obscura/diffusers
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
4,540 Commits 711 Branches 93 Tags
e2ead7cdcc00859533e6bec7b0707a6fb0efef0a
Commit Graph

4540 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Leo Jiang e2ead7cdcc Fix the issue on sd3 dreambooth w./w.t. lora training (#9419) 
* Fix dtype error

* [bugfix] Fixed the issue on sd3 dreambooth training

* [bugfix] Fixed the issue on sd3 dreambooth training

---------

Co-authored-by: 蒋硕 <jiangshuo9@h-partners.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-09-14 16:29:38 +05:30
Benjamin Bossan 48e36353d8 MAINT Permission for GH token in stale.yml (#9427) 
* MAINT Permission for GH token in stale.yml

See https://github.com/huggingface/peft/pull/2061 for the equivalent PR
in PEFT.

This restores the functionality of the stale bot after permissions for
the token have been limited. The action still shows errors for PEFT but
the bot appears to work fine.

* Also add write permissions for PRs

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-09-13 21:00:57 +05:30
Sayak Paul 6dc6486565 [LoRA] fix adapter movement when using DoRA. (#9411) 
fix adapter movement when using DoRA.
 2024-09-13 07:31:53 +05:30
Dhruv Nair 1e8cf2763d [CI] Nightly Test Updates (#9380) 
* update

* update

* update

* update

* update

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: YiYi Xu <yixu310@gmail.com>
 2024-09-12 20:21:28 +05:30
Sayak Paul 6cf8d98ce1 [CI] update artifact uploader version (#9426) 
update artifact uploader version
 2024-09-12 19:26:09 +05:30
Juan Acevedo 45aa8bb187 Ptxla sd training (#9381) 
* enable pxla training of stable diffusion 2.x models.

* run linter/style and run pipeline test for stable diffusion and fix issues.

* update xla libraries

* fix read me newline.

* move files to research folder.

* update per comments.

* rename readme.

---------

Co-authored-by: Juan Acevedo <jfacevedo@google.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-09-12 08:35:06 +05:30
Aryan 5e1427a7da [docs] AnimateDiff FreeNoise (#9414) 
* update docs

* apply suggestions from review

* Update docs/source/en/api/pipelines/animatediff.md

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

* Update docs/source/en/api/pipelines/animatediff.md

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

* Update docs/source/en/api/pipelines/animatediff.md

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

* apply suggestions from review

---------

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
 2024-09-11 12:59:58 -07:00
asfiyab-nvidia b9e2f886cd FluxPosEmbed: Remove Squeeze No-op (#9409) 
Remove Squeeze op

Signed-off-by: Asfiya Baig <asfiyab@nvidia.com>
Co-authored-by: YiYi Xu <yixu310@gmail.com>
 2024-09-10 19:12:36 -10:00
dianyo b19827f6b4 Migrate the BrownianTree to BrownianInterval in DPM solver (#9335) 
migrate the BrownianTree to BrownianInterval

Co-authored-by: YiYi Xu <yixu310@gmail.com>
 2024-09-10 18:29:15 -10:00
Yu Zheng c002731d93 [examples] add controlnet sd3 example (#9249) 
* add controlnet sd3 example

* add controlnet sd3 example

* update controlnet sd3 example

* add controlnet sd3 example test

* fix quality and style

* update test

* update test

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-09-11 07:04:37 +05:30
Sayak Paul adf1f911f0 [Tests] fix some fast gpu tests. (#9379) 
fix some fast gpu tests.
 2024-09-11 06:50:02 +05:30
captainzz f28a8c257a fix from_transformer() with extra conditioning channels (#9364) 
* fix from_transformer() with extra conditioning channels

* style fix

---------

Co-authored-by: YiYi Xu <yixu310@gmail.com>
Co-authored-by: Álvaro Somoza <somoza.alvaro@gmail.com>
 2024-09-09 07:51:48 -10:00
Jinzhe Pan 2c6a6c97b3 [docs] Add xDiT in section optimization (#9365) 
* docs: add xDiT to optimization methods

* fix: picture layout problem

* docs: add more introduction about xdit & apply suggestions

* 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>
 2024-09-09 10:31:07 -07:00
Igor Filippov a7361dccdc [Pipeline] animatediff + vid2vid + controlnet (#9337) 
* add animatediff + vid2vide + controlnet

* post tests fixes

* PR discussion fixes

* update docs

* change input video to links on HF + update an example

* make quality fix

* fix ip adapter test

* fix ip adapter test input

* update ip adapter test
 2024-09-09 22:48:21 +05:30
YiYi Xu 485b8bb000 refactor get_timesteps for SDXL img2img + add set_begin_index (#9375) 
* refator + add begin_index

