LLM/diffusers
1
0
Fork 0
mirror of https://github.com/huggingface/diffusers.git synced 2026-02-17 00:06:20 +08:00
Code Issues Packages Projects Releases Wiki Activity
4,913 Commits 745 Branches 94 Tags
4c5082ca685d1dd0a24907890da170e258e5cd01
Commit Graph

4913 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
PommesPeter
2256ec51ff [Alpha-VLLM Team] Add Lumina-T2X to diffusers (#8652) 
---------

Co-authored-by: zhuole1025 <zhuole1025@gmail.com>
Co-authored-by: YiYi Xu <yixu310@gmail.com>
 2024-12-23 13:02:14 +05:30
YiYi Xu
75682d2c00 fix loading sharded checkpoints from subfolder (#8798) 
* fix load sharded checkpoints from subfolder{

* style

* os.path.join

* add a small test

---------

Co-authored-by: sayakpaul <spsayakpaul@gmail.com>
 2024-12-23 13:02:14 +05:30
apolinário
67b04c891d Improve model card for push_to_hub trainers (#8697) 
* Improve trainer model cards

* Update train_dreambooth_sd3.py

* Update train_dreambooth_lora_sd3.py

* add link to adapters loading doc

* Update train_dreambooth_lora_sd3.py

---------

Co-authored-by: Linoy Tsaban <57615435+linoytsaban@users.noreply.github.com>
 2024-12-23 13:02:14 +05:30
Dhruv Nair
1f221b0cf9 Fix saving text encoder weights and kohya weights in advanced dreambooth lora script (#8766) 
* update

* update

* update
 2024-12-23 13:02:14 +05:30
Dhruv Nair
e2cd8937ee [Single File] Allow loading T5 encoder in mixed precision (#8778) 
* update

* update

* update

* update
 2024-12-23 13:02:14 +05:30
Thomas Eding
fe85e9c4f8 Add vae_roundtrip.py example (#7104) 
* Add vae_roundtrip.py example

* Add cuda support to vae_roundtrip

* Move vae_roundtrip.py into research_projects/vae

* Fix channel scaling in vae roundrip and also support taesd.

* Apply ruff --fix for CI gatekeep check

---------

Co-authored-by: Álvaro Somoza <asomoza@users.noreply.github.com>
 2024-12-23 13:02:14 +05:30
Sayak Paul
755b079bad [Tests] fix sharding tests (#8764) 
fix sharding tests
 2024-12-23 13:02:14 +05:30
Aryan
18be16351a Fix minor bug in SD3 img2img test (#8779) 
fix minor bug in sd3 img2img
 2024-12-23 13:02:14 +05:30
XCL
d070965a80 [Tencent Hunyuan Team] Add checkpoint conversion scripts and changed controlnet (#8783) 
* add conversion files; changed controlnet for hunyuandit

* style

---------

Co-authored-by: xingchaoliu <xingchaoliu@tencent.com>
Co-authored-by: yiyixuxu <yixu310@gmail.com>
 2024-12-23 13:02:14 +05:30
Linoy Tsaban
de14a194eb [advanced dreambooth lora] add clip_skip arg (#8715) 
* add clip_skip

* style

* smol fix

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-12-23 13:02:14 +05:30
Sayak Paul
300b73bea1 [Chore] add dummy lora attention processors to prevent failures in other libs (#8777) 
add dummy lora attention processors to prevent failures in other libs
 2024-12-23 13:02:14 +05:30
Sayak Paul
63d5de4846 Update README.md to include Colab link (#8775) 2024-12-23 13:02:14 +05:30
Sayak Paul
3ca7f09a09 Allow SD3 DreamBooth LoRA fine-tuning on a free-tier Colab (#8762) 
* add experimental scripts to train SD3 transformer lora on colab

* add readme

* add colab

* Apply suggestions from code review

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

* fix link in the notebook.

---------

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
 2024-12-23 13:02:14 +05:30
Sayak Paul
11c5f6bfcd Revert "[LoRA] introduce LoraBaseMixin to promote reusability." (#8773) 
Revert "[LoRA] introduce `LoraBaseMixin` to promote reusability. (#8670)"

This reverts commit a2071a1837.
 2024-12-23 13:02:14 +05:30
Sayak Paul
2686552727 [LoRA] introduce LoraBaseMixin to promote reusability. (#8670) 
* introduce  to promote reusability.

* up

* add more tests

* up

* remove comments.

