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
4,358 Commits 742 Branches 94 Tags
3bb1fd6fc05917ce2fc577fcda2163391c5bdcc0
Commit Graph

4358 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Ryan Dick
7ad70cee74 Model loading speed optimization (#5635) 
Move unchanging operation out of loop for speed benefit.
 2023-11-03 13:48:13 +01:00
Sayak Paul
60c5eb5877 [Easy] clean up the LCM docstrings. (#5637) 
* clean up the LCM docstrings.

* clean up

* fix: examples

* Apply suggestions from code review
 2023-11-03 12:14:48 +01:00
YiYi Xu
d122206466 fix a bug in AutoPipeline.from_pipe() when creating a controlnet pipeline from an existing controlnet (#5638) 
fix

Co-authored-by: yiyixuxu <yixu310@gmail,com>
 2023-11-03 12:14:19 +01:00
Sayak Paul
c84982a804 [Easy] Minor AnimateDiff Doc nits (#5640) 
minor
 2023-11-03 16:27:54 +05:30
Dhruv Nair
84e7bb875d Update animatediff docs to include section on Motion LoRAs (#5639) 
update animatediff docs
 2023-11-03 15:53:59 +05:30
Patrick von Platen
072e00897a [LCM] Make sure img2img works (#5632) 
* [LCM] Clean up implementations

* Add all

* correct more

* correct more

* finish

* up
 2023-11-02 19:50:47 +01:00
M. Tolga Cangöz
b91d5ddd1a [Docs] Fix typos, improve, update at Using Diffusers' Loading & Hub page (#5584) 
* Fix typos, improve, update

* Change to trending and apply some Grammarly fixes

* Grammarly fixes

* Update loading_adapters.md

* Update loading_adapters.md

* Update other-formats.md

* Update push_to_hub.md

* Update loading_adapters.md

* Update loading.md

* Update docs/source/en/using-diffusers/push_to_hub.md

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

* Update schedulers.md

* Update docs/source/en/using-diffusers/loading.md

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

* Update docs/source/en/using-diffusers/loading_adapters.md

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

* Update A1111 LoRA files part

* Update other-formats.md

---------

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
 2023-11-02 11:05:43 -07:00
Dhruv Nair
2a8cf8e39f Animatediff Proposal (#5413) 
* draft design

* clean up

* clean up

* clean up

* clean up

* clean up

* clean  up

* clean up

* clean up

* clean up

* update pipeline

* clean up

* clean up

* clean up

* add tests

* change motion block

* clean up

* clean up

* clean up

* update

* update

* update

* update

* update

* update

* update

* update

* clean up

* update

* update

* update model test

* update

* update

* update

* update

* make style

* update

* fix embeddings

* update

* merge upstream

* max fix copies

* fix bug

* fix mistake

* add docs

* update

* clean up

* update

* clean up

* clean up

* fix docstrings

* fix docstrings

* update

* update

* clean  up

* update
 2023-11-02 15:04:03 +01:00
M. Tolga Cangöz
9ced7844da [Docs] Fix typos, improve, update at Conceptual Guides page (#5585) 
* Fix typos, improve, update

* Update docs/source/en/conceptual/contribution.md

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

* Update docs/source/en/conceptual/contribution.md

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

* Update docs/source/en/conceptual/philosophy.md

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

* Update philosophy.md

* Update philosophy.md

* Update docs/source/en/conceptual/philosophy.md

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

* Update docs/source/en/using-diffusers/controlling_generation.md

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

* Update docs/source/en/using-diffusers/controlling_generation.md

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

* Remove e.g.; some Grammarly fixes

* Update docs/source/en/conceptual/philosophy.md

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

* Update contribution.md

---------

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
 2023-11-02 12:55:23 +01:00
Patrick von Platen
9723f8a557 [Tests] Fix cpu offload test (#5626) 
* fix more

