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
3,644 Commits 740 Branches 94 Tags
2fb9baf934629db718f00d4eaeeddd9dac80dfdd
Commit Graph

3644 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Dhruv Nair
2fb9baf934 update 2024-01-19 07:24:19 +00:00
Dhruv Nair
aee8b5f5d5 update 2024-01-19 06:24:35 +00:00
Dhruv Nair
fd2ec36369 update 2024-01-19 06:13:20 +00:00
Dhruv Nair
ffde1235fc update 2024-01-19 05:44:01 +00:00
Dhruv Nair
1ca79f7b83 update 2024-01-19 05:33:34 +00:00
Dhruv Nair
9b42fbfdbe update 2024-01-19 04:27:37 +00:00
Dhruv Nair
db3eb06ae4 update 2024-01-19 04:06:15 +00:00
spezialspezial
58b8dce129 Update convert_from_ckpt.py / read checkpoint config yaml contents (#6633) 
Update convert_from_ckpt.py / read config yaml contents

Added missing reading of config yaml file contents
 2024-01-19 08:25:03 +05:30
Dhruv Nair
a076513fd2 update 2024-01-18 16:50:05 +00:00
Dhruv Nair
32349c5ba5 update 2024-01-18 15:08:10 +00:00
Dhruv Nair
a65ca8a059 Fix failing tests due to Posix Path (#6627) 
update
 2024-01-18 19:19:57 +05:30
Dhruv Nair
eb71c80448 update 2024-01-18 13:13:54 +00:00
Dhruv Nair
c22c2aa28b update 2024-01-18 06:58:06 +00:00
Dhruv Nair
0939565b29 update 2024-01-18 05:55:26 +00:00
Dhruv Nair
de77ff6831 update 2024-01-18 04:12:20 +00:00
Steven Liu
5ca062e011 [docs] Fix missing API function (#6604) 
fix?
 2024-01-17 13:59:09 -08:00
Dhruv Nair
8a24733654 update 2024-01-17 16:02:08 +00:00
Linoy Tsaban
619e3ab6f6 [bug fix] advanced dreambooth lora sdxl - fixes bugs described in #6486 (#6599) 
* fixes bugs:
1. redundant retraction
2. param clone
3. stopping optimization of text encoder params

* param upscaling

* style
 2024-01-17 20:11:45 +05:30
Patrick von Platen
9e2804f720 Update pr_test_peft_backend.yml to use 1 process for testing (#6613) 2024-01-17 19:25:30 +05:30
Dhruv Nair
249f78e1c8 update 2024-01-17 11:55:18 +00:00
Aryan V S
9112028ed8 FreeInit (#6315) 
* freeinit

* update freeinit implementation based on review

Co-Authored-By: Dhruv Nair <dhruv.nair@gmail.com>

* fix

* another fix

* refactor

* fix timesteps missing bug

* apply suggestions from review

Co-Authored-By: Dhruv Nair <dhruv.nair@gmail.com>

* add test for freeinit

* apply suggestions from review

Co-Authored-By: Dhruv Nair <dhruv.nair@gmail.com>

* refactor

* fix test

* fix tensor not on same device

* update

* remove return_intermediate_results

* fix broken freeinit test

* update animatediff docs

---------

Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>
 2024-01-17 17:17:07 +05:30
Dhruv Nair
df4a8eaf37 update 2024-01-17 10:24:26 +00:00
Dhruv Nair
1cce591cd1 update 2024-01-17 08:50:37 +00:00
Dhruv Nair
1bd8ba3de1 update 2024-01-17 08:03:40 +00:00
Dhruv Nair
e37abaf1ee update 2024-01-17 06:55:59 +00:00
Steve Rhoades
dce06680d2 Fixes torch.compile() compatible training (#6589) 
resolve conflicts
 2024-01-17 07:47:03 +05:30
Bhavay Malhotra
dd63168319 Update installation.md (#6438) 
* Update installation.md

* Update installation.md

* Update installation.md
 2024-01-16 13:41:38 -08:00
Celestial Phineas
1040dfd9cc [Fix] Multiple image conditionings in a single batch for StableDiffusionControlNetPipeline (#6334) 
* [Fix] Multiple image conditionings in a single batch for `StableDiffusionControlNetPipeline`.

* Refactor `check_inputs` in `StableDiffusionControlNetPipeline` to avoid redundant codes.

* Make the behavior of MultiControlNetModel to be the same to the original ControlNetModel

* Keep the code change minimum for nested list support

* Add fast test `test_inference_nested_image_input`

* Remove redundant check for nested image condition in `check_inputs`

Remove `len(image) == len(prompt)` check out of `check_image()`

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

* Better `ValueError` message for incompatible nested image list size

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

* Fix syntax error in `check_inputs`

* Remove warning message for multi-ControlNets with multiple prompts

* Fix a typo in test_controlnet.py

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

* Add test case for multiple prompts, single image conditioning in `StableDiffusionMultiControlNetPipelineFastTests`

* Improved `ValueError` message for nested `controlnet_conditioning_scale`

* Documenting the behavior of image list as `StableDiffusionControlNetPipeline` input