* fix fuse_nan test

* clarify the scope of fuse_lora and unfuse_lora

* remove space
 2024-12-23 13:02:13 +05:30
YiYi Xu
c147a42586 correct attention_head_dim for JointTransformerBlock (#8608) 
* add

* update sd3 controlnet

* Update src/diffusers/models/controlnet_sd3.py

---------

Co-authored-by: yiyixuxu <yixu310@gmail,com>
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>
 2024-12-23 13:02:13 +05:30
Jiwook Han
08db291f18 Reflect few contributions on philosophy.md that were not reflected on #8294 (#8690) 
* Update philosophy.md 

Some contributions were not reflected previously, so I am resubmitting them.

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

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

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

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

---------

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
 2024-12-23 13:02:13 +05:30
Dhruv Nair
56735380d8 Fix mistake in Single File Docs page (#8765) 
update
 2024-12-23 13:02:13 +05:30
Dhruv Nair
c586a8faff Fix indent in dreambooth lora advanced SD 15 script (#8753) 
update
 2024-12-23 13:02:13 +05:30
Dhruv Nair
b09dbbdfd2 Fix warning in UNetMotionModel (#8756) 
* update

* Update src/diffusers/models/unets/unet_motion_model.py

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

---------

Co-authored-by: YiYi Xu <yixu310@gmail.com>
 2024-12-23 13:02:13 +05:30
Dhruv Nair
dc5f12df61 Enforce ordering when running Pipeline slow tests (#8763) 
update
 2024-12-23 13:02:13 +05:30
YiYi Xu
a4bbc5fb39 [hunyuan-dit] refactor HunyuanCombinedTimestepTextSizeStyleEmbedding (#8761) 
up

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-12-23 13:02:13 +05:30
Sayak Paul
f5f9f9c083 [Tests] add test suite for SD3 DreamBooth (#8650) 
* add a test suite for SD3 DreamBooth

* lora suite

* style

* add checkpointing tests for LoRA

* add test to cover train_text_encoder.
 2024-12-23 13:02:13 +05:30
Álvaro Somoza
4d12d764f0 [SD3 LoRA Training] Fix errors when not training text encoders (#8743) 
* fix

* fix things.

Co-authored-by: Linoy Tsaban <linoy.tsaban@gmail.com>

* remove patch

* apply suggestions

---------

Co-authored-by: Linoy Tsaban <57615435+linoytsaban@users.noreply.github.com>
Co-authored-by: sayakpaul <spsayakpaul@gmail.com>
Co-authored-by: Linoy Tsaban <linoy.tsaban@gmail.com>
 2024-12-23 13:02:13 +05:30
Haofan Wang
7c253318d7 Allow from_transformer in SD3ControlNetModel (#8749) 
* Update controlnet_sd3.py

---------

Co-authored-by: YiYi Xu <yixu310@gmail.com>
 2024-12-23 13:02:13 +05:30
Dhruv Nair
a039005206 Remove legacy single file model loading mixins (#8754) 
update
 2024-12-23 13:02:13 +05:30
YiYi Xu
ace869b5ac [doc] add a tip about using SDXL refiner with hunyuan-dit and pixart (#8735) 
* up

* Apply suggestions from code review

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

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
 2024-12-23 13:02:13 +05:30
Lucain
48f8cfdc7b Always raise from previous error (#8751) 2024-12-23 13:02:13 +05:30
XCL
ad8cf587ed [Tencent Hunyuan Team] Add HunyuanDiT-v1.2 Support (#8747) 
* add v1.2 support

---------

Co-authored-by: xingchaoliu <xingchaoliu@tencent.com>
Co-authored-by: yiyixuxu <yixu310@gmail.com>
 2024-12-23 13:02:13 +05:30
WenheLI
7b3b87f45f fix the LR schedulers for dreambooth_lora (#8510) 
* update training

* update

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: Linoy Tsaban <57615435+linoytsaban@users.noreply.github.com>
 2024-12-23 13:02:13 +05:30
Bhavay Malhotra
19a53baeba [train_controlnet_sdxl.py] Fix the LR schedulers when num_train_epochs is passed in a distributed training env (#8476) 
* Create diffusers.yml

* num_train_epochs

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-12-23 13:02:13 +05:30
Sayak Paul
f9ba2ffcdf shift cache in benchmarking. (#8740) 
* shift cache.

* comment
 2024-12-23 13:02:13 +05:30
Shauray Singh
5f10c18270 add PAG support for SD architecture (#8725) 
* add pag to sd pipelines
 2024-12-23 13:02:13 +05:30
Sayak Paul
d64e0a89ff Benchmarking workflow fix (#8389) 
* fix

* fixes

* add back the deadsnakes

* better messaging

* disable IP adapter tests for the moment.

