AI/diffusers
1
0
Fork 0
mirror of https://github.com/huggingface/diffusers.git synced 2026-10-24 20:59:27 +03:00
Code Activity
3,077 Commits 930 Branches 101 Tags
fix/lora-dtype
Commit Graph

3077 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
sayakpaul
62ece6ab5a debug 2023-10-16 11:45:49 +05:30
sayakpaul
7722f5b67c debug 2023-10-16 11:44:45 +05:30
sayakpaul
0281e85827 debug 2023-10-16 11:36:48 +05:30
sayakpaul
9106e66382 debug 2023-10-16 11:32:50 +05:30
sayakpaul
2fb3d141c2 debug 2023-10-16 11:30:39 +05:30
sayakpaul
6e1b06c01c debug 2023-10-16 11:25:46 +05:30
sayakpaul
50f2544697 debug 2023-10-16 11:21:06 +05:30
sayakpaul
fc5fc8c8d2 debug 2023-10-16 10:44:03 +05:30
sayakpaul
030bb528ba debug 2023-10-16 10:39:51 +05:30
sayakpaul
f803d3d1f5 Merge branch 'main' into fix/lora-dtype 2023-10-16 09:46:56 +05:30
Sayak Paul
07b297e7de [Bot] FIX stale.py uses timezone-aware datetime (#5396) 
reflect stalebot change from https://github.com/huggingface/peft/pull/1016/
 2023-10-16 00:54:50 +05:30
Younes Belkada
2bfa55f4ed [core / PEFT / LoRA] Integrate PEFT into Unet (#5151) 
* v1

* add tests and fix previous failing tests

* fix CI

* add tests + v1 `PeftLayerScaler`

* style

* add scale retrieving mechanism system

* fix CI

* up

* up

* simple approach --> not same results for some reason

* fix issues

* fix copies

* remove unneeded method

* active adapters!

* fix merge conflicts

* up

* up

* kohya - test-1

* Apply suggestions from code review

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

* fix scale

* fix copies

* add comment

* multi adapters

* fix tests

* oops

* v1 faster loading - in progress

* Revert "v1 faster loading - in progress"

This reverts commit ac925f8132.

* kohya same generation

* fix some slow tests

* peft integration features for unet lora

1. Support for Multiple ranks/alphas
2. Support for Multiple active adapters
3. Support for enabling/disabling LoRAs

* fix `get_peft_kwargs`

* Update loaders.py

* add some tests

* add unfuse tests

* fix tests

* up

* add set adapter from sourab and tests

* fix multi adapter tests

* style & quality

* style

* remove comment

* fix `adapter_name` issues

* fix unet adapter name for sdxl

* fix enabling/disabling adapters

* fix fuse / unfuse unet

* nit

* fix

* up

* fix cpu offloading

* fix another slow test

* fix another offload test

* add more tests

* all slow tests pass

* style

* fix alpha pattern for unet and text encoder

* Update src/diffusers/loaders.py

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

* Update src/diffusers/models/attention.py

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

* up

* up

* clarify comment

* comments

* change comment order

* change comment order

* stylr & quality

* Update tests/lora/test_lora_layers_peft.py

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

* fix bugs and add tests

* Update src/diffusers/models/modeling_utils.py

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

* Update src/diffusers/models/modeling_utils.py

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

* refactor

* suggestion

* add break statemebt

* add compile tests

* move slow tests to peft tests as I modified them

* quality

* refactor a bit

* style

* change import

* style

* fix CI

* refactor slow tests one last time

* style

* oops

* oops

* oops

* final tweak tests

* Apply suggestions from code review

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

* Update src/diffusers/loaders.py

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

* comments

* Apply suggestions from code review

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

* remove comments

* more comments

* try

* revert

* add `safe_merge` tests

* add comment

* style, comments and run tests in fp16

* add warnings

* fix doc test

* replace with `adapter_weights`

* add `get_active_adapters()`

* expose `get_list_adapters` method

* better error message

* Apply suggestions from code review

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

* style

* trigger slow lora tests

* fix tests

* maybe fix last test

* revert

* Update src/diffusers/loaders.py

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

* Update src/diffusers/loaders.py

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

* Update src/diffusers/loaders.py

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

* Update src/diffusers/loaders.py

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

* Apply suggestions from code review

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

* move `MIN_PEFT_VERSION`

* Apply suggestions from code review

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

* let's not use class variable

* fix few nits

* change a bit offloading logic

* check earlier

* rm unneeded block

* break long line

* return empty list

* change logic a bit and address comments

* add typehint

* remove parenthesis

* fix

* revert to fp16 in tests

* add to gpu

* revert to old test

* style

* Update src/diffusers/loaders.py

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

* change indent

* Apply suggestions from code review

* Apply suggestions from code review

---------

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: Sourab Mangrulkar <13534540+pacman100@users.noreply.github.com>
Co-authored-by: Benjamin Bossan <BenjaminBossan@users.noreply.github.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
 2023-10-13 16:47:03 +02:00
Sayak Paul
9bc55e8b7f [Core] Add FreeU to all the core pipelines and their (mostly-used) derivatives (#5376) 
* add: freeu to the core sdxl pipeline.

