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
5,553 Commits 740 Branches 94 Tags
368958df6f79da805bed6178b90bf1ca76e5d57b
Commit Graph

5553 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Sayak Paul
368958df6f [LoRA] parse metadata from LoRA and save metadata (#11324) 
* feat: parse metadata from lora state dicts.

* tests

* fix tests

* key renaming

* fix

* smol update

* smol updates

* load metadata.

* automatically save metadata in save_lora_adapter.

* propagate changes.

* changes

* add test to models too.

* tigher tests.

* updates

* fixes

* rename tests.

* sorted.

* Update src/diffusers/loaders/lora_base.py

Co-authored-by: Benjamin Bossan <BenjaminBossan@users.noreply.github.com>

* review suggestions.

* removeprefix.

* propagate changes.

* fix-copies

* sd

* docs.

* fixes

* get review ready.

* one more test to catch error.

* change to a different approach.

* fix-copies.

* todo

* sd3

* update

* revert changes in get_peft_kwargs.

* update

* fixes

* fixes

* simplify _load_sft_state_dict_metadata

* update

* style fix

* uipdate

* update

* update

* empty commit

* _pack_dict_with_prefix

* update

* TODO 1.

* todo: 2.

* todo: 3.

* update

* update

* Apply suggestions from code review

Co-authored-by: Benjamin Bossan <BenjaminBossan@users.noreply.github.com>

* reraise.

* move argument.

---------

Co-authored-by: Benjamin Bossan <BenjaminBossan@users.noreply.github.com>
Co-authored-by: Linoy Tsaban <57615435+linoytsaban@users.noreply.github.com>
 2025-06-13 14:37:49 +05:30
Aryan
e52ceae375 Support Wan AccVideo lora (#11704) 
* update

* make style

* Update src/diffusers/loaders/lora_conversion_utils.py

* add note explaining threshold
 2025-06-13 11:55:08 +05:30
Sayak Paul
62cbde8d41 [docs] mention fp8 benefits on supported hardware. (#11699) 
* mention fp8 benefits on supported hardware.

* Update docs/source/en/quantization/torchao.md

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

---------

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
 2025-06-13 07:17:03 +05:30
Sayak Paul
648e8955cf swap out token for style bot. (#11701) 2025-06-13 06:51:19 +05:30
Sayak Paul
00b179fb1a [docs] add compilation bits to the bitsandbytes docs. (#11693) 
* add compilation bits to the bitsandbytes docs.

* Apply suggestions from code review

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

* finish

---------

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
 2025-06-12 08:49:24 +05:30
Tolga Cangöz
47ef79464f Apply Occam's Razor in position embedding calculation (#11562) 
* fix: remove redundant indexing

* style
 2025-06-11 13:47:37 -10:00
Joel Schlosser
b272807bc8 Avoid DtoH sync from access of nonzero() item in scheduler (#11696) 2025-06-11 12:03:40 -10:00
rasmi
447ccd0679 Set _torch_version to N/A if torch is disabled. (#11645) 2025-06-11 11:59:54 -10:00
Aryan
f3e09114f2 Improve Wan docstrings (#11689) 
* improve docstrings for wan

* Apply suggestions from code review

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

* make style

---------

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
 2025-06-12 01:18:40 +05:30
Sayak Paul
91545666e0 [tests] model-level device_map clarifications (#11681) 
* add clarity in documentation for device_map

* docs

* fix how compiler tester mixins are used.

* propagate

* more

* typo.

* fix tests

* fix order of decroators.

* clarify more.

* more test cases.

* fix doc

* fix device_map docstring in pipeline_utils.

* more examples

* more

* update

* remove code for stuff that is already supported.

* fix stuff.
 2025-06-11 22:41:59 +05:30
Sayak Paul
b6f7933044 [tests] tests for compilation + quantization (bnb) (#11672) 
* start adding compilation tests for quantization.

* fixes

* make common utility.

* modularize.

