Aryan
de7cdf6287
Merge modular diffusers with main ( #11893 )
...
* [CI] Fix big GPU test marker (#11786 )
* update
* update
* First Block Cache (#11180 )
* update
* modify flux single blocks to make compatible with cache techniques (without too much model-specific intrusion code)
* remove debug logs
* update
* cache context for different batches of data
* fix hs residual bug for single return outputs; support ltx
* fix controlnet flux
* support flux, ltx i2v, ltx condition
* update
* update
* Update docs/source/en/api/cache.md
* Update src/diffusers/hooks/hooks.py
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com >
* address review comments pt. 1
* address review comments pt. 2
* cache context refacotr; address review pt. 3
* address review comments
* metadata registration with decorators instead of centralized
* support cogvideox
* support mochi
* fix
* remove unused function
* remove central registry based on review
* update
---------
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com >
* fix
---------
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com >
2025-07-08 18:30:27 -10:00
yiyixuxu
73c5fe8bb1
Merge branch 'modular-diffusers' of github.com:huggingface/diffusers into modular-diffusers
2025-07-08 22:13:34 +02:00
yiyixuxu
595581d6ba
style
2025-07-08 22:13:00 +02:00
yiyixuxu
d27b65411e
add more docstrings + experimental marks
2025-07-08 20:23:44 +02:00
yiyixuxu
cb9dca5523
add experimental marks to all modular docs
2025-07-08 20:23:21 +02:00
YiYi Xu
79166dcb47
Merge branch 'main' into modular-diffusers
2025-07-08 05:46:01 -10:00
Sayak Paul
01240fecb0
[training ] add Kontext i2i training ( #11858 )
...
* feat: enable i2i fine-tuning in Kontext script.
* readme
* more checks.
* Apply suggestions from code review
Co-authored-by: Linoy Tsaban <57615435+linoytsaban@users.noreply.github.com >
* fixes
* fix
* add proj_mlp to the mix
* Update README_flux.md
add note on installing from commit `05e7a854d0a5661f5b433f6dd5954c224b104f0b`
* fix
* fix
---------
Co-authored-by: Linoy Tsaban <57615435+linoytsaban@users.noreply.github.com >
2025-07-08 21:04:16 +05:30
Steven Liu
ce338d4e4a
[docs] LoRA metadata ( #11848 )
...
* draft
* hub image
* update
* fix
2025-07-08 08:29:38 -07:00
yiyixuxu
f95c320467
addreess more review comments
2025-07-08 07:11:57 +02:00
yiyixuxu
59abd9514b
add link to components manager doc
2025-07-08 06:47:14 +02:00
yiyixuxu
5f3ebef0d7
update remove duplicated config for pag, and remove the description of all the guiders
2025-07-08 06:29:47 +02:00
YiYi Xu
e6ffde2936
Apply suggestions from code review
...
Co-authored-by: Aryan <aryan@huggingface.co >
2025-07-07 18:25:31 -10:00
yiyixuxu
04171c7345
Merge branch 'modular-diffusers' of github.com:huggingface/diffusers into modular-diffusers
2025-07-08 06:17:08 +02:00
Aryan
be5e10ae61
Copied-from implementation of PAG-guider ( #11882 )
...
* update
* fix
2025-07-07 18:16:52 -10:00
yiyixuxu
a2da0004ee
add a guide on components manager
2025-07-08 06:16:26 +02:00
yiyixuxu
863c7df543
components manager: use shorter ID, display id instead of name
2025-07-08 06:15:37 +02:00
Sayak Paul
bc55b631fd
[tests] remove tests for deprecated pipelines. ( #11879 )
...
* remove tests for deprecated pipelines.
