

* handle ip adapter params correctly

* fix chroma qkv fusion test

* fix fastercache implementation

* remove set_attention_backend related code

* fix more tests

* fight more tests

* add back set_attention_backend

* update

* update

* make style

* make fix-copies

* make ip adapter processor compatible with attention dispatcher

* refactor chroma as well

* attnetion dispatcher support

* remove transpose; fix rope shape

* remove rmsnorm assert

* minify and deprecate npu/xla processors

* remove rmsnorm assert

* minify and deprecate npu/xla processors

* update

* Update src/diffusers/models/transformers/transformer_wan.py

---------

Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>
 2025-07-29 10:02:56 +05:30
Aryan
6f3ac3050f [refactor] some shared parts between hooks + docs (#11968) 
* update

* try test fix

* add missing link

* fix tests

* Update src/diffusers/hooks/first_block_cache.py

* make style
 2025-07-29 07:44:02 +05:30
YiYi Xu
a6d9f6a1a9 [WIP] Wan2.2 (#12004) 
* support wan 2.2 i2v

* add t2v + vae2.2

* add conversion script for vae 2.2

* add

* add 5b t2v

* conversion script

* refactor out reearrange

* remove a copied from in skyreels

* Apply suggestions from code review

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

* Update src/diffusers/models/transformers/transformer_wan.py

* fix fast tests

* style

---------

Co-authored-by: bagheera <59658056+bghira@users.noreply.github.com>
 2025-07-28 11:58:55 -10:00
Yao Matrix
284150449d enable quantcompile test on xpu (#11988) 
Signed-off-by: Yao, Matrix <matrix.yao@intel.com>
 2025-07-28 09:58:45 +05:30
Aryan
3d2f8ae99b [compile] logger statements create unnecessary guards during dynamo tracing (#11987) 
* update

* update
 2025-07-26 00:28:17 +05:30
Aryan
f36ba9f094 [modular diffusers] Wan (#11913) 
* update
 2025-07-23 06:19:40 -10:00
Sayak Paul
1c50a5f7e0 [tests] enforce torch version in the compilation tests. (#11979) 
enforce torch version in the compilation tests.
 2025-07-23 19:42:46 +05:30
Sayak Paul
7ae6347e33 [docs] update guidance_scale docstring for guidance_distilled models. (#11935) 
* update guidance_scale docstring for guidance_distilled models.

* Update pipeline_flux.py

* Update pipeline_flux_control.py

* Update pipeline_flux_kontext.py

* Update pipeline_flux_kontext_inpaint.py

* Update pipeline_sana_sprint.py

* style

* Update pipeline_hidream_image.py

* Update pipeline_chroma.py

* Update pipeline_chroma_img2img.py

* Update pipeline_hunyuan_video.py

---------

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
 2025-07-23 17:49:38 +05:30
Aryan
178d32dedd [tests] Add test slices for Wan (#11920) 
* update

* fix wan vace test slice

* test

* fix
 2025-07-23 17:23:52 +05:30
YiYi Xu
ef1e628729 fix style (#11975) 
up
 2025-07-22 10:25:40 -10:00
Sam Gao
173e1b147d [Examples] Uniform notations in train_flux_lora (#10011) 
[Examples] uniform naming notations

since the in parameter `size` represents `args.resolution`, I thus replace the `args.resolution` inside DreamBoothData with `size`. And revise some notations such as `center_crop`.

Co-authored-by: Linoy Tsaban <57615435+linoytsaban@users.noreply.github.com>
 2025-07-22 09:14:00 -10:00
Aryan
e46e139f95 Remove logger warnings for attention backends and hard error during runtime instead (#11967) 
* update

* update

* update
 2025-07-22 20:47:44 +05:30
Yao Matrix
14725164be fix "Expected all tensors to be on the same device, but found at least two devices" error (#11690) 
* xx

* fix

Signed-off-by: YAO Matrix <matrix.yao@intel.com>

* Update model_loading_utils.py

* Update test_models_unet_2d_condition.py

* Update test_models_unet_2d_condition.py

* fix style

Signed-off-by: YAO Matrix <matrix.yao@intel.com>

* fix comments

Signed-off-by: Matrix Yao <matrix.yao@intel.com>

* Update unet_2d_blocks.py

* update

Signed-off-by: Matrix Yao <matrix.yao@intel.com>

---------

Signed-off-by: YAO Matrix <matrix.yao@intel.com>
Signed-off-by: Matrix Yao <matrix.yao@intel.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2025-07-22 13:39:24 +02:00
YiYi Xu
638cc035e5 [Modular] update the collection behavior (#11963) 
* only remove from the collection
 2025-07-21 08:47:07 -10:00