* add kolors img2img to doc
 2024-09-09 06:38:22 -10:00
Sayak Paul d08ad65819 modify benchmarks to replace sdv1.5 with dreamshaper. (#9334) 2024-09-09 20:54:56 +05:30
YiYi Xu 8cdcdd9e32 add flux inpaint + img2img + controlnet to auto pipeline (#9367) 2024-09-06 07:14:48 -10:00
Dhruv Nair d269cc8a4e [CI] Quick fix for Cog Video Test (#9373) 
update
 2024-09-06 15:25:53 +05:30
Aryan 6dfa49963c [core] Freenoise memory improvements (#9262) 
* update

* implement prompt interpolation

* make style

* resnet memory optimizations

* more memory optimizations; todo: refactor

* update

* update animatediff controlnet with latest changes

* refactor chunked inference changes

* remove print statements

* update

* chunk -> split

* remove changes from incorrect conflict resolution

* remove changes from incorrect conflict resolution

* add explanation of SplitInferenceModule

* update docs

* Revert "update docs"

This reverts commit c55a50a271.

* update docstring for freenoise split inference

* apply suggestions from review

* add tests

* apply suggestions from review
 2024-09-06 12:51:20 +05:30
Haruya Ishikawa 5249a2666e fix one uncaught deprecation warning for accessing vae_latent_channels in VaeImagePreprocessor (#9372) 
deprecation warning vae_latent_channels
 2024-09-05 07:32:27 -10:00
Linoy Tsaban 55ac421f7b improve README for flux dreambooth lora (#9290) 
* improve readme

* improve readme

* improve readme

* improve readme
 2024-09-05 17:53:23 +05:30
Dhruv Nair 53051cf282 [CI] Update Single file Nightly Tests (#9357) 
* update

* update
 2024-09-05 14:33:44 +05:30
Tolga Cangöz 3000551729 Update UNet2DConditionModel's error messages (#9230) 
* refactor
 2024-09-04 10:49:56 -10:00
Vishnu V Jaddipal 249a9e48e8 Add Flux inpainting and Flux Img2Img (#9135) 
---------

Co-authored-by: yiyixuxu <yixu310@gmail.com>
 2024-09-04 10:31:43 -10:00
Fanli Lin 2ee3215949 [tests] make 2 tests device-agnostic (#9347) 
* enabel on xpu

* fix style
 2024-09-03 16:34:03 -10:00
Eduardo Escobar 8ecf499d8b Enable load_lora_weights for StableDiffusion3InpaintPipeline (#9330) 
Enable load_lora_weights for StableDiffusion3InpaintPipeline

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-09-03 15:19:37 -10:00
YiYi Xu dcf320f293 small update on rotary embedding (#9354) 
* update

* fix

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-09-03 07:18:33 -10:00
Sayak Paul 8ba90aa706 chore: add a cleaning utility to be useful during training. (#9240) 2024-09-03 15:00:17 +05:30
Aryan 9d49b45b19 [refactor] move positional embeddings to patch embed layer for CogVideoX (#9263) 
* remove frame limit in cogvideox

* remove debug prints

* Update src/diffusers/models/transformers/cogvideox_transformer_3d.py

* revert pipeline; remove frame limitation

* revert transformer changes

* address review comments

* add error message

* apply suggestions from review
 2024-09-03 14:45:12 +05:30
Dhruv Nair 81da2e1c95 [CI] Add option to dispatch Fast GPU tests on main (#9355) 
update
 2024-09-03 14:35:13 +05:30
Aryan 24053832b5 [tests] remove/speedup some low signal tests (#9285) 
* remove 2 shapes from SDFunctionTesterMixin::test_vae_tiling

* combine freeu enable/disable test to reduce many inference runs

* remove low signal unet test for signature

* remove low signal embeddings test

* remove low signal progress bar test from PipelineTesterMixin

* combine ip-adapter single and multi tests to save many inferences

* fix broken tests

* Update tests/pipelines/test_pipelines_common.py

* Update tests/pipelines/test_pipelines_common.py

* add progress bar tests
 2024-09-03 13:59:18 +05:30
Dhruv Nair f6f16a0c11 [CI] More Fast GPU Test Fixes (#9346) 
* update

* update

* update

* update
 2024-09-03 13:22:38 +05:30
Vishnu V Jaddipal 1c1ccaa03f Xlabs lora fix (#9348) 
* Fix ```from_single_file``` for xl_inpaint

