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
4,989 Commits 742 Branches 94 Tags
83ba01a38d94466ab16ab99c0d2bd74e463561de
Commit Graph

4989 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Linoy Tsaban
83ba01a38d small readme changes for advanced training examples (#10473) 
add to readme about hf login and wandb installation to address https://github.com/huggingface/diffusers/issues/10142#issuecomment-2571655570

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2025-01-10 07:35:19 +05:30
Zehuan Huang
7116fd24e5 Support pass kwargs to cogvideox custom attention processor (#10456) 
* Support pass kwargs to cogvideox custom attention processor

* remove args in cogvideox attn processor

* remove unused kwargs
 2025-01-09 11:57:03 -10:00
Sayak Paul
553b13845f [LoRA] clean up load_lora_into_text_encoder() and fuse_lora() copied from (#10495) 
* factor out text encoder loading.

* make fix-copies

* remove copied from fuse_lora and unfuse_lora as needed.

* remove unused imports
 2025-01-09 11:29:16 -10:00
chaowenguo
7bc8b92384 add callable object to convert frame into control_frame to reduce cpu memory usage. (#10501) 
* Update rerender_a_video.py

* Update rerender_a_video.py

* Update examples/community/rerender_a_video.py

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

---------

Co-authored-by: hlky <hlky@hlky.ac>
Co-authored-by: YiYi Xu <yixu310@gmail.com>
 2025-01-09 11:25:53 -10:00
Vladimir Mandic
f0c6d9784b flux: make scheduler config params optional (#10384) 
* dont assume scheduler has optional config params

* make style, make fix-copies

* calculate_shift

* fix-copies, usage in pipelines

---------

Co-authored-by: hlky <hlky@hlky.ac>
 2025-01-09 10:44:26 -10:00
Steven Liu
d006f0769b [docs] Fix missing parameters in docstrings (#10419) 
* fix docstrings

* add
 2025-01-09 10:54:39 -08:00
geronimi73
a26d57097a AutoModel instead of AutoModelForCausalLM (#10507) 2025-01-09 16:28:04 +05:30
Sayak Paul
daf9d0f119 [chore] remove prints from tests. (#10505) 
remove prints from tests.
 2025-01-09 14:19:43 +05:30
hlky
95c5ce4e6f PyTorch/XLA support (#10498) 
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2025-01-08 12:31:27 -10:00
Junsong Chen
c0964571fc [Sana 4K] (#10493) 
add 4K support for Sana
 2025-01-08 11:58:11 -10:00
hlky
b13cdbb294 UNet2DModel mid_block_type (#10469) 2025-01-08 10:50:29 -10:00
Bagheera
a0acbdc989 fix for #7365, prevent pipelines from overriding provided prompt embeds (#7926) 
* fix for #7365, prevent pipelines from overriding provided prompt embeds

* fix-copies

* fix implementation

* update

---------

Co-authored-by: bghira <bghira@users.github.com>
Co-authored-by: Aryan <aryan@huggingface.co>
Co-authored-by: sayakpaul <spsayakpaul@gmail.com>
 2025-01-08 10:12:12 -10:00
Parag Ekbote
5655b22ead Notebooks for Community Scripts-5 (#10499) 
Add 5 Notebooks for Diffusers Community
Pipelines.
 2025-01-08 08:56:17 -08:00
hlky
4df9d49218 Fix tokenizers install from main in LoRA tests (#10494) 
* Fix tokenizers install from main in LoRA tests

* @

* rust

* -e

* uv

* just update tokenizers
 2025-01-08 16:14:25 +00:00
Dhruv Nair
9731773d39 [CI] Torch Min Version Test Fix (#10491) 
update
 2025-01-08 19:43:38 +05:30
Marc Sun
e2deb82e69 Fix compatibility with pipeline when loading model with device_map on single gpu (#10390) 
* fix device issue in single gpu case

* Update src/diffusers/pipelines/pipeline_utils.py

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

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2025-01-08 11:35:00 +01:00
hlky
1288c8560a Update tokenizers in pr_test_peft_backend (#10132) 
Update tokenizers
 2025-01-08 10:09:32 +00:00
AstraliteHeart
cb342b745a Add AuraFlow GGUF support (#10463) 
* Add support for loading AuraFlow models from GGUF

https://huggingface.co/city96/AuraFlow-v0.3-gguf

* Update AuraFlow documentation for GGUF, add GGUF tests and model detection.

* Address code review comments.

* Remove unused config.

