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
5,368 Commits 740 Branches 94 Tags
d63e6fccb11f1ec6e47940efb565bd8aeeda18b8
Commit Graph

5368 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Ishan Modi
d63e6fccb1 [BUG] fixed _toctree.yml alphabetical ordering (#11277) 
update
 2025-04-16 09:04:22 -07:00
Dhruv Nair
59f1b7b1c8 Hunyuan I2V fast tests fix (#11341) 
* update

* update
 2025-04-16 18:40:33 +05:30
Sayak Paul
ce1063acfa [docs] add a snippet for compilation in the auraflow docs. (#11327) 
* add a snippet for compilation in the auraflow docs.

* include speedups.
 2025-04-16 11:12:09 +05:30
Sayak Paul
7212f35de2 [single file] enable telemetry for single file loading when using GGUF. (#11284) 
* enable telemetry for single file loading when using GGUF.

* quality
 2025-04-16 08:33:52 +05:30
Sayak Paul
3252d7ad11 unpin torch versions for onnx Dockerfile (#11290) 
unpin torch versions for onnx
 2025-04-16 08:16:38 +05:30
Dhruv Nair
b316104ddd Fix Hunyuan I2V for transformers>4.47.1 (#11293) 
* update

* update
 2025-04-16 07:53:32 +05:30
Álvaro Somoza
d3b2699a7f another fix for FlowMatchLCMScheduler forgotten import (#11330) 
fix
 2025-04-15 13:53:16 -10:00
Sayak Paul
4b868f14c1 post release 0.33.0 (#11255) 
* post release

* update

* fix deprecations

* remaining

* update

---------

Co-authored-by: YiYi Xu <yixu310@gmail.com>
 2025-04-15 06:50:08 -10:00
AstraliteHeart
b6156aafe9 Rewrite AuraFlowPatchEmbed.pe_selection_index_based_on_dim to be torch.compile compatible (#11297) 
* Update pe_selection_index_based_on_dim

* Make pe_selection_index_based_on_dim work with torh.compile

* Fix AuraFlowTransformer2DModel's dpcstring default values

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2025-04-15 19:30:30 +05:30
Sayak Paul
7ecfe29160 [docs] fix hidream docstrings. (#11325) 
* fix hidream docstrings.

* fix

* empty commit
 2025-04-15 16:26:21 +05:30
Yao Matrix
7edace9a05 fix CPU offloading related fail cases on XPU (#11288) 
* fix CPU offloading related fail cases on XPU

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

* fix style

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

* Apply style fixes

* trigger tests

* test_pipe_same_device_id_offload

---------

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: hlky <hlky@hlky.ac>
 2025-04-15 09:06:56 +01:00
hlky
6e80d240d3 Fix vae.Decoder prev_output_channel (#11280) 2025-04-15 08:03:50 +01:00
Hameer Abbasi
9352a5ca56 [LoRA] Add LoRA support to AuraFlow (#10216) 
* Add AuraFlowLoraLoaderMixin

* Add comments, remove qkv fusion

* Add Tests

* Add AuraFlowLoraLoaderMixin to documentation

* Add Suggested changes

* Change attention_kwargs->joint_attention_kwargs

* Rebasing derp.

* fix

* fix

* Quality fixes.

* make style

* `make fix-copies`

* `ruff check --fix`

* Attept 1 to fix tests.

* Attept 2 to fix tests.

* Attept 3 to fix tests.

* Address review comments.

* Rebasing derp.

* Get more tests passing by copying from Flux. Address review comments.

* `joint_attention_kwargs`->`attention_kwargs`

* Add `lora_scale` property for te LoRAs.

* Make test better.

* Remove useless property.

* Skip TE-only tests for AuraFlow.

* Support LoRA for non-CLIP TEs.

* Restore LoRA tests.

* Undo adding LoRA support for non-CLIP TEs.

* Undo support for TE in AuraFlow LoRA.

* `make fix-copies`

* Sync with upstream changes.

* Remove unneeded stuff.

* Mirror `Lumina2`.

* Skip for MPS.

* Address review comments.

* Remove duplicated code.

* Remove unnecessary code.

* Remove repeated docs.

* Propagate attention.

* Fix TE target modules.

* MPS fix for LoRA tests.

* Unrelated TE LoRA tests fix.

* Fix AuraFlow LoRA tests by applying to the right denoiser layers.

Co-authored-by: AstraliteHeart <81396681+AstraliteHeart@users.noreply.github.com>

* Apply style fixes

* empty commit

* Fix the repo consistency issues.

* Remove unrelated changes.

* Style.

* Fix `test_lora_fuse_nan`.

* fix quality issues.

* `pytest.xfail` -> `ValueError`.

* Add back `skip_mps`.

