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
3,762 Commits 740 Branches 94 Tags
f57e7bd92c57bf59cba45496fc85ea77797bedcc
Commit Graph

3762 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Suraj Patil
f57e7bd92c Add EDMEulerScheduler (#7109) 
* Add EDMEulerScheduler

* address review comments

* fix import

* fix test

* add tests

* add co-author

Co-authored-by:  @dg845 dgu8957@gmail.com
 2024-02-27 17:51:19 +05:30
Sayak Paul
3e3d46924b [Dockerfile] remove uv from docker jax tpu (#7115) 
remove uv from docker jax tpu
 2024-02-27 16:25:50 +05:30
Suraj Patil
d71ecad8cd denormalize latents with the mean and std if available (#7111) 
* denormalize latents with the mean and std if available

* fix denormalize

* add latent mean and std in vae config

* address sayak's comment
 2024-02-27 16:20:05 +05:30
Dhruv Nair
ac49f97a75 Add tests to check configs when using single file loading (#7099) 
* update

* update

* update

* update

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-02-27 15:47:23 +05:30
Sayak Paul
04bafcbbc2 move to uv in the Dockerfiles. (#7094) 
move to uv in the Dockerfiles.
 2024-02-27 15:11:28 +05:30
Sayak Paul
7081a25618 [Examples] Multiple enhancements to the ControlNet training scripts (#7096) 
* log_validation unification for controlnet.

* additional fixes.

* remove print.

* better reuse and loading

* make final inference run conditional.

* Update examples/controlnet/README_sdxl.md

Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

* resize the control image in the snippet.

---------

Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
 2024-02-27 09:18:46 +05:30
Sayak Paul
848f9fe6ce [Core] pass revision in the loading_kwargs. (#7019) 
* pass revision in the loading_kwarhs.

* remove revision from load_sub_model.
 2024-02-27 08:52:38 +05:30
Younes Belkada
8a692739c0 FIX [PEFT / Core] Copy the state dict when passing it to load_lora_weights (#7058) 
* copy the state dict in load lora weights

* fixup
 2024-02-27 02:42:23 +01:00
Sayak Paul
5aa31bd674 [Easy] edit issue and PR templates (#7092) 
edit templates to remove patrick's name.
 2024-02-27 07:10:03 +05:30
jinghuan-Chen
88aa7f6ebf Make LoRACompatibleConv padding_mode work. (#6031) 
* Make LoRACompatibleConv padding_mode work.

* Format code style.

* add fast test

* Update src/diffusers/models/lora.py

Simplify the code by patrickvonplaten.

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* code refactor

* apply patrickvonplaten suggestion to simplify the code.

* rm test_lora_layers_old_backend.py and add test case in test_lora_layers_peft.py

* update test case.

---------

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: YiYi Xu <yixu310@gmail.com>
 2024-02-26 14:05:13 -10:00
M. Tolga Cangöz
ad310af0d6 Fix EMA in train_text_to_image_sdxl.py (#7048) 
* Fix typos
 2024-02-26 10:39:57 -10:00
Dhruv Nair
d603ccb614 Small change to download in dance diffusion convert script (#7070) 
* update

* make style
 2024-02-26 12:05:19 +05:30
jiqing-feng
fd0f469568 Resize image before crop (#7095) 
resize first

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-02-26 11:14:08 +05:30
Stephen
ae84e405a3 Pass use_linear_projection parameter to mid block in UNetMotionModel (#7035) 
* pass linear projection parameter to mid block

* add cond_proj_dim to motion UNet

* run style and quality checks
 2024-02-26 10:49:14 +05:30
Aryan
3a66113306 [Community] Bug fix + Latest IP-Adapter impl. for AnimateDiff img2vid/controlnet (#7086) 
* fix img2vid; update to latest ip-adapter impl

* update README

* update animatediff controlnet to latest impl
 2024-02-26 10:27:42 +05:30
Vinh H. Pham
7f16187182 Modularize Dreambooth LoRA SDXL inferencing during and after training (#6655) 
* modularize log validation

* run make style

* revert import wandb

* fix code quality & import wandb

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-02-26 09:53:12 +05:30
Vinh H. Pham
f11b922b4f Modularize Dreambooth LoRA SD inferencing during and after training (#6654) 
* modulize log validation