---------

Co-authored-by: hlky <hlky@hlky.ac>
 2025-01-08 13:23:12 +05:30
Junsong Chen
80fd9260bb [Sana][bug fix]change clean_caption from True to False. (#10481) 
change clean_caption from True to False.
 2025-01-07 15:31:23 -10:00
Aryan
71ad16b463 Add _no_split_modules to some models (#10308) 
* set supports gradient checkpointing to true where necessary; add missing no split modules

* fix cogvideox tests

* update

---------

Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>
 2025-01-08 06:34:19 +05:30
hlky
ee7e141d80 Use pipelines without vae (#10441) 
* Use pipelines without vae

* getattr

* vqvae

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2025-01-07 13:26:51 -10:00
hlky
01bd79649e Fix HunyuanVideo produces NaN on PyTorch<2.5 (#10482) 
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2025-01-07 13:13:55 -10:00
Teriks
03bcf5aefe RFInversionFluxPipeline, small fix for enable_model_cpu_offload & enable_sequential_cpu_offload compatibility (#10480) 
RFInversionFluxPipeline.encode_image, device fix

Use self._execution_device instead of self.device when selecting
a device for the input image tensor.

This allows for compatibility with enable_model_cpu_offload &
enable_sequential_cpu_offload

Co-authored-by: Teriks <Teriks@users.noreply.github.com>
Co-authored-by: Linoy Tsaban <57615435+linoytsaban@users.noreply.github.com>
 2025-01-07 15:47:28 +01:00
dependabot[bot]
e0b96ba7b0 Bump jinja2 from 3.1.4 to 3.1.5 in /examples/research_projects/realfill (#10377) 
Bumps [jinja2](https://github.com/pallets/jinja) from 3.1.4 to 3.1.5.
- [Release notes](https://github.com/pallets/jinja/releases)
- [Changelog](https://github.com/pallets/jinja/blob/main/CHANGES.rst)
- [Commits](https://github.com/pallets/jinja/compare/3.1.4...3.1.5)

---
updated-dependencies:
- dependency-name: jinja2
  dependency-type: direct:production
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
 2025-01-07 19:59:41 +05:30
Dhruv Nair
854a04659c [CI] Add minimal testing for legacy Torch versions (#10479) 
* update

* update
 2025-01-07 18:51:41 +05:30
hlky
628f2c544a Use Pipelines without scheduler (#10439) 
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2025-01-07 12:07:08 +00:00
Aryan
811560b1d7 [LoRA] Support original format loras for HunyuanVideo (#10376) 
* update

* fix make copies

* update

* add relevant markers to the integration test suite.

* add copied.

* fox-copies

* temporarily add print.

* directly place on CUDA as CPU isn't that big on the CIO.

* fixes to fuse_lora, aryan was right.

* fixes

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2025-01-07 13:18:57 +05:30
Rahul Raman
f1e0c7ce4a Refactor instructpix2pix lora to support peft (#10205) 
* make base code changes referred from train_instructpix2pix script in examples

* change code to use PEFT as discussed in issue 10062

* update README training command

* update README training command

* refactor variable name and freezing unet

* Update examples/research_projects/instructpix2pix_lora/train_instruct_pix2pix_lora.py

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

* update README installation instructions.

* cleanup code using make style and quality

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2025-01-07 12:00:45 +05:30
Sayak Paul
b94cfd7937 [Training] QoL improvements in the Flux Control training scripts (#10461) 
* qol improvements to the Flux script.

* propagate the dataloader changes.
 2025-01-07 11:56:17 +05:30
Aryan
661bde0ff2 Fix style (#10478) 
fix
 2025-01-07 11:06:36 +05:30
Ameer Azam
4f5e3e35d2 Regarding the RunwayML path for V1.5 did change to stable-diffusion-v1-5/[stable-diffusion-v1-5/ stable-diffusion-inpainting] (#10476) 
* Update pipeline_controlnet.py

* Update pipeline_controlnet_img2img.py

runwayml Take-down so change all from to this
stable-diffusion-v1-5/stable-diffusion-v1-5

* Update pipeline_controlnet_inpaint.py

* runwayml take-down make change to sd-legacy

* runwayml take-down make change to sd-legacy

* runwayml take-down make change to sd-legacy

* runwayml take-down make change to sd-legacy

* Update convert_blipdiffusion_to_diffusers.py

style change
 2025-01-06 15:01:52 -08:00
hlky
8f2253c58c Add torch_xla and from_single_file to instruct-pix2pix (#10444) 
* Add torch_xla and from_single_file to instruct-pix2pix