* add: freeu to video2video

* add: freeu to the core SD pipelines.

* add: freeu to image variation for sdxl.

* add: freeu to SD ControlNet pipelines.

* add: freeu to SDXL controlnet pipelines.

* add: freu to t2i adapter pipelines.

* make fix-copies.
 2023-10-13 17:16:16 +05:30
Sayak Paul
3758d7a8b0 debug 2023-10-13 15:51:32 +05:30
Sayak Paul
3a794b54c9 derbug 2023-10-13 15:44:39 +05:30
Sayak Paul
fe623f3bea derbug 2023-10-13 15:34:48 +05:30
Sayak Paul
bc65f829b7 debug 2023-10-13 14:41:43 +05:30
Sayak Paul
c22be1a557 debug 2023-10-13 14:36:48 +05:30
Sayak Paul
05f716d4ac debug 2023-10-13 14:12:28 +05:30
Sayak Paul
25b0d5b8c4 debug 2023-10-13 14:09:12 +05:30
Dhruv Nair
4d2c981d55 New xformers test runner (#5349) 
* move xformers to dedicated runner

* fix

* remove ptl from test runner images
 2023-10-13 00:32:39 +05:30
Steven Liu
cf03f5b718 [docs] Minor fixes (#5369) 
minor fixes
 2023-10-11 17:18:29 -07:00
Patrick von Platen
5313aa6231 make style 2023-10-11 11:19:35 +00:00
Chi
ea8364e581 I Added Doc-String Into The class. (#5293) 
* 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

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2023-10-11 13:19:06 +02:00
Soumik Rakshit
e00df25aee Fix StableDiffusionXLImg2ImgPipeline creation in sdxl tutorial (#5367) 
fix: StableDiffusionXLImg2ImgPipeline creation in sdxl tutorial
 2023-10-11 13:07:53 +02:00
Aryan V S
91fd181245 Improve typehints and docs in diffusers/models (#5312) 
* improvement: add missing typehints and docs to diffusers/models/attention.py

* chore: convert doc strings to raw python strings

add missing typehints

* improvement: add missing typehints and docs to diffusers/models/adapter.py

* improvement: add missing typehints and docs to diffusers/models/lora.py

* docs: include suggestion by @sayakpaul in src/diffusers/models/adapter.py

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

* docs: include suggestion by @sayakpaul in src/diffusers/models/adapter.py

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

* docs: include suggestion by @sayakpaul in src/diffusers/models/adapter.py

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

* docs: include suggestion by @sayakpaul in src/diffusers/models/adapter.py

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

* Update src/diffusers/models/lora.py

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
 2023-10-11 13:04:59 +02:00
Sayak Paul
0fa32bd674 [Examples] use loralinear instead of depecrecated lora attn procs. (#5331) 
* use loralinear instead of depecrecated lora attn procs.

* fix parameters()

* fix saving

* add back support for add kv proj.

* fix: param accumul,ation.

* propagate the changes.
 2023-10-11 13:02:42 +02:00
ssusie
aea73834f6 Adding PyTorch XLA support for sdxl inference (#5273) 
* Added  mark_step for sdxl to run with pytorch xla. Also updated README with instructions for xla

* adding soft dependency on torch_xla

* fix some styling

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>
 2023-10-11 12:35:37 +02:00
Steven Liu
a139213578 [docs] Create a mask for inpainting (#5322) 
add mask making section
 2023-10-10 08:29:27 -07:00
Humphrey009
9c82b68f07 fix problem of 'accelerator.is_main_process' to run in mutiple GPUs (#5340) 
fix problem of 'accelerator.is_main_process' to run in mutiple GPUs or NPUs

Co-authored-by: jiaqiw <wangjiaqi50@huawei.com>
 2023-10-10 15:39:22 +05:30
Julien Simon
d3e0750d5d Add missing dependency in requirements file (#5345) 
Update requirements_sdxl.txt

Add missing 'datasets'

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2023-10-10 15:37:58 +05:30
Roy Hvaara
4ac205e32f [JAX] Replace uses of jnp.array in types with jnp.ndarray. (#4719) 
`jnp.array` is a function, not a type:
https://jax.readthedocs.io/en/latest/_autosummary/jax.numpy.array.html
so it never makes sense to use `jnp.array` in a type annotation.

Presumably the intent was to write `jnp.ndarray` aka `jax.Array`. Change uses of `jnp.array` to `jnp.ndarray`.