* remove folders
* test_pipelines_common
2025-07-08 07:13:16 +05:30
yiyixuxu
e0083b29d5
Merge branch 'modular-diffusers' of github.com:huggingface/diffusers into modular-diffusers
2025-07-07 20:52:54 +02:00
yiyixuxu
6521f599b2
make sure modularpipeline from_pretrained works without modular_model_index
2025-07-07 20:52:37 +02:00
YiYi Xu
0fcce2acd8
Merge branch 'main' into modular-diffusers
2025-07-07 07:17:20 -10:00
Sayak Paul
15d50f16f2
[docs] fix references in flux pipelines. ( #11857 )
...
* fix references in flux.
* Update src/diffusers/pipelines/flux/pipeline_flux_kontext.py
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com >
---------
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com >
2025-07-07 22:20:34 +05:30
yiyixuxu
ceeb3c1da3
fix
2025-07-07 10:21:01 +02:00
Sayak Paul
2c30287958
[chore] deprecate blip controlnet pipeline. ( #11877 )
...
* deprecate blip controlnet pipeline.
* last_supported_version
2025-07-07 13:25:40 +05:30
yiyixuxu
0fcdd699cf
style
2025-07-07 09:55:04 +02:00
yiyixuxu
5af003a9e1
update from_componeenet, update_component
2025-07-07 09:51:04 +02:00
yiyixuxu
179d6d958b
add subfolder to push_to_hub
2025-07-07 09:50:33 +02:00
yiyixuxu
229c4b355c
add from_pretrained/save_pretrained for guider
2025-07-07 09:50:04 +02:00
yiyixuxu
0a4819a755
add sub_folder to save_pretrained() for config mixin
2025-07-07 09:49:29 +02:00
yiyixuxu
7cea9a3bb0
add a guider section on doc
2025-07-07 09:48:28 +02:00
yiyixuxu
23de59e21a
add sub_blocks for pipelineBlock
2025-07-06 06:18:34 +02:00
yiyixuxu
4f8b6f5a15
style + copy
2025-07-06 03:23:31 +02:00
yiyixuxu
63e94cbc61
resolve conflicnt
2025-07-06 02:59:32 +02:00
YiYi Xu
2c66fb3a85
Apply suggestions from code review
...
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
2025-07-05 14:26:13 -10:00
Aryan
284f827d6c
Modular custom config object serialization ( #11868 )
...
* update
* make style
2025-07-05 07:49:35 -10:00
Aryan
b750c69859
Modular Guider ConfigMixin ( #11862 )
...
* update
* update
* register to config pag
2025-07-04 17:08:05 -10:00
Aryan
13c51bb038
Modular PAG Guider ( #11860 )
...
* update
* fix
* update
2025-07-04 12:19:10 -10:00
Aryan
425a715e35
Fix Wan AccVideo/CausVid fuse_lora ( #11856 )
...
* fix
* actually, better fix
* empty commit; trigger tests again
* mark wanvace test as flaky
2025-07-04 21:10:35 +05:30
Benjamin Bossan
2527917528
FIX set_lora_device when target layers differ ( #11844 )
...
* FIX set_lora_device when target layers differ
Resolves #11833
Fixes a bug that occurs after calling set_lora_device when multiple LoRA
adapters are loaded that target different layers.
Note: Technically, the accompanying test does not require a GPU because
the bug is triggered even if the parameters are already on the
corresponding device, i.e. loading on CPU and then changing the device
to CPU is sufficient to cause the bug. However, this may be optimized
away in the future, so I decided to test with GPU.
* Update docstring to warn about device mismatch
* Extend docstring with an example
* Fix docstring
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
2025-07-04 19:26:17 +05:30
Sayak Paul
e6639fef70
[benchmarks] overhaul benchmarks ( #11565 )
...
* start overhauling the benchmarking suite.
* fixes
* fixes
* checking.
* checking
* fixes.
* error handling and logging.
* add flops and params.
* add more models.
* utility to fire execution of all benchmarking scripts.
* utility to push to the hub.
* push utility improvement
* seems to be working.
* okay
* add torchprofile dep.
* remove total gpu memory
* fixes
* fix
* need a big gpu
* better
* what's happening.