* add group offloading+compile

* xfail

* update

* Update tests/quantization/test_torch_compile_utils.py

Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>

* fixes

---------

Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>
 2025-06-11 21:14:24 +05:30
Yao Matrix
33e636cea5 enable torchao test cases on XPU and switch to device agnostic APIs for test cases (#11654) 
* enable torchao cases on XPU

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

* device agnostic APIs

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

* more

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

* fix style

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

* enable test_torch_compile_recompilation_and_graph_break on XPU

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

* resolve comments

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

---------

Signed-off-by: Matrix YAO <matrix.yao@intel.com>
Signed-off-by: YAO Matrix <matrix.yao@intel.com>
 2025-06-11 15:17:06 +05:30
Tolga Cangöz
e27142ac64 [Wan] Fix VAE sampling mode in WanVideoToVideoPipeline (#11639) 
* fix: vae sampling mode

* fix a typo
 2025-06-11 14:19:23 +05:30
Sayak Paul
8e88495da2 [LoRA] support Flux Control LoRA with bnb 8bit. (#11655) 
support Flux Control LoRA with bnb 8bit.
 2025-06-11 08:32:47 +05:30
Akash Haridas
b79803fe08 Allow remote code repo names to contain "." (#11652) 
* allow loading from repo with dot in name

* put new arg at the end to avoid breaking compatibility

* add test for loading repo with dot in name

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2025-06-10 13:38:54 -10:00
Meatfucker
b0f7036d9a Update pipeline_flux_inpaint.py to fix padding_mask_crop returning only the inpainted area (#11658) 
* Update pipeline_flux_inpaint.py to fix padding_mask_crop returning only the inpainted area and not the entire image.

* Apply style fixes

* Update src/diffusers/pipelines/flux/pipeline_flux_inpaint.py
 2025-06-10 13:07:22 -04:00
Philip Brown
6c7fad7ec8 Add community class StableDiffusionXL_T5Pipeline (#11626) 
* Add community class StableDiffusionXL_T5Pipeline
Will be used with base model opendiffusionai/stablediffusionxl_t5

* Changed pooled_embeds to use projection instead of slice

* "make style" tweaks

* Added comments to top of code

* Apply style fixes
 2025-06-09 15:57:51 -04:00
Dhruv Nair
5b0dab1253 Introduce DeprecatedPipelineMixin to simplify pipeline deprecation process (#11596) 
* update

* update

* update

* update

* update

* update

* update
 2025-06-09 13:03:40 +05:30
Sayak Paul
7c6e9ef425 [tests] Fix how compiler mixin classes are used (#11680) 
* fix how compiler tester mixins are used.

* propagate

* more
 2025-06-09 09:24:45 +05:30
Valeriy Sofin
f46abfe4ce fixed axes_dims_rope init (huggingface#11641) (#11678) 2025-06-09 01:16:30 +05:30
Aryan
73a9d5856f Wan VACE (#11582) 
* initial support

* make fix-copies

* fix no split modules

* add conversion script

* refactor

* add pipeline test

* refactor

* fix bug with mask

* fix for reference images

* remove print

* update docs

* update slices

* update

* update

* update example
 2025-06-06 17:53:10 +05:30
Sayak Paul
16c955c5fd [tests] add test for torch.compile + group offloading (#11670) 
* add a test for group offloading + compilation.

* tests
 2025-06-06 11:34:44 +05:30
jiqing-feng
0f91f2f6fc use deterministic to get stable result (#11663) 
* use deterministic to get stable result

Signed-off-by: jiqing-feng <jiqing.feng@intel.com>

* add deterministic for int8 test

Signed-off-by: jiqing-feng <jiqing.feng@intel.com>

---------

Signed-off-by: jiqing-feng <jiqing.feng@intel.com>
 2025-06-06 09:14:00 +05:30
Markus Pobitzer
745199a869 [examples] flux-control: use num_training_steps_for_scheduler (#11662) 
[examples] flux-control: use num_training_steps_for_scheduler in get_scheduler instead of args.max_train_steps * accelerator.num_processes

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2025-06-05 14:56:25 +05:30
Sayak Paul
0142f6f35a [chore] bring PipelineQuantizationConfig at the top of the import chain. (#11656) 
bring PipelineQuantizationConfig at the top of the import chain.
 2025-06-05 14:17:03 +05:30
Dhruv Nair
d04cd95012 [CI] Some improvements to Nightly reports summaries (#11166) 
* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* updatee