* Apply style fixes

* `make fix-copies`

---------

Co-authored-by: Warlord-K <warlordk28@gmail.com>
Co-authored-by: hlky <hlky@hlky.ac>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: AstraliteHeart <81396681+AstraliteHeart@users.noreply.github.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
 2025-04-15 10:41:28 +05:30
Sayak Paul
cefa28f449 [docs] Promote AutoModel usage (#11300) 
* docs: promote the usage of automodel.

* bitsandbytes

* 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>
 2025-04-15 09:25:40 +05:30
Beinsezii
8819cda6c0 Add skrample section to community_projects.md (#11319) 
Update community_projects.md

https://github.com/huggingface/diffusers/discussions/11158#discussioncomment-12681691
 2025-04-14 12:12:59 -10:00
hlky
dcf836cf47 Use float32 on mps or npu in transformer_hidream_image's rope (#11316) 2025-04-14 20:19:21 +01:00
Álvaro Somoza
1cb73cb19f import for FlowMatchLCMScheduler (#11318) 
* add

* fix-copies
 2025-04-14 06:28:57 -10:00
Linoy Tsaban
ba6008abfe [HiDream] code example (#11317) 2025-04-14 16:19:30 +01:00
Sayak Paul
a8f5134c11 [LoRA] support more SDXL loras. (#11292) 
* support more SDXL loras.

* update

---------

Co-authored-by: hlky <hlky@hlky.ac>
 2025-04-14 17:09:59 +05:30
Fanli Lin
c7f2d239fe make KolorsPipelineFastTests::test_inference_batch_single_identical pass on XPU (#11313) 
adjust diff
 2025-04-14 11:02:02 +01:00
Yao Matrix
fa1ac50a66 make test_stable_diffusion_karras_sigmas pass on XPU (#11310) 
Signed-off-by: Matrix Yao <matrix.yao@intel.com>
 2025-04-14 08:15:38 +01:00
Yao Matrix
aa541b9fab make KandinskyV22PipelineInpaintCombinedFastTests::test_float16_inference pass on XPU (#11308) 
loose expected_max_diff from 5e-1 to 8e-1 to make
KandinskyV22PipelineInpaintCombinedFastTests::test_float16_inference
pass on XPU

Signed-off-by: Matrix Yao <matrix.yao@intel.com>
 2025-04-14 07:49:20 +01:00
Ishan Modi
f1f38ffbee [ControlNet] Adds controlnet for SanaTransformer (#11040) 
* added controlnet for sana transformer

* improve code quality

* addressed PR comments

* bug fixes

* added test cases

* update

* added dummy objects

* addressed PR comments

* update

* Forcing update

* add to docs

* code quality

* addressed PR comments

* addressed PR comments

* update

* addressed PR comments

* added proper styling

* update

* Revert "added proper styling"

This reverts commit 344ee8a701.

* manually ordered

* Apply suggestions from code review

---------

Co-authored-by: Aryan <contact.aryanvs@gmail.com>
 2025-04-13 19:19:39 +05:30
Tuna Tuncer
36538e1135 Fix incorrect tile_latent_min_width calculations (#11305) 2025-04-13 18:21:50 +05:30
Aryan
97e0ef4db4 Hidream refactoring follow ups (#11299) 
* HiDream Image

* update

* -einops

* py3.8

* fix -einops

* mixins, offload_seq, option_components

* docs

* Apply style fixes

* trigger tests

* Apply suggestions from code review

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

* joint_attention_kwargs -> attention_kwargs, fixes

* fast tests

* -_init_weights

* style tests

* move reshape logic

* update slice 😴

* supports_dduf

* 🤷🏻‍♂️

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

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

* address review comments

* update tests

* doc updates

* update

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

* Apply style fixes

---------

Co-authored-by: hlky <hlky@hlky.ac>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
 2025-04-13 09:45:19 +05:30
Adrien B
ed41db8525 Update autoencoderkl_allegro.md (#11303) 
Correction typo
 2025-04-13 09:41:30 +05:30
Nikita Starodubcev
ec0b2b3947 flow matching lcm scheduler (#11170) 
* add flow matching lcm scheduler
* stochastic sampling
* upscaling for scale-wise generation

* Apply style fixes

* Apply suggestions from code review

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

---------

Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: YiYi Xu <yixu310@gmail.com>
Co-authored-by: hlky <hlky@hlky.ac>
 2025-04-12 11:14:57 -10:00
hlky
0ef29355c9 HiDream Image (#11231) 
* HiDream Image