---------

Co-authored-by: YiYi Xu <yixu310@gmail.com>
 2024-01-16 10:40:55 -10:00
Sayak Paul
49a4b377c1 remove omegaconf from the residues 👋 (#6600) 
remove omegaconf 👋
 2024-01-16 21:55:41 +05:30
JuanCarlosPi
dff35a86e4 Change in ip-adapter docs. CLIPVisionModelWithProjection should be im… (#6597) 
Change in ip-adapter docs. CLIPVisionModelWithProjection should be imported from transformers, not diffusers
 2024-01-16 08:18:13 -08:00
Dhruv Nair
68a49b1b45 update 2024-01-16 16:03:37 +00:00
Dhruv Nair
4bb4ed4711 update 2024-01-16 13:51:38 +00:00
Yondon Fu
8842bcadb9 [SVD] Return np.ndarray when output_type="np" (#6507) 
[SVD] Fix output_type="np"
 2024-01-16 14:51:36 +05:30
Steve Rhoades
181280baba Fixes training resuming: Advanced Dreambooth LoRa Training (#6566) 
* Fixes #6418 Advanced Dreambooth LoRa Training

* change order of import to fix nit

* fix nit, use cast_training_params

* remove torch.compile fix, will move to a new PR

* remove unnecessary import
 2024-01-16 14:30:49 +05:30
Charchit Sharma
53f498d2a4 Use of Posix to better support Windows compatibility in testing_utils (#6587) 
* changes in utils

* removed loc
 2024-01-16 10:27:29 +02:00
Charchit Sharma
990860911f change to posix for better Windows support for lora loaders (#6590) 
* posix lora

* changes and style fix
 2024-01-16 13:46:29 +05:30
Dhruv Nair
0ec1ed7a91 update 2024-01-16 07:52:32 +00:00
Fabio Rigano
23eed39702 Fix path generation in IP Adapter (#6564) 
* Fix path generation on Windows

* Update set_default_attn_processors

* Use pathlib

* Fix quality

* Fix copy

* Revert changes in set_default_attn_processors

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-01-16 11:25:22 +05:30
YiYi Xu
fefed44543 update slow test for SDXL k-diffusion pipeline (#6588) 
update expected slice
 2024-01-15 18:54:33 -10:00
Dong
814f56d2fe 🐛 fix ip-adapter controlnet img2img missing code (#6528) 
* 🐛 fix ip-adapter controlnet img2img missing code

* 📝 edit test

* 📝 edit test

* 📝 run make style and quality

* 🎨 remove slow tests
 2024-01-15 16:41:09 -10:00
SangKim
96d6e16550 Enable image resizing to adjust its height and width in StableDiffusionXLInstructPix2PixPipeline (#6581) 
* Enable image resizing to adjust its height and width in StableDiffusionXLInstructPix2PixPipeline

* Ensure that validation is performed at every 'validation_step', not at every step
 2024-01-16 07:50:34 +05:30
Aryan V S
c11de13588 [training] fix training resuming problem for fp16 (SD LoRA DreamBooth) (#6554) 
* fix training resume

* update

* update
 2024-01-16 07:27:06 +05:30
Patrick von Platen
357855f8fc [Docs] Fix controlnet indent (#6578) 2024-01-15 18:12:55 +02:00
Fabio Rigano
f825221b5d [Community Pipeline] IPAdapter FaceID (#6276) 
* Add support for IPAdapter FaceID

* Add docs

* Move subfolder to kwargs

* Fix quality

* Fix image encoder loading

* Fix loading + add test

* Move to community folder

* Fix style

* Revert constant update

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-01-15 16:43:54 +02:00
Aryan V S
119d734f6e [AnimateDiff+Controlnet] Fix multicontrolnet support (#6551) 
* fix multicontrolnet support

* update README with multicontrolnet example
 2024-01-15 16:36:54 +02:00
Sayak Paul
cb4b3f0b78 [OmegaConf] replace it with yaml (#6488) 
* remove omegaconf from convert_from_ckpt.

* remove from single_file.

* change to string based ubscription.

* style

* okay

* fix: vae_param

* no . indexing.

* style

* style

* turn getattrs into explicit if/else

* style

* propagate changes to ldm_uncond.

* propagate to gligen

* propagate to if.

* fix: quotes.

* propagate to audioldm.

* propagate to audioldm2

* propagate to musicldm.

* propagate to vq_diffusion

* propagate to zero123.

* remove omegaconf from diffusers codebase.
 2024-01-15 20:02:10 +05:30
Haofan Wang
3d574b3bbe Fix a bug of flip in SDXL training script (#6547) 
* Update train_text_to_image_sdxl.py

* Update train_text_to_image_lora_sdxl.py
 2024-01-15 16:28:04 +02:00
Charchit Sharma
09903774d9 Make T2I Adapter SDXL Training Script torch.compile compatible (#6577) 
update for t2i_adapter
 2024-01-15 19:42:56 +05:30
dependabot[bot]
d6a70d8ba8 Bump jinja2 from 3.1.2 to 3.1.3 in /examples/research_projects/realfill (#6539) 
Bumps [jinja2](https://github.com/pallets/jinja) from 3.1.2 to 3.1.3.
- [Release notes](https://github.com/pallets/jinja/releases)
- [Changelog](https://github.com/pallets/jinja/blob/main/CHANGES.rst)
- [Commits](https://github.com/pallets/jinja/compare/3.1.2...3.1.3)

---
updated-dependencies:
- dependency-name: jinja2
  dependency-type: direct:production
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
 2024-01-15 16:10:10 +02:00
Dhruv Nair
cf560a715e update 2024-01-15 12:54:10 +00:00