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
2,569 Commits 740 Branches 94 Tags
ee2f2775b25ebbbff7314b72c64ed07461fdd4b6
Commit Graph

2569 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Patrick von Platen
ee2f2775b2 [tests] use parent class for monkey patching to not break other tests (#4088) 
* [tests] use parent class for monkey patching to not break other tests

* fix
 2023-07-14 13:44:44 +02:00
Sayak Paul
692b7a907d [Feat] add: utility for unloading lora. (#4034) 
* add: test for testing unloading lora.

* add :reason to skipif.

* initial implementation of lora unload().

* apply styling.

* add: doc.

* change checkpoints.

* reinit generator

* finalize slow test.

* add fast test for unloading lora.
 2023-07-14 16:30:18 +05:30
Patrick von Platen
71c918b848 [Invisible watermark] Correct version (#4087) 2023-07-14 09:30:43 +05:30
Sayak Paul
83ca21f539 fix: minor things in the SDXL docs. (#4070) 2023-07-14 09:01:20 +05:30
Gabriel Birnbaum
f3802eb805 fix requirement in SDXL (#4082) 2023-07-14 02:58:20 +02:00
Patrick von Platen
bfe8b41315 [From Single File] Force accelerate to be installed (#4078) 
force accelerate to be installed
 2023-07-13 23:16:43 +02:00
YiYi Xu
4535088cec add kandinsky to readme table (#4081) 
Co-authored-by: yiyixuxu <yixu310@gmail,com>
 2023-07-13 22:26:51 +02:00
Thomas Chambon
2eceaaef0f [Community] Implementation of the IADB community pipeline (#3996) 
* community pipeline: implementation of iadb

* iadb.py: reformat using black

* iadb.py: linting update
 2023-07-13 16:49:41 +02:00
Ruoxi
ece55227ff Multiply lr scheduler steps by num_processes. (#3983) 
* Multiply lr scheduler steps by `num_processes`.

* Stop multiplying steps by gradient accumulation.
 2023-07-13 17:50:25 +05:30
Patrick von Platen
92a57a8e84 Fix kandinsky remove safety (#4065) 
* Finish

* make style
 2023-07-12 21:42:29 +02:00
Lucain
d7280b7436 Trigger CI on ci-* branches (#3635) 2023-07-12 19:31:36 +02:00
Patrick von Platen
e9eb0938f4 make style 2023-07-12 19:24:47 +02:00
junming huang
a29ea36d62 Update train_unconditional.py (#3899) 
increase the time of timeout when using big dataset or high resolution
 2023-07-12 19:24:28 +02:00
Evgenii Kashin
af48bf2008 Add circular padding for artifact-free StableDiffusionPanoramaPipeline (#4025) 
* Add circular padding option

* Fix style with black

* Fix corner case with small image size

* Add circular padding test cases

* Fix docstring

* Improve docstring for circular padding, remove slow test case

* Update docs for circular padding argument

* Add images comparison for circular padding
 2023-07-12 20:49:46 +05:30
Patrick von Platen
4b50ecceb0 Correct sdxl docs (#4058) 2023-07-12 16:02:31 +02:00
Bagheera
99b540b072 [SDXL] Partial diffusion support for Text2Img and Img2Img Pipelines (#4015) 
* diffusers#4003 - initial implementation of max_inference_steps

* diffusers#4003 - initial implementation of max_inference_steps and first_inference_step for img2img

* diffusers#4003 - use first_inference_step as an input arg for get_timestamps in img2img

* diffusers#4003 Do not add noise during img2img when we have a defined first timestep

* diffusers#4003 Mild updates after revert

* diffusers#4003 Missing change

* Show implementation with denoising_start and end

* Apply suggestions from code review

* Update src/diffusers/pipelines/stable_diffusion_xl/pipeline_stable_diffusion_xl.py

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

* move to 0.19.0dev

* Apply suggestions from code review

* add exhaustive tests

* add docs

* finish

* Apply suggestions from code review

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

* make style

---------

Co-authored-by: bghira <bghira@users.github.com>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2023-07-12 13:54:27 +02:00
Patrick von Platen
b9feed8795 move to 0.19.0dev (#4048) 2023-07-11 22:49:12 +02:00
Kadir Nar
f9cedfb75c 📝 Fix broken link to models documentation (#4026) 
* 📝 Fix broken link to models documentation

Corrected the link to the models documentation in the README. Previously, the link was pointing to an incorrect URL. Now, the link directs users to the correct documentation page for more details on the models.

