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
5,527 Commits 742 Branches 94 Tags
a0deefb6061408a5ff6523ceed24a0fa31c30b20
Commit Graph

5527 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
yiyixuxu
a0deefb606 fix more 2025-05-13 20:51:21 +02:00
yiyixuxu
e2491af650 fix import 2025-05-13 20:42:57 +02:00
yiyixuxu
506a8ea09c fix imports 2025-05-13 04:36:06 +02:00
yiyixuxu
58358c2d00 decode block, if skip decoding do not need to update latent 2025-05-13 01:57:47 +02:00
yiyixuxu
5cde77f915 make inputs truly immutable, remove the output logic in sequential pipeline, and update so that intermediates_outputs are only new variables 2025-05-13 01:52:51 +02:00
yiyixuxu
522e827625 move block mappings to its own file 2025-05-12 01:17:45 +02:00
yiyixuxu
144eae4e0b add block state will also make sure modifed intermediates_inputs will be updated 2025-05-12 01:16:42 +02:00
yiyixuxu
796453cad1 add notes 2025-05-12 01:14:43 +02:00
yiyixuxu
153ae34ff6 update __init__ 2025-05-10 03:50:47 +02:00
yiyixuxu
0acb5e1460 made a modular_pipelines folder! 2025-05-10 03:50:31 +02:00
yiyixuxu
462429b687 remove modular reelated change from pipelines folder 2025-05-10 03:50:10 +02:00
yiyixuxu
cf01aaeb49 update imports on guiders 2025-05-10 03:49:30 +02:00
yiyixuxu
2017ae5624 fix auto denoise so all tests pass 2025-05-09 08:19:24 +02:00
yiyixuxu
2b361a2413 fix get_execusion blocks with loopsequential 2025-05-09 08:17:10 +02:00
yiyixuxu
c677d528e4 change warning to debug 2025-05-09 08:16:24 +02:00
yiyixuxu
0f0618ff2b refactor the denoiseestep using LoopSequential! also add a new file for denoise step 2025-05-08 11:28:52 +02:00
yiyixuxu
d89631fc50 update input formating, consider kwarggs_type inputs with no name, e/g *_controlnet_kwargs 2025-05-08 11:27:17 +02:00
yiyixuxu
16b6583fa8 allow input_fields as input & update message 2025-05-08 11:25:31 +02:00
yiyixuxu
f552773572 remove controlnet union denoise step, refactor & reuse controlnet denoisee step to accept aditional contrlnet kwargs 2025-05-06 10:00:14 +02:00
yiyixuxu
dc4dbfe107 reefactor pipeline/block states so that it can dynamically accept kwargs 2025-05-06 09:58:44 +02:00
yiyixuxu
43ac1ff7e7 refactor controlnet union 2025-05-04 22:17:25 +02:00
yiyixuxu
efd70b7838 seperate controlnet step into input + denoise 2025-05-03 20:22:05 +02:00
yiyixuxu
7ca860c24b rename pipeline -> components, data -> block_state 2025-05-03 01:32:59 +02:00
yiyixuxu
7b86fcea31 remove lora step and ip-adapter step -> no longer needed 2025-05-02 11:31:25 +02:00
yiyixuxu
c8b5d56412 make loader optional 2025-05-02 00:46:31 +02:00
YiYi Xu
ce642e92da Merge branch 'modular-diffusers' into modular-refactor 2025-04-30 17:56:51 -10:00
YiYi Xu
6a509ba862 Merge branch 'main' into modular-diffusers 2025-04-30 17:56:25 -10:00
YiYi Xu
6d5beefe29 [modular diffusers] introducing ModularLoader (#11462) 
* cfg; slg; pag; sdxl without controlnet

---------

Co-authored-by: Aryan <aryan@huggingface.co>
 2025-04-30 11:17:20 -10:00
Yao Matrix
06beecafc5 make autoencoders. controlnet_flux and wan_transformer3d_single_file pass on xpu (#11461) 
* make autoencoders. controlnet_flux and wan_transformer3d_single_file
pass on XPU

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

* Apply style fixes

---------

Signed-off-by: Yao Matrix <matrix.yao@intel.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Aryan <aryan@huggingface.co>
 2025-05-01 02:43:31 +05:30
Vaibhav Kumawat
daf0a23958 Add LANCZOS as default interplotation mode. (#11463) 
* Add LANCZOS as default interplotation mode.

* LANCZOS as default interplotation

* LANCZOS as default interplotation mode

* Added LANCZOS as default interplotation mode
 2025-04-30 14:22:38 -04:00
tongyu
38ced7ee59 [test_models_transformer_hunyuan_video] help us test torch.compile() for impactful models (#11431) 
* Update test_models_transformer_hunyuan_video.py

* update

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2025-04-30 19:11:42 +08:00
Yao Matrix
23c98025b3 make safe diffusion test cases pass on XPU and A100 (#11458) 
* make safe diffusion test cases pass on XPU and A100

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

* calibrate A100 expected values

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

---------

Signed-off-by: Yao Matrix <matrix.yao@intel.com>
Signed-off-by: YAO Matrix <matrix.yao@intel.com>
 2025-04-30 16:05:28 +05:30
captainzz
8cd7426e56 Add StableDiffusion3InstructPix2PixPipeline (#11378) 
* upload StableDiffusion3InstructPix2PixPipeline

* Move to community

* Add readme

* Fix images

* remove images

* Change image url

* fix

* Apply style fixes
 2025-04-30 06:13:12 -04:00
Daniel Socek
fbce7aeb32 Add generic support for Intel Gaudi accelerator (hpu device) (#11328) 
* Add generic support for Intel Gaudi accelerator (hpu device)