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update
 2025-06-05 13:55:01 +05:30
Steven Liu
c934720629 [docs] Model cards (#11112) 
* initial

* update

* hunyuanvideo

* ltx

* fix

* wan

* gen guide

* feedback

* feedback

* pipeline-level quant config

* feedback

* ltx
 2025-06-02 16:55:14 -07:00
Steven Liu
9f48394bf7 [docs] Caching methods (#11625) 
* cache

* feedback
 2025-06-02 10:58:47 -07:00
Sayak Paul
20273e5503 [tests] chore: rename lora model-level tests. (#11481) 
chore: rename lora model-level tests.
 2025-06-02 09:21:40 -07:00
Sayak Paul
d4dc4d7654 [chore] misc changes in the bnb tests for consistency. (#11355) 
misc changes in the bnb tests for consistency.
 2025-06-02 08:41:10 -07:00
Roy Hvaara
3a31b291f1 Use float32 RoPE freqs in Wan with MPS backends (#11643) 
Use float32 for RoPE on MPS in Wan
 2025-06-02 09:30:09 +05:30
Sayak Paul
b975bceff3 [docs] update torchao doc link (#11634) 
update torchao doc link
 2025-05-30 08:30:36 -07:00
co63oc
8183d0f16e Fix typos in strings and comments (#11476) 
* Fix typos in strings and comments

Signed-off-by: co63oc <co63oc@users.noreply.github.com>

* Update src/diffusers/hooks/hooks.py

Co-authored-by: Aryan <contact.aryanvs@gmail.com>

* Update src/diffusers/hooks/hooks.py

Co-authored-by: Aryan <contact.aryanvs@gmail.com>

* Update layerwise_casting.py

* Apply style fixes

* update

---------

Signed-off-by: co63oc <co63oc@users.noreply.github.com>
Co-authored-by: Aryan <contact.aryanvs@gmail.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
 2025-05-30 18:49:00 +05:30
Yaniv Galron
6508da6f06 typo fix in pipeline_flux.py (#11623) 2025-05-30 11:32:13 +05:30
VLT Media
d0ec6601df Bug: Fixed Image 2 Image example (#11619) 
Bug: Fixed Image 2 Image example where a PIL.Image was improperly being asked for an item via index.
 2025-05-30 11:30:52 +05:30
Yao Matrix
a7aa8bf28a enable group_offloading and PipelineDeviceAndDtypeStabilityTests on XPU, all passed (#11620) 
* enable group_offloading and PipelineDeviceAndDtypeStabilityTests on XPU,
all passed

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

* fix style

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

* fix

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

---------

Signed-off-by: Matrix YAO <matrix.yao@intel.com>
Co-authored-by: Aryan <aryan@huggingface.co>
 2025-05-30 11:30:37 +05:30
Yaniv Galron
3651bdb766 removing unnecessary else statement (#11624) 
Co-authored-by: Aryan <aryan@huggingface.co>
 2025-05-30 11:29:24 +05:30
Justin Ruan
df55f05358 Fix wrong indent for examples of controlnet script (#11632) 
fix wrong indent for training controlnet
 2025-05-29 15:26:39 -07:00
Yuanzhou Cai
89ddb6c0a4 [textual_inversion_sdxl.py] fix lr scheduler steps count (#11557) 
fix lr scheduler steps count

Co-authored-by: Linoy Tsaban <57615435+linoytsaban@users.noreply.github.com>
 2025-05-29 15:25:45 +03:00
Steven Liu
be2fb77dc1 [docs] PyTorch 2.0 (#11618) 
* combine

* Update docs/source/en/optimization/fp16.md

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

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2025-05-28 09:42:41 -07:00
Sayak Paul
54cddc1e12 [CI] fix the filename for displaying failures in lora ci. (#11600) 
fix the filename for displaying failures in lora ci.
 2025-05-27 22:27:27 -07:00
Linoy Tsaban
28ef0165b9 [Sana Sprint] add image-to-image pipeline (#11602) 
* sana sprint img2img

* fix import

* fix name

* fix image encoding

* fix image encoding

* fix image encoding

* fix image encoding

* fix image encoding

* fix image encoding

* try w/o strength

* try scaling differently

* try with strength

* revert unnecessary changes to scheduler

* revert unnecessary changes to scheduler

* Apply style fixes

* remove comment

* add copy statements

* add copy statements

* add to doc

* add to doc

* add to doc

* add to doc

* Apply style fixes

* empty commit

* fix copies

* fix copies

* fix copies

* fix copies

* fix copies

* docs

* make fix-copies.