* okay
* separate requirements and make it nightly.
* add db population script.
* update secret name
* update secret.
* population db update
* disable db population for now.
* change to every monday
* Update .github/workflows/benchmark.yml
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com >
* quality improvements.
* reparate hub upload step.
* repository
* remove csv
* check
* update
* update
* threading.
* update
* update
* updaye
* update
* update
* update
* remove peft dep
* upgrade runner.
* fix
* fixes
* fix merging csvs.
* push dataset to the Space repo for analysis.
* warm up.
* add a readme
* Apply suggestions from code review
Co-authored-by: Luc Georges <McPatate@users.noreply.github.com >
* address feedback
* Apply suggestions from code review
* disable db workflow.
* update to bi weekly.
* enable population
* enable
* updaye
* update
* metadata
* fix
---------
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com >
Co-authored-by: Luc Georges <McPatate@users.noreply.github.com >
2025-07-04 11:04:17 +05:30
Aryan
8c938fb410
[docs] Add a note of _keep_in_fp32_modules ( #11851 )
...
* update
* Update docs/source/en/using-diffusers/schedulers.md
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com >
* Update schedulers.md
---------
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com >
2025-07-02 15:51:57 -07:00
Linoy Tsaban
f864a9a352
[Flux Kontext] Support Fal Kontext LoRA ( #11823 )
...
* initial commit
* initial commit
* initial commit
* fix import
* fix prefix
* remove print
* Apply style fixes
---------
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2025-07-02 16:57:08 +03:00
Vương Đình Minh
d6fa3298fa
update: FluxKontextInpaintPipeline support ( #11820 )
...
* update: FluxKontextInpaintPipeline support
* fix: Refactor code, remove mask_image_latents and ruff check
* feat: Add test case and fix with pytest
* Apply style fixes
* copies
---------
Co-authored-by: YiYi Xu <yixu310@gmail.com >
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2025-07-01 23:34:27 -10:00
Sayak Paul
6f1d6694df
[lora] tests for exclude_modules with Wan VACE ( #11843 )
...
* wan vace.
* update
* update
* import problem
2025-07-02 14:23:26 +05:30
Ju Hoon Park
0e95aa853e
[From Single File] support from_single_file method for WanVACE3DTransformer ( #11807 )
...
* add `WandVACETransformer3DModel` in`SINGLE_FILE_LOADABLE_CLASSES`
* add rename keys for `VACE`
add rename keys for `VACE`
* fix typo
Sincere thanks to @nitinmukesh 🙇♂️
* support for `1.3B VACE` model
Sincere thanks to @nitinmukesh again🙇♂️
* update
* update
* Apply style fixes
---------
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com >
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2025-07-02 05:55:36 +02:00
Luo Yihang
5ef74fd5f6
fix norm not training in train_control_lora_flux.py ( #11832 )
2025-07-01 17:37:54 -10:00
Steven Liu
64a9210315
[docs] Deprecated pipelines ( #11838 )
...
add warning
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
2025-07-01 14:02:54 -10:00
Steven Liu
d31b8cea3e
[docs] Batch generation ( #11841 )
...
* draft
* fix
* fix
* feedback
* feedback
2025-07-01 17:00:20 -07:00
Mikko Tukiainen
62e847db5f
Use real-valued instead of complex tensors in Wan2.1 RoPE ( #11649 )
...
* use real instead of complex tensors in Wan2.1 RoPE
* remove the redundant type conversion
* unpack rotary_emb
* register rotary embedding frequencies as non-persistent buffers
* Apply style fixes
---------
Co-authored-by: Aryan <aryan@huggingface.co >
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2025-07-01 13:57:19 -10:00
Sayak Paul
470458623e
[docs] fix single_file example. ( #11847 )
...
fix single_file example.
2025-07-01 21:23:27 +05:30
Aryan
a79c3af6bb
[single file] Cosmos ( #11801 )
...
* update
* update
* update docs
2025-07-01 18:02:58 +05:30