Thanks! 🙌

* Update src/diffusers/models/README.md

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

---------

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
 2023-07-11 12:10:37 -07:00
Michael Monashev
fc7aa64ea8 Fixed pipeline parameter descriptions. (#3955) 
Fixed parameter descriptions
 2023-07-11 09:52:17 -07:00
Patrick von Platen
d0979f5274 quick fix to make sure sdxl conversion works 2023-07-11 16:51:56 +00:00
Vines
fcb0da7f00 Fix diffedit doc typo (#3977) 
fix diffedit code mistake
 2023-07-11 09:47:36 -07:00
manosplitsis
8e8b046d24 Typo fix in example docstring in audioldm pipeline (#4044) 
typo fix in example docstring in audioldm pipeline
 2023-07-11 09:35:11 -07:00
oOraph
5e704a2c71 keep _use_default_values as a list type (#4040) 
Signed-off-by: Raphael <oOraph@users.noreply.github.com>
Co-authored-by: Raphael <oOraph@users.noreply.github.com>
 2023-07-11 18:21:08 +02:00
Patrick von Platen
8bff782354 Improve single loading file (#4041) 
* start improving single file load

* Fix more

* start improving single file load

* Fix sd 2.1

* further improve from_single_file
 2023-07-11 17:01:25 +02:00
Lucain
6632823690 FIX force_download in download utility (#4036) 
FIX force_download in download utils
 2023-07-11 12:20:00 +02:00
Sayak Paul
f74d5e1c2f [diffusers-cli] Add a CLI command to run FP16 and safetensors conversions and opening PRs (#3982) 
* feat: add a cli util for fp16 and safetensors format.

* fix: commit_description.

* add: usage example.
 2023-07-11 08:30:09 +05:30
Sayak Paul
3d74dc2abd [Examples] Add a training script for SDXL DreamBooth LoRA (#4016) 
* add dreambooth lora script for SDXL incorporating latest changes.

* remove use_auth_token=True.

* add: documentation

* remove unneeded cli.

* increase the number of training steps in the readme.

* add LoraLoaderMixin to the subclassing mix.

* add sdxl lora dreambooth test.

* add: inference code sample.

* add: refiner output.

* add LoraLoaderMixin to the mix of classes of StableDiffusionXLImg2ImgPipeline.

* change default resolution of DreamBoothDataset.

* better sdxl report path.

* Apply suggestions from code review

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

---------

Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
 2023-07-11 07:38:41 +05:30
Susnato Dhar
dfd7eafbce Fixed wrong link in CONTRIBUTING.md (#4028) 
Update CONTRIBUTING.md
 2023-07-10 21:00:55 +02:00
Steven Liu
8dd0ddc3c4 [docs] Fix index page (#3997) 
* fix

* correct link

* Fix typo

---------

Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
 2023-07-10 10:24:37 -07:00
Patrick von Platen
080ecf01b3 Improve loading pipe (#4009) 
* improve loading subcomponents

* Add test for logging

* improve loading subcomponents

* make style

* make style

* fix

* finish
 2023-07-10 18:05:40 +02:00
Pedro Cuenca
7a91ea6c2b Remove remaining not in upscale pipeline (#4020) 
Remove remaining `not` in upscale pipeline.
 2023-07-10 12:37:50 +02:00
Sayak Paul
e4559f48c1 minor improvements to the SDXL doc. (#3985) 
* minor improvements to the SDXL doc.

* use_refiner variable.