* fix doc building error.

* initial commit - add img2img test

* initial commit - add img2img test

* fix import

* fix imports

* Apply style fixes

* empty commit

* remove

* empty commit

* test vocab size

* fix

* fix prompt missing from last commits

* small changes

* fix image processing when input is tensor

* fix order

* Apply style fixes

* empty commit

* fix shape

* remove comment

* image processing

* remove comment

* skip vae tiling test for now

* Apply style fixes

* empty commit

---------

Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: sayakpaul <spsayakpaul@gmail.com>
 2025-05-27 22:09:51 +03:00
Sayak Paul
a4da216125 [LoRA] improve LoRA fusion tests (#11274) 
* improve lora fusion tests

* more improvements.

* remove comment

* update

* relax tolerance.

* num_fused_loras as a property

Co-authored-by: BenjaminBossan <benjamin.bossan@gmail.com>

* updates

* update

* fix

* fix

Co-authored-by: BenjaminBossan <benjamin.bossan@gmail.com>

* Update src/diffusers/loaders/lora_base.py

Co-authored-by: Benjamin Bossan <BenjaminBossan@users.noreply.github.com>

---------

Co-authored-by: BenjaminBossan <benjamin.bossan@gmail.com>
Co-authored-by: Benjamin Bossan <BenjaminBossan@users.noreply.github.com>
 2025-05-27 09:02:12 -07:00
Leo Jiang
5939ace91b Adding NPU for get device function (#11617) 
* Adding device choice for npu

* Adding device choice for npu

---------

Co-authored-by: J石页 <jiangshuo9@h-partners.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2025-05-27 06:59:15 -07:00
Linoy Tsaban
cc59505e26 [training docs] smol update to README files (#11616) 
add comment to install prodigy
 2025-05-27 06:26:54 -07:00
Sayak Paul
5f5d02fbf1 Make group offloading compatible with torch.compile() (#11605) 
wip: check if we can make go compile compat
 2025-05-26 20:15:29 -07:00
Sayak Paul
53748217e6 fix security issue in build docker ci (#11614) 
* fix security issue in build docker ci

* better

* update
 2025-05-26 22:43:01 +05:30
Dhruv Nair
826f43505d Fix mixed variant downloading (#11611) 
* update

* update
 2025-05-26 21:43:48 +05:30
Sayak Paul
4af76d0d7d [tests] Changes to the torch.compile() CI and tests (#11508) 
* remove compile cuda docker.

* replace compile cuda docker path.

* better manage compilation cache.

* propagate similar to the pipeline tests.

* remove unneeded compile test.

* small.

* don't check for deleted files.
 2025-05-26 08:31:04 -07:00
kaixuanliu
b5c2050a16 Fix bug when variant and safetensor file does not match (#11587) 
* Apply style fixes

* init test

Signed-off-by: Liu, Kaixuan <kaixuan.liu@intel.com>

* adjust

Signed-off-by: Liu, Kaixuan <kaixuan.liu@intel.com>

* add the variant check when there are no component folders

Signed-off-by: Liu, Kaixuan <kaixuan.liu@intel.com>

* update related test cases

Signed-off-by: Liu, Kaixuan <kaixuan.liu@intel.com>

* update related unit test cases

Signed-off-by: Liu, Kaixuan <kaixuan.liu@intel.com>

* adjust

Signed-off-by: Liu, Kaixuan <kaixuan.liu@intel.com>

* Apply style fixes

---------

Signed-off-by: Liu, Kaixuan <kaixuan.liu@intel.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
 2025-05-26 14:18:41 +05:30