Signed-off-by: Daniel Socek <daniel.socek@intel.com>
Co-authored-by: Libin Tang <libin.tang@intel.com>

* Add loggers for generic HPU support

Signed-off-by: Daniel Socek <daniel.socek@intel.com>

* Refactor hpu support with is_hpu_available() logic

Signed-off-by: Daniel Socek <daniel.socek@intel.com>

* Fix style for hpu support update

Signed-off-by: Daniel Socek <daniel.socek@intel.com>

* Decouple soft HPU check from hard device validation to support HPU migration

Signed-off-by: Daniel Socek <daniel.socek@intel.com>

---------

Signed-off-by: Daniel Socek <daniel.socek@intel.com>
Co-authored-by: Libin Tang <libin.tang@intel.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2025-04-30 14:45:02 +05:30
Yao Matrix
35fada4169 enable unidiffuser test cases on xpu (#11444) 
* enable unidiffuser cases on XPU

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

* fix a typo

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

* fix style

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

---------

Signed-off-by: Yao Matrix <matrix.yao@intel.com>
 2025-04-30 13:58:00 +05:30
Yao Matrix
fbe2fe5578 enable consistency test cases on XPU, all passed (#11446) 
Signed-off-by: Yao Matrix <matrix.yao@intel.com>
 2025-04-30 12:41:29 +05:30
Aryan
c86511586f torch.compile fullgraph compatibility for Hunyuan Video (#11457) 
udpate
 2025-04-30 11:21:17 +05:30
Yao Matrix
60892c55a4 enable marigold_intrinsics cases on XPU (#11445) 
Signed-off-by: Yao Matrix <matrix.yao@intel.com>
 2025-04-30 11:07:37 +05:30
Aryan
8fe5a14d9b Raise warning instead of error for block offloading with streams (#11425) 
raise warning instead of error
 2025-04-30 08:26:16 +05:30
Youlun Peng
58431f102c Set LANCZOS as the default interpolation for image resizing in ControlNet training (#11449) 
Set LANCZOS as the default interpolation for image resizing
 2025-04-29 08:47:02 -04:00
urpetkov-amd
4a9ab650aa Fixing missing provider options argument (#11397) 
* Fixing missing provider options argument

* Adding if else for provider options

* Apply suggestions from code review

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

* Apply style fixes

* Update src/diffusers/pipelines/onnx_utils.py

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

* Update src/diffusers/pipelines/onnx_utils.py

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

---------

Co-authored-by: Uros Petkovic <urpektov@amd.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: YiYi Xu <yixu310@gmail.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
 2025-04-28 10:23:05 -10:00
Linoy Tsaban
0ac1d5b482 [Hi-Dream LoRA] fix bug in validation (#11439) 
remove unnecessary pipeline moving to cpu in validation

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2025-04-28 06:22:32 -10:00
Yao Matrix
7567adfc45 enable 28 GGUF test cases on XPU (#11404) 
* enable gguf test cases on XPU

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

* make SD35LargeGGUFSingleFileTests::test_pipeline_inference pas

Signed-off-by: root <root@a4bf01945cfe.jf.intel.com>

* make FluxControlLoRAGGUFTests::test_lora_loading pass

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

* polish code

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

* Apply style fixes

---------

Signed-off-by: YAO Matrix <matrix.yao@intel.com>
Signed-off-by: root <root@a4bf01945cfe.jf.intel.com>
Signed-off-by: Yao Matrix <matrix.yao@intel.com>
Co-authored-by: root <root@a4bf01945cfe.jf.intel.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
 2025-04-28 21:32:04 +05:30
tongyu
3da98e7ee3 [train_text_to_image_lora] Better image interpolation in training scripts follow up (#11427) 
* Update train_text_to_image_lora.py

* update_train_text_to_image_lora
 2025-04-28 11:23:24 -04:00
tongyu
b3b04fefde [train_text_to_image] Better image interpolation in training scripts follow up (#11426) 
* Update train_text_to_image.py

* update
 2025-04-28 10:50:33 -04:00
Sayak Paul
0e3f2713c2 [tests] fix import. (#11434) 
fix import.
 2025-04-28 13:32:28 +08:00
Yao Matrix
a7e9f85e21 enable test_layerwise_casting_memory cases on XPU (#11406) 
* enable test_layerwise_casting_memory cases on XPU

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

* fix style

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

---------

Signed-off-by: Yao Matrix <matrix.yao@intel.com>
 2025-04-28 06:38:39 +05:30
Yao Matrix
9ce89e2efa enable group_offload cases and quanto cases on XPU (#11405) 
* enable group_offload cases and quanto cases on XPU

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

* use backend APIs

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

* fix style

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

---------

Signed-off-by: YAO Matrix <matrix.yao@intel.com>
Signed-off-by: Yao Matrix <matrix.yao@intel.com>
 2025-04-28 06:37:16 +05:30
Sayak Paul
aa5f5d41d6 [tests] add tests to check for graph breaks, recompilation, cuda syncs in pipelines during torch.compile() (#11085) 
* test for better torch.compile stuff.

* fixes

* recompilation and graph break.

* clear compilation cache.

* change to modeling level test.

* allow running compilation tests during nightlies.
 2025-04-28 08:36:33 +08:00
Mert Erbak
bd96a084d3 [train_dreambooth_lora.py] Set LANCZOS as default interpolation mode for resizing (#11421) 
* Set LANCZOS as default interpolation mode for resizing

* [train_dreambooth_lora.py] Set LANCZOS as default interpolation mode for resizing
 2025-04-26 01:58:41 -04:00