Co-authored-by: Peter Hawkins <phawkins@google.com>
 2023-10-09 22:04:40 +02:00
Patrick von Platen
ed2f956072 Fix loading broken LoRAs that could give NaN (#5316) 
* Fix fuse Lora

* improve a bit

* make style

* Update src/diffusers/models/lora.py

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

* ciao C file

* ciao C file

* test & make style

---------

Co-authored-by: Benjamin Bossan <BenjaminBossan@users.noreply.github.com>
 2023-10-09 18:01:55 +02:00
Jake Vanderplas
a844065384 replace references to deprecated KeyArray & PRNGKeyArray (#5324) 2023-10-09 17:31:50 +02:00
Jonathan Whitaker
35952e61c1 Fix links in docs to adapter code (#5323) 
Update adapter.md to fix links to adapter pipelines
 2023-10-09 17:20:12 +02:00
Patrick von Platen
d199bc62ec make style 2023-10-09 17:12:12 +02:00
Aryan V S
8d314c96ee [HacktoberFest] Add missing docstrings to diffusers/models (#5248) 
* add missing docstrings

* chore: run make quality

* improvement: include docs suggestion by @yiyixuxu

---------

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
 2023-10-09 17:09:16 +02:00
Brian Yarbrough
e2c0208c86 Add py.typed for PEP 561 compliance (#5326) 
See #5325
 2023-10-09 17:08:55 +02:00
Aryan V S
bd72927c63 Improve typehints and docs in diffusers/models (#5299) 
* improvement: add typehints and docs to diffusers/models/activations.py

* improvement: add typehints and docs to diffusers/models/resnet.py
 2023-10-09 16:29:23 +02:00
__mo_san__
c4d66200b7 make-fast-test-for-StableDiffusionControlNetPipeline-faster (#5292) 
* decrease UNet2DConditionModel & ControlNetModel blocks

* decrease UNet2DConditionModel & ControlNetModel blocks

* decrease even more blocks & number of norm groups

* decrease vae block out channels and n of norm goups

* fix code style

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2023-10-09 14:56:27 +05:30
Sebastian
2ed7e05fc2 Improve performance of fast test by reducing down blocks (#5290) 
* Reduce number of down block channels

* Remove debug code

* Set new excepted image slice values for sdxl euler test
 2023-10-09 14:49:56 +05:30
Pu Cao
cc2c4ae759 fix inference in custom diffusion (#5329) 
* Update train_custom_diffusion.py

* make style

* Empty-Commit

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2023-10-09 10:08:01 +02:00
chuzh
6bd55b54bc Fix [core/GLIGEN]: TypeError when iterating over 0-d tensor with In-painting mode when EulerAncestralDiscreteScheduler is used (#5305) 
* fix(gligen_inpaint_pipeline): 🐛 Wrap the timestep() 0-d tensor in a list to convert to 1-d tensor. This avoids the TypeError caused by trying to directly iterate over a 0-dimensional tensor in the denoising stage

* test(gligen/gligen_text_image): unit test using the EulerAncestralDiscreteScheduler

---------

Co-authored-by: zhen-hao.chu <zhen-hao.chu@vitrox.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2023-10-09 09:54:01 +02:00
Zeng Xian
0513a8cfd8 fix typo in train dreambooth lora description (#5332) 2023-10-08 14:54:33 +02:00
Shubham S Jagtap
306dc6e751 Update README.md (#5267) 
Co-authored-by: YiYi Xu <yixu310@gmail.com>
 2023-10-06 14:50:18 -07:00
vedant2003
dd25ef5679 [Hacktoberfest]Fixing issues #5241 (#5255) 
* Update pipeline_wuerstchen_prior.py

* prior_num_inference_steps updated

* height, width, num_inference_steps, and guidance_scale synced

* parameters synced

* latent_mean, latent_std, and resolution_multiple synced

* prior_num_inference_steps changed

* Formatted pipeline_wuerstchen_prior.py

* Update src/diffusers/pipelines/wuerstchen/pipeline_wuerstchen_prior.py

---------

Co-authored-by: Kashif Rasul <kashif.rasul@gmail.com>
 2023-10-06 14:19:38 -07:00
TimothyAlexisVass
016866792d Minor fixes (#5309) 
tiny fixes
 2023-10-06 11:20:06 -07:00
Steven Liu
f0a2c63753 [docs] Improved inpaint docs (#5210) 
* start

* finish draft

* add section

* edits

* feedback

* make fix-copies

* rebase
 2023-10-06 09:44:24 -07:00
Sayak Paul
7eaae83f16 [LoRA] fix: torch.compile() for lora conv (#5298) 
fix: torch.compile() for lora conv
 2023-10-06 17:14:47 +02:00
Dhruv Nair
872ae1dd12 Add from single file to StableDiffusionUpscalePipeline and StableDiffusionLatentUpscalePipeline (#5194) 
* add from single file

* clean up

* make style

* add single file loading for upscaling
 2023-10-06 13:18:13 +02:00