* fix more
 2023-11-02 12:49:58 +01:00
Sayak Paul
b81f709fb6 [remote code] document trust remote code. (#5620) 
document trust remote code.
 2023-11-02 12:02:31 +01:00
Steven Liu
75ea54a151 [docs] Kandinsky guide (#4555) 
* kandinsky 2.1 first draft

* add kandinsky 2.2

* fix identical section headers

* try hfoptions syntax

* add img2img

* add inpaint

* add interpolate

* fix tag

* more cleanups

* typo

* update hfoptions id

* align hfoptions tags
 2023-11-01 15:36:22 -07:00
Patrick von Platen
c0f0582651 [SDXL Adapter] Revert load lora (#5615) 
* fix

* fix
 2023-11-01 22:18:58 +01:00
M. Tolga Cangöz
b81c69e489 [Docs] Fix typos, improve, update at Get Started page (#5587) 
* Fix typos, improve, update

* Update _toctree.yml

* Update docs/README.md

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

* Update docs/README.md

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

* Apply Grammarly fixes

---------

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
 2023-11-01 22:11:57 +01:00
Younes Belkada
02ba50c610 [PEFT / LoRA] Fix civitai bug when network alpha is an empty dict (#5608) 
* fix civitai bug

* add test

* up

* fix test

* added slow test.

* style

* Update src/diffusers/utils/peft_utils.py

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

* Update src/diffusers/utils/peft_utils.py

---------

Co-authored-by: Benjamin Bossan <BenjaminBossan@users.noreply.github.com>
 2023-11-01 22:08:22 +01:00
Patrick von Platen
4f2bf67355 Revert "Fix the order of width and height of original size in SDXL training script" (#5614) 
Revert "Fix the order of width and height of original size in SDXL training script (#5382)"

This reverts commit 45db049973.
 2023-11-01 22:04:47 +01:00
Chi
29cf163b95 Remove Redundant Variables from Encoder and Decoder (#5569) 
* I added a new doc string to the class. This is more flexible to understanding other developers what are doing and where it's using.

* Update src/diffusers/models/unet_2d_blocks.py

This changes suggest by maintener.

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

* Update src/diffusers/models/unet_2d_blocks.py

Add suggested text

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

* Update unet_2d_blocks.py

I changed the Parameter to Args text.

* Update unet_2d_blocks.py

proper indentation set in this file.

* Update unet_2d_blocks.py

a little bit of change in the act_fun argument line.

* I run the black command to reformat style in the code

* Update unet_2d_blocks.py

similar doc-string add to have in the original diffusion repository.

* I removed the dummy variable defined in both the encoder and decoder.

* Now, I run black package to reformat my file

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>
 2023-11-01 21:50:33 +01:00
Patrick von Platen
839c2a5ece fix 2023-11-01 21:39:30 +01:00
ilisparrow
5712c3d2ef [Core] enable lora for sdxl adapters too and add slow tests. (#5555) 
* Enable lora for sdxl adapters too.

Issue #5516

* fix: assertion values.

* Use numpy_cosine_similarity_distance on the arrays

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

* Use numpy_cosine_similarity_distance on the arrays

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

* Changed imports orders to pass tests

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

---------

Co-authored-by: Ilias A <iliasamri00@gmail.com>
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2023-11-01 21:25:38 +01:00
clarencechen
151998e1c2 Update final CPU offloading code for more diffusion pipelines (#5589) 
* Update final model offload for more pipelines

Add test to ensure all pipeline components are returned to CPU after
execution with model offloading

* Add comment to explain early UNet offload in Text-to-Video pipeline

* Style
 2023-11-01 21:22:56 +01:00
Steven Liu
d1eb14bc35 [docs] Lu lambdas (#5602) 
lu lambdas
 2023-11-01 11:47:11 -07:00
M. Tolga Cangöz
5c75a5fbc4 [Docs] Fix typos, improve, update at Tutorials page (#5586) 
* Fix typos, improve, update