* run make style and refactor wanddb support

* remove redundant initialization

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-02-26 09:01:39 +05:30
Steven Liu
3dd4168d4c [docs] Minor updates (#7063) 
* updates

* feedback
 2024-02-25 09:38:02 -08:00
Fabio Rigano
1c47d1fc05 Fix head_to_batch_dim for IPAdapterAttnProcessor (#7077) 
* Fix IPAdapterAttnProcessor

* Fix batch_to_head_dim and revert reshape
 2024-02-25 00:05:46 -10:00
Aryan
bbf70c8739 Fix truthy-ness condition in pipelines that use denoising_start (#6912) 
* fix denoising start

* fix tests

* remove debug
 2024-02-24 23:39:22 -10:00
M. Tolga Cangöz
738c986957 [Refactor] StableDiffusionReferencePipeline inheriting from DiffusionPipeline (#7071) 
Refactor StableDiffusionReferencePipeline to inherit from DiffusionPipeline rather than StableDiffusionPipeline
 2024-02-23 22:04:31 -10:00
caiyueliang
c09bb588d3 fix: TensorRTStableDiffusionPipeline cannot set guidance_scale (#7065) 2024-02-23 14:59:02 -10:00
bimsarapathiraja
66a7160f9d Change images to image. The variable images is not used anywhere (#7074) 2024-02-23 10:40:21 -10:00
Chong-U Lim
f05ee56b2f Fix docstring of community pipeline imagic (#7062) 2024-02-23 09:37:52 -08:00
M. Tolga Cangöz
34cc7f9b98 Fix typos (#7068) 2024-02-23 09:24:51 -08:00
M. Tolga Cangöz
53605ed00a [Refactor] save_model_card function in text_to_image examples (#7051) 
* Refactor save_model_card function to handle images and repo_folder parameters

* Discard changes to examples/text_to_image/train_text_to_image.py

* Discard changes to examples/text_to_image/train_text_to_image_lora_sdxl.py

* Update train_text_to_image_lora.py

* Update train_text_to_image_sdxl.py
 2024-02-23 20:57:37 +05:30
Aryan
bb1b76d3bf IPAdapterTesterMixin (#6862) 
* begin IPAdapterTesterMixin



---------

Co-authored-by: YiYi Xu <yixu310@gmail.com>
 2024-02-22 14:25:33 -10:00
YiYi Xu
e4b8f173b9 re-add unet refactor PR (#7044) 
* add

* remove copied from

---------

Co-authored-by: ultranity <1095429904@qq.com>
Co-authored-by: yiyixuxu <yixu310@gmail,com>
 2024-02-21 22:00:32 -10:00
Hezi Zisman
f0216b7756 allow explicit tokenizer & text_encoder in unload_textual_inversion (#6977) 
* allow passing tokenizer & text_encoder to unload_textual_inversion


---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: YiYi Xu <yixu310@gmail.com>
Co-authored-by: Fabio Rigano <fabio2rigano@gmail.com>
Co-authored-by: Linoy Tsaban <57615435+linoytsaban@users.noreply.github.com>
 2024-02-21 16:53:25 -10:00
Lincoln Stein
d5f444de4b Update checkpoint_merger pipeline to pass the "variant" argument (#6670) 
* make checkpoint_merger pipeline pass the "variant" argument to from_pretrained()

* make style

---------

Co-authored-by: Lincoln Stein <lstein@gmail.com>
Co-authored-by: YiYi Xu <yixu310@gmail.com>
 2024-02-21 15:45:50 -10:00
M. Tolga Cangöz
5a54dc9e95 Fix typos in text_to_image examples (#7050) 
Update copyright information and fix typos in text_to_image examples
 2024-02-21 16:40:45 -08:00
YiYi Xu
6fedbd850a fix doc example for fom_single_file (#7015) 
* fix doc

* remove use_safetensors from signature

* more

---------

Co-authored-by: yiyixuxu <yixu310@gmail,com>
 2024-02-21 19:11:21 +05:30
pravdomil
1b3cfb1b10 update header (#6596) 
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
 2024-02-20 10:09:15 -08:00
Dhruv Nair
af13a90ebd Remove disable_full_determinism from StableVideoDiffusion xformers test. (#7039) 
* update