* fix: typo.
 2023-07-10 16:04:23 +05:30
Pedro Cuenca
d6b861401e Correctly keep vae in float16 when using PyTorch 2 or xFormers (#4019) 
* Update pipeline_stable_diffusion_xl.py

fix a bug

* Update pipeline_stable_diffusion_xl_img2img.py

* Update pipeline_stable_diffusion_xl_img2img.py

* Update pipeline_stable_diffusion_upscale.py

* style

---------

Co-authored-by: Hu Ye <xiaohuzc@gmail.com>
 2023-07-10 12:19:56 +02:00
Patrick von Platen
e4f6c3799d [DiffusionPipeline] Deprecate not throwing error when loading non-existant variant (#4011) 
* Deprecate variant nicely

* make style

* Apply suggestions from code review

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

* Apply suggestions from code review

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

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
 2023-07-10 12:12:29 +02:00
Patrick von Platen
98c9aac1d5 [SDXL] Fix all sequential offload (#4010) 
* Fix all sequential offload

* make style

* make style
 2023-07-10 10:27:23 +02:00
Omar Sanseviero
e3d71ad89a Minor nits to Dance DIffusion (#4012) 
Update pipeline_dance_diffusion.py
 2023-07-10 02:53:06 +05:30
Patrick von Platen
68f61a07d6 Make sure torch compile doesn't access unet config (#4008) 2023-07-10 00:23:55 +05:30
Patrick von Platen
4a3e574807 make style 2023-07-09 16:02:59 +00:00
Will Berman
c2a28c346c Refactor LoRA (#3778) 
* refactor to support patching LoRA into T5

instantiate the lora linear layer on the same device as the regular linear layer

get lora rank from state dict

tests

fmt

can create lora layer in float32 even when rest of model is float16

fix loading model hook

remove load_lora_weights_ and T5 dispatching

remove Unet#attn_processors_state_dict

docstrings

* text encoder monkeypatch class method

* fix test

---------

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
 2023-07-09 18:02:46 +02:00
Patrick von Platen
78922ed7c7 Add sdxl prompt embeddings (#3995) 
* Add sdxl prompt embeddings

* Fix more

* fix some slow tests
 2023-07-07 16:50:53 +02:00
Patrick von Platen
6fde5a6dd6 [Tests] Fix some slow tests (#3989) 
fix some slow tests
 2023-07-07 15:17:57 +02:00
Amiha
d1d0b8afce Don't use bare prints in a library (#3991) 2023-07-07 15:17:50 +02:00
Batuhan Taskaya
04ddad484e Add 'rank' parameter to Dreambooth LoRA training script (#3945) 2023-07-07 17:26:10 +05:30
Saurav Maheshkar
03d829d59e feat: add Dropout to Flax UNet (#3894) 
* feat: add Dropout to Flax UNet

* feat: add @compact decorator

* fix: drop nn.compact
 2023-07-07 11:38:16 +02:00
Omar Sanseviero
8d8b4311b9 Fix code snippet for Audio Diffusion (#3987) 2023-07-07 10:39:38 +02:00
Yorai Levi
1fbcc78d6e typo in safetensors (safetenstors) (#3976) 
* Update pipeline_utils.py

typo in safetensors (safetenstors)

* Update loaders.py

typo in safetensors (safetenstors)

* Update modeling_utils.py

typo in safetensors (safetenstors)
 2023-07-07 13:03:51 +05:30
Patrick von Platen
51593da25a fix main docs 2023-07-06 19:28:33 +02:00
Patrick von Platen
38e563d0c7 Fix SD XL Docs (#3971) 
* finish sd xl docs

* make style

* Apply suggestions from code review

* uP

* uP

* Correct
 2023-07-06 19:21:03 +02:00
Aisuko
b8f089c5a3 fix/doc-code: import torch and fix the broken document address (#3941) 
Signed-off-by: GitHub <noreply@github.com>
 2023-07-06 09:29:04 -07:00
Patrick von Platen
187ea539ae Improve SD XL (#3968) 
* improve sd xl

* correct more

* finish

* make style

* fix more
 2023-07-06 18:11:20 +02:00