* Update autopipeline.md

* Update docs/source/en/tutorials/using_peft_for_inference.md

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

* Update docs/source/en/tutorials/using_peft_for_inference.md

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

* Update docs/source/en/tutorials/using_peft_for_inference.md

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

---------

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
 2023-11-01 10:40:47 -07:00
M. Tolga Cangöz
442017ccc8 [Docs] Fix typos (#5583) 
* Add Copyright info

* Fix typos, improve, update

* Update deepfloyd_if.md

* Update ldm3d_diffusion.md

* Update opt_overview.md
 2023-10-31 10:04:08 -07:00
Dhruv Nair
f1d052c5b8 Update docker image for xformers (#5597) 
update docker image for xformers
 2023-10-31 15:02:10 +05:30
YiYi Xu
ce9484b139 fix a mistake in text2image training script for kandinsky2.2 (#5244) 
fix

Co-authored-by: yiyixuxu <yixu@Yis-MacBook-Pro.local>
 2023-10-30 23:06:16 -10:00
Jincheng Miao
ed00ead345 [Community Pipelines] add textual inversion support for stable_diffusion_ipex (#5571) 2023-10-31 11:54:16 +05:30
TimothyAlexisVass
f0b2f6ce05 Fix divide by zero RuntimeWarning (#5543) 2023-10-31 11:39:08 +05:30
Younes Belkada
32fea1cc9b [core / PEFT ]Bump transformers min version for PEFT integration (#5579) 
Update constants.py
 2023-10-30 19:35:46 +01:00
Aryan V S
bb46be2f18 Fix incorrect loading of custom pipeline (#5568) 
* update

* update

* update

* update
 2023-10-30 19:32:11 +01:00
Cheng Lu
ac7b1716b7 Stabilize DPM++, especially for SDXL and SDE-DPM++ (#5541) 
* stabilize dpmpp for sdxl by using euler at the final step

* add lu's uniform logsnr time steps

* add test

* fix check_copies

* fix tests

---------

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
 2023-10-30 06:36:53 -10:00
Peter @sHTiF Stefcek
3fc10ded00 add fix to be able use StableDiffusionXLAdapterPipeline.from_single_file (#5547) 2023-10-30 16:46:44 +01:00
Thuan H. Nguyen
5b087e82d1 Add realfill (#5456) 
* Add realfill

* Move realfill folder

* Fix some format issues
 2023-10-30 15:21:40 +01:00
Younes Belkada
8f3100db9f [PEFT / Tests] Add peft slow tests on push (#5419) 
* add peft slow tests workflow

* Update .github/workflows/push_tests.yml

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2023-10-30 14:27:00 +01:00
Patrick von Platen
3ec828d6dd Fix moved _expand_mask function (#5581) 
* finish

* finish
 2023-10-30 14:25:31 +01:00
Gabriel de Souza
9135e54e76 docs: initial pt translation (#5549) 
* docs: initial pt translation

* docs: add pt build to github workflow and fix some missing translations
 2023-10-27 10:51:35 -07:00
jiaqiw09
e140c0562e fix error reported 'find_unused_parameters' running in mutiple GPUs (#5355) 
* fix error reported 'find_unused_parameters' running in mutiple GPUs or NPUs

* fix code check of importing module by its alphabetic order

---------

Co-authored-by: jiaqiw <wangjiaqi50@huawei.com>
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>
 2023-10-27 22:49:14 +05:30
Steven Liu
595ba6f786 [docs] Internal classes API (#5513) 
* internal classes api

* add internal class overview

* fix toctree
 2023-10-27 09:48:41 -07:00
Sayak Paul
798591346d [Core] fix FreeU disable method (#5552) 
* disable freeu debug

* debug

* potentially fix.