* update
 2024-02-20 21:43:23 +05:30
Dhruv Nair
3067da1261 Fix load_model_dict_into_meta for ControlNet from_single_file (#7034) 
update
 2024-02-20 11:01:02 +05:30
Dhruv Nair
6bceaea3fe Update ControlNet Inpaint single file test (#7022) 
update
 2024-02-20 10:58:30 +05:30
Dhruv Nair
baf9924be7 Fix alt text and image links in AnimateLCM docs (#7029) 
update
 2024-02-20 08:30:44 +05:30
Nontapat Kaewamporn
d8d208acde Supper IP Adapter weight loading in StableDiffusionXLControlNetInpaintPipeline (#7031) 
* support ip adapter loading

* fix style
 2024-02-19 09:44:35 -10:00
Vinh H. Pham
e0f33dfca4 IP-Adapter support for StableDiffusionXLControlNetInpaintPipeline (#6941) 
* add ip-adapter support

* support ip image embeds

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-02-19 08:20:24 -10:00
Dhruv Nair
15b125bb0e Add section on AnimateLCM to docs (#7024) 
* update

* update

* update
 2024-02-19 22:20:37 +05:30
ustcuna
12004bf3a7 [Community Pipelines]Accelerate inference of stable diffusion xl (SDXL) by IPEX on CPU (#6683) 
* add stable_diffusion_xl_ipex community pipeline

* make style for code quality check

* update docs as suggested

---------

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
 2024-02-19 13:39:08 +01:00
Dhruv Nair
d2fc5ebb95 [Refactor] FreeInit for AnimateDiff based pipelines (#6874) 
* update

* update

* update

* update

* update

* update

* update

* update

* update

* update
 2024-02-19 11:11:42 +05:30
YiYi Xu
779eef95b4 [from_single_file] pass torch_dtype to set_module_tensor_to_device (#6994) 
fix

Co-authored-by: yiyixuxu <yixu310@gmail,com>
 2024-02-19 10:09:19 +05:30
Dhruv Nair
d5b8d1ca04 Fix Pixart Slow Tests (#6962) 
* update

* update
 2024-02-19 09:50:18 +05:30
Fabio Rigano
eba7e7a6d7 IP-Adapter attention masking (#6847) 
* Add attention masking to attn processors

* Update tensor conversion

---------

Co-authored-by: YiYi Xu <yixu310@gmail.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-02-18 18:06:14 -10:00
Sayak Paul
31de879fb4 [IP2P] Make text encoder truly optional in InstructPi2Pix (#6995) 
* make text encoder component truly optional.

* more fixes

* Apply suggestions from code review

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

---------

Co-authored-by: YiYi Xu <yixu310@gmail.com>
 2024-02-18 20:21:22 +05:30
nbpppp
07349c25fe Fix deprecation warning for torch.utils._pytree._register_pytree_node in PyTorch 2.2 (#7008) 
Fixed deprecation warning for torch.utils._pytree._register_pytree_node in PyTorch 2.2

Co-authored-by: Yinghua <yzho0423@uni.sydney.edu.au>
 2024-02-18 20:11:33 +05:30
YiYi Xu
8974c50bff [SVD] fix a bug when passing image as tensor (#6999) 
* fix

* update docstring

---------

Co-authored-by: yiyixuxu <yixu310@gmail,com>
 2024-02-17 23:10:31 -10:00
Mikhail Koltakov
c18058b405 Fixed typos in dosctrings of __init__() and in forward() of Unet3DConditionModel (#6663) 
* Fixed typos in __init__ and in forward of Unet3DConditionModel

* Resolving conflicts

---------

Co-authored-by: YiYi Xu <yixu310@gmail.com>
 2024-02-17 21:56:16 -10:00
Thomas Lips
2938d5a672 Add documentation for strength parameter in Controlnet_img2img pipelines (#6951) 
copy docstring for `strength` from  stablediffusion img2img pipeline to controlnet img2img pipelines
 2024-02-17 21:47:02 -10:00