* Add basic flux inpaint pipeline

* style, quality, stray print

* Fix stray changes

* Add inpainting model support

* Change lora conversion for xlabs

* Fix stray changes

* Apply suggestions from code review

* style

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-09-03 10:43:43 +05:30
Dhruv Nair 007ad0e2aa [CI] More fixes for Fast GPU Tests on main (#9300) 
update
 2024-09-02 17:51:48 +05:30
Aryan 0e6a8403f6 [core] Support VideoToVideo with CogVideoX (#9333) 
* add vid2vid pipeline for cogvideox

* make fix-copies

* update docs

* fake context parallel cache, vae encode tiling

* add test for cog vid2vid

* use video link from HF docs repo

* add copied from comments; correctly rename test class
 2024-09-02 16:54:58 +05:30
Aryan af6c0fb766 [core] CogVideoX memory optimizations in VAE encode (#9340) 
fake context parallel cache, vae encode tiling

(cherry picked from commit bf890bca0e)
 2024-09-02 15:48:37 +05:30
YiYi Xu d8a16635f4 update runway repo for single_file (#9323) 
update to a place holder
 2024-08-30 08:51:21 -10:00
Aryan e417d02811 [docs] Add a note on torchao/quanto benchmarks for CogVideoX and memory-efficient inference (#9296) 
* add a note on torchao/quanto benchmarks and memory-efficient inference

* apply suggestions from review

* update

* Update docs/source/en/api/pipelines/cogvideox.md

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

* Update docs/source/en/api/pipelines/cogvideox.md

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

* add note on enable sequential cpu offload

---------

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
 2024-08-30 13:53:25 +05:30
Dhruv Nair 1d4d71875b [CI] Update Hub Token on nightly tests (#9318) 
update
 2024-08-30 10:23:50 +05:30
YiYi Xu 61d96c3ae7 refactor rotary embedding 3: so it is not on cpu (#9307) 
change get_1d_rotary to accept pos as torch tensors
 2024-08-30 01:07:15 +05:30
YiYi Xu 4f495b06dc rotary embedding refactor 2: update comments, fix dtype for use_real=False (#9312) 
fix notes and dtype
 2024-08-28 23:31:47 -10:00
Anand Kumar 40c13fe5b4 [train_custom_diffusion.py] Fix the LR schedulers when num_train_epochs is passed in a distributed training env (#9308) 
* Update train_custom_diffusion.py to fix the LR schedulers for `num_train_epochs`

* Fix saving text embeddings during safe serialization

* Fixed formatting
 2024-08-29 14:23:36 +05:30
Sayak Paul 2a3fbc2cc2 [LoRA] support kohya and xlabs loras for flux. (#9295) 
* support kohya lora in flux.

* format

* support xlabs

* diffusion_model prefix.

* Apply suggestions from code review

Co-authored-by: apolinário <joaopaulo.passos@gmail.com>

* empty commit.

Co-authored-by: Leommm-byte <leom20031@gmail.com>

---------

Co-authored-by: apolinário <joaopaulo.passos@gmail.com>
Co-authored-by: Leommm-byte <leom20031@gmail.com>
 2024-08-29 07:41:46 +05:30
apolinário 089cf798eb Change default for guidance_scalein FLUX (#9305) 
To match the original code, 7.0 is too high
 2024-08-28 07:39:45 -10:00
Aryan cbc2ec8f44 AnimateDiff prompt travel (#9231) 
* update

* implement prompt interpolation

* make style

* resnet memory optimizations

* more memory optimizations; todo: refactor

* update

* update animatediff controlnet with latest changes

* refactor chunked inference changes

* remove print statements

* undo memory optimization changes

* update docstrings

* fix tests

* fix pia tests

* apply suggestions from review

* add tests

* update comment
 2024-08-28 14:48:12 +05:30
Frank (Haofan) Wang b5f591fea8 Update __init__.py (#9286) 2024-08-27 07:57:25 -10:00
Dhruv Nair 05b38c3c0d Fix Flux CLIP prompt embeds repeat for num_images_per_prompt > 1 (#9280) 
update
 2024-08-27 07:41:12 -10:00
Dhruv Nair 8f7fde5701 [CI] Update Release Tests (#9274) 
* update

* update
 2024-08-27 18:34:00 +05:30
Dhruv Nair a59672655b Fix Freenoise for AnimateDiff V3 checkpoint. (#9288) 
update
 2024-08-27 18:30:39 +05:30
Marçal Comajoan Cara 9aca79f2b8 Replace transformers.deepspeed with transformers.integrations.deepspeed (#9281) 
to avoid "FutureWarning: transformers.deepspeed module is deprecated and will be removed in a future version. Please import deepspeed modules directly from transformers.integrations"

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-08-27 18:08:23 +05:30