* finish

* manually remove the spaces

* remove tab
 2023-10-27 21:29:11 +05:30
YiYi Xu
f912f39b50 correct checkpoint in kandinsky2.2 doc page (#5550) 
update checkpoint

Co-authored-by: yiyixuxu <yixu310@gmail,com>
 2023-10-27 08:49:15 +05:30
nickkolok
0d4b459be6 Update train_dreambooth.py - fix typos (#5539) 2023-10-26 13:35:05 -07:00
Patrick von Platen
cee1cd6e9c [Remote code] Add functionality to run remote models, schedulers, pipelines (#5472) 
* upload custom remote poc

* up

* make style

* finish

* better name

* Apply suggestions from code review

* Update tests/pipelines/test_pipelines.py

* more fixes

* remove ipdb

* more fixes

* fix more

* finish tests

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2023-10-26 17:11:49 +02:00
p1kit
5b448a5e5d [Tests] Optimize test configurations for faster execution (#5535) 
Optimize test configurations for faster execution
 2023-10-26 16:02:34 +05:30
Patrick von Platen
a69ebe5527 [Tests] Speed up expert of mixture tests (#5533) 
* [Tests] Speed up expert of mixture tests

* make style
 2023-10-26 09:42:27 +02:00
Chi
ce7f334472 Remove multiple if-else statement in the get_activation function. (#5446) 
* I added a new doc string to the class. This is more flexible to understanding other developers what are doing and where it's using.

* Update src/diffusers/models/unet_2d_blocks.py

This changes suggest by maintener.

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

* Update src/diffusers/models/unet_2d_blocks.py

Add suggested text

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

* Update unet_2d_blocks.py

I changed the Parameter to Args text.

* Update unet_2d_blocks.py

proper indentation set in this file.

* Update unet_2d_blocks.py

a little bit of change in the act_fun argument line.

* I run the black command to reformat style in the code

* Update unet_2d_blocks.py

similar doc-string add to have in the original diffusion repository.

* I use a lower method in the activation function.

* Replace multiple if-else statements with a dictionary of activation functions, and call one if statement to retrieve the appropriate function.

* I am using black package to reforamted my file

* I defined the ACTIVATION_FUNCTIONS variable outside of the function

* activation function variable convert to lower case

* First, I resolved the conflict issue. Then, I ran the Black package to reformat my file.

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2023-10-26 09:36:30 +05:30
Ran Ran
8959c5b9de Add from_pt flag to enable model from PT (#5501) 
* Add from_pt flag to enable model from PT

* Format the file

* Reformat the file
 2023-10-25 23:07:34 +02:00
Steven Liu
bc8a08f67c [docs] Loader docs (#5473) 
* first draft

* make fix-copies

* add peft section

* manual fix

* make fix-copies again

* manually revert changes to other files
 2023-10-25 09:45:05 -07:00
Yi-Xuan XU
dbce14da56 fix a bug on torch_dtype argument in from_single_file of ControlNetModel (#5528) 
fix wrong parameter
 2023-10-25 17:29:56 +02:00
RampagingSloth
71ad02607d Fix missing punctuation in PHILOSOPHY.md (#5530) 
Fix missing punctuation.
 2023-10-25 17:29:34 +02:00
Patrick von Platen
dd981256ad make fix-copies 2023-10-25 17:19:38 +02:00
Aryan V S
0c9f174d59 Improve typehints and docs in diffusers/models (#5391) 
* improvement: add typehints and docs to src/diffusers/models/attention_processor.py

* improvement: add typehints and docs to src/diffusers/models/vae.py

* improvement: add missing docs in src/diffusers/models/vq_model.py

* improvement: add typehints and docs to src/diffusers/models/transformer_temporal.py

* improvement: add typehints and docs to src/diffusers/models/t5_film_transformer.py

* improvement: add type hints to src/diffusers/models/unet_1d_blocks.py

* improvement: add missing type hints to src/diffusers/models/unet_2d_blocks.py

* fix: CI error (make fix-copies required)

* fix: CI error (make fix-copies required again)

---------

Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>
 2023-10-25 17:19:15 +02:00