* style

* up

* empty
 2024-12-23 13:02:13 +05:30
Álvaro Somoza
29884169ad [Community pipeline] SD3 Differential Diffusion Img2Img Pipeline (#8679) 
* new pipeline
 2024-12-23 13:02:13 +05:30
Luo Chaofan
630b3d3256 fix: ValueError when using FromOriginalModelMixin in subclasses #8440 (#8454) 
* fix: ValueError when using FromOriginalModelMixin in subclasses #8440

(cherry picked from commit 9285997843)

* Update src/diffusers/loaders/single_file_model.py

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

* Update single_file_model.py

* Update single_file_model.py

---------

Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-12-23 13:02:13 +05:30
Dhruv Nair
5ac9ed8dd6 [Tests] Fix precision related issues in slow pipeline tests (#8720) 
update
 2024-12-23 13:02:13 +05:30
Linoy Tsaban
94b734163a [Advanced dreambooth lora] adjustments to align with canonical script (#8406) 
* minor changes

* minor changes

* minor changes

* minor changes

* minor changes

* minor changes

* minor changes

* fix

* fix

* aligning with blora script

* aligning with blora script

* aligning with blora script

* aligning with blora script

* aligning with blora script

* remove prints

* style

* default val

* license

* move save_model_card to outside push_to_hub

* Update train_dreambooth_lora_sdxl_advanced.py

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-12-23 13:02:13 +05:30
Sayak Paul
bd83b68d0f [Chore] perform better deprecation for vqmodeloutput (#8719) 
perform better deprecation for vqmodeloutput
 2024-12-23 13:02:13 +05:30
Mathis Koroglu
74cee44e88 Motion Model / Adapter versatility (#8301) 
* Motion Model / Adapter versatility

- allow to use a different number of layers per block
- allow to use a different number of transformer per layers per block
- allow a different number of motion attention head per block
- use dropout argument in get_down/up_block in 3d blocks

* Motion Model added arguments renamed & refactoring

* Add test for asymmetric UNetMotionModel
 2024-12-23 13:02:13 +05:30
vincedovy
03003823f5 Fix json WindowsPath crash (#8662) 
* Add check for WindowsPath in to_json_string

On Windows, os.path.join returns a WindowsPath. to_json_string does not convert this from a WindowsPath to a string. Added check for WindowsPath to to_json_saveable.

* Remove extraneous convert to string in test_check_path_types (tests/others/test_config.py)

* Fix style issues in tests/others/test_config.py

* Add unit test to test_config.py to verify that PosixPath and WindowsPath (depending on system) both work when converted to JSON

* Remove distinction between PosixPath and WindowsPath in ConfigMixIn.to_json_string(). Conditional now tests for Path, and uses Path.as_posix() to convert to string.

---------

Co-authored-by: Vincent Dovydaitis <vincedovy@gmail.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-12-23 13:02:13 +05:30
Álvaro Somoza
26d6d995a4 Modify FlowMatch Scale Noise (#8678) 
* initial fix

* apply suggestion

* delete step_index line
 2024-12-23 13:02:13 +05:30
Sayak Paul
ac2d23da6b [Release notification] add some info when there is an error. (#8718) 
add some info when there is an error.
 2024-12-23 13:02:13 +05:30
Sayak Paul
91b58caea1 modify PR and issue templates (#8687) 
* modify PR and issue templates

* add single file poc.
 2024-12-23 13:02:13 +05:30
Sayak Paul
24f124928e [LoRA] fix conversion utility so that lora dora loads correctly (#8688) 
fix conversion utility so that lora dora loads correctly
 2024-12-23 13:02:13 +05:30
Dhruv Nair
cb6b3458b0 Update xformers SD3 test (#8712) 
update
 2024-12-23 13:02:13 +05:30
Sayak Paul
202defda7c [LoRA] fix vanilla fine-tuned lora loading. (#8691) 
fix vanilla fine-tuned lora loading.
 2024-12-23 13:02:13 +05:30
Sayak Paul
23145f2d9b [Chore] remove deprecation from transformer2d regarding the output class. (#8698) 
* remove deprecation from transformer2d regarding the output class.

* up

* deprecate more
 2024-12-23 13:02:13 +05:30
Donald.Lee
027d73f60a Fix: unet save_attn_procs at UNet2DconditionLoadersMixin (#8699) 
* fix: unet save_attn_procs at custom diffusion

* style: recover unchanaged parts(max line length 119) / mod: add condition

* style: recover unchanaged parts(max line length 119)

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-12-23 13:02:13 +05:30
Sayak Paul
4cb34081e5 [Observability] add reporting mechanism when mirroring community pipelines. (#8676) 
* add reporting mechanism when mirroring community pipelines.

* remove unneeded argument

* get the actual PATH_IN_REPO

* don't need tag
 2024-12-23 13:02:13 +05:30