---------

Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Aryan <contact.aryanvs@gmail.com>
Co-authored-by: Aryan <aryan@huggingface.co>
 2025-04-11 06:31:34 -10:00
Tuna Tuncer
bc261058ee Fix incorrect tile_latent_min_width calculation in AutoencoderKLMochi (#11294) 2025-04-11 19:11:08 +05:30
Sayak Paul
7054a34978 do not use DIFFUSERS_REQUEST_TIMEOUT for notification bot (#11273) 
fix to a constant
 2025-04-11 14:19:46 +05:30
Sayak Paul
511d738121 [CI] relax tolerance for unclip further (#11268) 
relax tolerance for unclip further.
 2025-04-11 14:06:52 +05:30
Sayak Paul
ea5a6a8b7c [Tests] Cleanup lora tests utils (#11276) 
* start cleaning up lora test utils for reusability

* update

* updates

* updates
 2025-04-10 15:50:34 +05:30
hlky
b8093e6665 Fix LTX 0.9.5 single file (#11271) 2025-04-10 07:06:13 +01:00
Yuqian Hong
e121d0ef67 [BUG] Fix convert_vae_pt_to_diffusers bug (#11078) 
* fix attention

* Apply style fixes

---------

Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
 2025-04-10 06:59:45 +01:00
Yao Matrix
31c4f24fc1 make test_instant_style_multiple_masks pass on XPU (#11266) 
Signed-off-by: Matrix Yao <matrix.yao@intel.com>
 2025-04-10 06:23:00 +01:00
xieofxie
0efdf411fb add onnxruntime-qnn & onnxruntime-cann (#11269) 
Co-authored-by: hualxie <hualxie@microsoft.com>
 2025-04-10 06:00:23 +01:00
Yao Matrix
450dc48a2c make test_dict_tuple_outputs_equivalent pass on XPU (#11265) 
Signed-off-by: Matrix Yao <matrix.yao@intel.com>
 2025-04-10 05:56:28 +01:00
Yao Matrix
77b4f66b9e make test_stable_diffusion_inpaint_fp16 pass on XPU (#11264) 
Signed-off-by: Matrix Yao <matrix.yao@intel.com>
 2025-04-10 05:55:54 +01:00
Yao Matrix
68663f8a17 fix test_vanilla_funetuning failure on XPU and A100 (#11263) 
* fix test_vanilla_funetuning failure on XPU and A100

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

* change back to 5e-2

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

---------

Signed-off-by: Matrix Yao <matrix.yao@intel.com>
 2025-04-10 05:55:07 +01:00
Sayak Paul
ffda8735be [LoRA] support musubi wan loras. (#11243) 
* support musubi wan loras.

* Update src/diffusers/loaders/lora_conversion_utils.py

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

* support i2v loras from musubi too.

---------

Co-authored-by: hlky <hlky@hlky.ac>
 2025-04-10 09:50:22 +05:30
YiYi Xu
0706786e53 fix wan ftfy import (#11262) 2025-04-09 09:08:34 -10:00
Sayak Paul
5b27f8aba8 fix consisid imports (#11254) 
* fix consisid imports

* fix opencv import

* fix
 2025-04-09 18:49:32 +05:30
Sayak Paul
d1387ecee5 fix timeout constant (#11252) 
* fix timeout constant

* style

* fix
 2025-04-09 17:48:52 +05:30
Ilya Drobyshevskiy
6a7c2d0afa fix flux controlnet bug (#11152) 
Before this if txt_ids was 3d tensor, line with txt_ids[:1] concat txt_ids by batch dim. Now we first check that txt_ids is 2d tensor (or take first batch element) and then concat by token dim
 2025-04-09 13:01:07 +01:00
Dhruv Nair
edc154da09 Update Ruff to latest Version (#10919) 
* update

* update

* update

* update
 2025-04-09 16:51:34 +05:30
hlky
552cd32058 [docs] AutoModel (#11250) 
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2025-04-09 16:42:23 +05:30
Yao Matrix
c36c745ceb fix FluxReduxSlowTests::test_flux_redux_inference case failure on XPU (#11245) 
* loose test_float16_inference's tolerance from 5e-2 to 6e-2, so XPU can
pass UT

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

* fix test_pipeline_flux_redux fail on XPU

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

---------

Signed-off-by: Matrix Yao <matrix.yao@intel.com>
 2025-04-09 11:41:15 +01:00
hlky
437cb36c65 AutoModel (#11115) 
* AutoModel

* ...

* lol

* ...

* add test

* update

* make fix-copies

---------

Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>
 2025-04-09 15:20:07 +05:30
hlky
9ee3dd3862 AudioLDM2 Fixes (#11244) 2025-04-09 14:12:00 +05:30
Sayak Paul
fd02aad402 fix: SD3 ControlNet validation so that it runs on a A100. (#11238) 
* fix: SD3 ControlNet validation so that it runs on a A100.

* use backend-agnostic cache and pass devide.
 2025-04-09 12:12:53 +05:30