* StableDiffusionInstructPix2PixPipelineSingleFileSlowTests

* StableDiffusionInstructPix2PixPipelineSingleFileSlowTests

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: YiYi Xu <yixu310@gmail.com>
 2025-01-06 10:11:16 -10:00
Aryan
7747b588e2 Fix hunyuan video attention mask dim (#10454) 
* fix

* add coauthor

Co-Authored-By: Nerogar <nerogar@arcor.de>

---------

Co-authored-by: Nerogar <nerogar@arcor.de>
 2025-01-06 10:07:54 -10:00
Sayak Paul
d9d94e12f3 [LoRA] fix: lora unloading when using expanded Flux LoRAs. (#10397) 
* fix: lora unloading when using expanded Flux LoRAs.

* fix argument name.

Co-authored-by: a-r-r-o-w <contact.aryanvs@gmail.com>

* docs.

---------

Co-authored-by: a-r-r-o-w <contact.aryanvs@gmail.com>
 2025-01-06 08:35:05 -10:00
hlky
2f25156c14 LEditsPP - examples, check height/width, add tiling/slicing (#10471) 
* LEditsPP - examples, check height/width, add tiling/slicing

* make style
 2025-01-06 08:19:53 -10:00
SahilCarterr
6da6406529 [Fix] broken links in docs (#10434) 
* Fix broken links in docs

* fix parenthesis
 2025-01-06 10:07:38 -08:00
Aryan
04e783cd9e Update variable names correctly in docs (#10435) 
fix
 2025-01-06 08:56:43 -08:00
hlky
1896b1f7c1 lora_bias PEFT version check in unet.load_attn_procs (#10474) 
`lora_bias` PEFT version check in `unet.load_attn_procs` path
 2025-01-06 21:27:56 +05:30
Sayak Paul
b5726358cf [Tests] add slow and nightly markers to sd3 lora integation. (#10458) 
add slow and nightly markers to sd3 lora integation.
 2025-01-06 07:29:04 +05:30
hlky
fdcbbdf0bb Add torch_xla and from_single_file support to TextToVideoZeroPipeline (#10445) 
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2025-01-05 05:24:28 +00:00
chaowenguo
4e44534845 Update rerender_a_video.py fix dtype error (#10451) 
Update rerender_a_video.py
 2025-01-04 14:52:50 +00:00
chaowenguo
a17832b2d9 add pythor_xla support for render a video (#10443) 
* Update rerender_a_video.py

* Update rerender_a_video.py

* make style

---------

Co-authored-by: hlky <hlky@hlky.ac>
 2025-01-03 16:00:02 +00:00
hlky
c28db0aa5b Fix AutoPipeline from_pipe where source pipeline is missing target pipeline's optional components (#10400) 
* Optional components in AutoPipeline

* missing_modules

---------

Co-authored-by: YiYi Xu <yixu310@gmail.com>
 2025-01-02 11:06:51 -10:00
Doug J
f7822ae4bf Update train_text_to_image_sdxl.py (#8830) 
Enable VAE hash to be able to change with args change. If not, train_dataset_with_embeddiings may have row number inconsistency with train_dataset_with_vae.

Co-authored-by: Linoy Tsaban <57615435+linoytsaban@users.noreply.github.com>
 2025-01-02 10:41:18 -10:00
Steven Liu
d81cc6f1da [docs] Fix internal links (#10418) 
fix links

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2025-01-02 10:11:16 -10:00
Aryan
476795c5c3 Update Flux docstrings (#10423) 
update
 2025-01-02 10:06:18 -10:00
Sayak Paul
3cb66865f7 [LTX-Video] fix attribute adjustment for ltx. (#10426) 
fix attribute adjustment for ltx.
 2025-01-02 10:05:41 -10:00
Daniel Regado
68bd6934b1 IP-Adapter support for StableDiffusion3ControlNetPipeline (#10363) 
* IP-Adapter support for `StableDiffusion3ControlNetPipeline`

* Update src/diffusers/pipelines/controlnet_sd3/pipeline_stable_diffusion_3_controlnet.py

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

---------

Co-authored-by: hlky <hlky@hlky.ac>
 2025-01-02 10:02:32 -10:00
G.O.D
f4fdb3a0ab fix bug for ascend npu (#10429) 2025-01-02 09:52:53 -10:00
Junsong Chen
7ab7c12173 [Sana] 1k PE bug fixed (#10431) 
fix pe bug for Sana

Co-authored-by: YiYi Xu <yixu310@gmail.com>
 2025-01-02 09:50:51 -10:00