AI/diffusers
1
0
Fork 0
mirror of https://github.com/huggingface/diffusers.git synced 2026-01-29 07:22:12 +03:00
Code Activity
5,503 Commits 742 Branches 94 Tags
modular-refactor-custom-code
Commit Graph

1418 Commits

Author SHA1 Message Date
Yoach Lacombe
ea1b4ea7ca Fix Stable Audio repository id (#9016) 
Fix Stable Audio repo id
 2024-07-30 23:17:44 +05:30
Aryan
e5b94b4c57 [core] Move community AnimateDiff ControlNet to core (#8972) 
* add animatediff controlnet to core

* make style; remove unused method

* fix copied from comment

* add tests

* changes to make tests work

* add utility function to load videos

* update docs

* update pipeline example

* make style

* update docs with example

* address review comments

* add latest freeinit test from #8969

* LoraLoaderMixin -> StableDiffusionLoraLoaderMixin

* fix docs

* Update src/diffusers/utils/loading_utils.py

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

* fix: variable out of scope

---------

Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>
 2024-07-30 17:10:37 +05:30
Yoach Lacombe
69e72b1dd1 Stable Audio integration (#8716) 
* WIP modeling code and pipeline

* add custom attention processor + custom activation + add to init

* correct ProjectionModel forward

* add stable audio to __initèè

* add autoencoder and update pipeline and modeling code

* add half Rope

* add partial rotary v2

* add temporary modfis to scheduler

* add EDM DPM Solver

* remove TODOs

* clean GLU

* remove att.group_norm to attn processor

* revert back src/diffusers/schedulers/scheduling_dpmsolver_multistep.py

* refactor GLU -> SwiGLU

* remove redundant args

* add channel multiples in autoencoder docstrings

* changes in docsrtings and copyright headers

* clean pipeline

* further cleaning

* remove peft and lora and fromoriginalmodel

* Delete src/diffusers/pipelines/stable_audio/diffusers.code-workspace

* make style

* dummy models

* fix copied from

* add fast oobleck tests

* add brownian tree

* oobleck autoencoder slow tests

* remove TODO

* fast stable audio pipeline tests

* add slow tests

* make style

* add first version of docs

* wrap is_torchsde_available to the scheduler

* fix slow test

* test with input waveform

* add input waveform

* remove some todos

* create stableaudio gaussian projection + make style

* add pipeline to toctree

* fix copied from

* make quality

* refactor timestep_features->time_proj

* refactor joint_attention_kwargs->cross_attention_kwargs

* remove forward_chunk

* move StableAudioDitModel to transformers folder

* correct convert + remove partial rotary embed

* apply suggestions from yiyixuxu -> removing attn.kv_heads

* remove temb

* remove cross_attention_kwargs

* further removal of cross_attention_kwargs

* remove text encoder autocast to fp16

* continue removing autocast

* make style

* refactor how text and audio are embedded

* add paper

* update example code

* make style

* unify projection model forward + fix device placement

* make style

* remove fuse qkv

* apply suggestions from review

* Update src/diffusers/pipelines/stable_audio/pipeline_stable_audio.py

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

* make style

* smaller models in fast tests

* pass sequential offloading fast tests

* add docs for vae and autoencoder

* make style and update example

* remove useless import

* add cosine scheduler

* dummy classes

* cosine scheduler docs

* better description of scheduler

---------

Co-authored-by: YiYi Xu <yixu310@gmail.com>
 2024-07-30 15:29:06 +05:30
Álvaro Somoza
73acebb8cf [Kolors] Add IP Adapter (#8901) 
* initial draft

* apply suggestions

* fix failing test

* added ipa to img2img

* add docs

* apply suggestions
 2024-07-26 14:25:44 -04:00
Aryan
5c53ca5ed8 [core] AnimateDiff SparseCtrl (#8897) 
* initial sparse control model draft

* remove unnecessary implementation

* copy animatediff pipeline

* remove deprecated callbacks

* update

* update pipeline implementation progress

* make style

* make fix-copies

* update progress

* add partially working pipeline

* remove debug prints

* add model docs

* dummy objects

* improve motion lora conversion script

* fix bugs

* update docstrings

* remove unnecessary model params; docs

* address review comment

* add copied from to zero_module

* copy animatediff test

* add fast tests

* update docs

* update

* update pipeline docs

* fix expected slice values

* fix license

* remove get_down_block usage

* remove temporal_double_self_attention from get_down_block

* update

* update docs with org and documentation images

* make from_unet work in sparsecontrolnetmodel

* add latest freeinit test from #8969

* make fix-copies

* LoraLoaderMixin -> StableDiffsuionLoraLoaderMixin
 2024-07-26 17:46:05 +05:30
Aryan
57a021d5e4 [fix] FreeInit step index out of bounds (#8969) 
* fix step index out of bounds

* add test for free_init with different schedulers

* add test to vid2vid and pia
 2024-07-26 16:45:55 +05:30
Sayak Paul
d87fe95f90 [Chore] add LoraLoaderMixin to the inits (#8981) 
* 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

* rewrite fuse_lora a bit.

* feedback

* copy over load_lora_into_text_encoder.

* address dhruv's feedback.

* fix-copies

* fix issubclass.

* num_fused_loras

* fix

* fix

* remove mapping

* up

* fix

* style

* fix-copies

* change to SD3TransformerLoRALoadersMixin

* Apply suggestions from code review

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

* up

* handle wuerstchen

* up

* move lora to lora_pipeline.py

* up

* fix-copies

* fix documentation.

* comment set_adapters().

* fix-copies

* fix set_adapters() at the model level.

* fix?

* fix

* loraloadermixin.

---------

Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>
 2024-07-26 08:59:33 +05:30
YiYi Xu
62863bb1ea Revert "[LoRA] introduce LoraBaseMixin to promote reusability." (#8976) 
Revert "[LoRA] introduce LoraBaseMixin to promote reusability. (#8774)"

This reverts commit 527430d0a4.
 2024-07-25 09:10:35 -10:00
Sayak Paul
527430d0a4 [LoRA] introduce LoraBaseMixin to promote reusability. (#8774) 
* 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

* rewrite fuse_lora a bit.

* feedback

* copy over load_lora_into_text_encoder.

* address dhruv's feedback.

* fix-copies

* fix issubclass.

* num_fused_loras

* fix

* fix

* remove mapping

* up

* fix

* style

* fix-copies

* change to SD3TransformerLoRALoadersMixin

* Apply suggestions from code review

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

* up

* handle wuerstchen

* up

* move lora to lora_pipeline.py

* up

* fix-copies

* fix documentation.

* comment set_adapters().

* fix-copies

* fix set_adapters() at the model level.

* fix?

* fix

---------

Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>
 2024-07-25 21:40:58 +05:30
Aryan
3ae0ee88d3 [tests] speed up animatediff tests (#8846) 
* speed up animatediff tests

* fix pia test_ip_adapter_single

* fix tests/pipelines/pia/test_pia.py::PIAPipelineFastTests::test_dict_tuple_outputs_equivalent

* update

* fix ip adapter tests

* skip test_from_pipe_consistent_config tests

* fix prompt_embeds test

* update test_from_pipe_consistent_config tests

* fix expected_slice values

* remove temporal_norm_num_groups from UpBlockMotion

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>
 2024-07-25 17:35:43 +05:30
Sayak Paul
d8bcb33f4b [Tests] fix slices of 26 tests (first half) (#8959) 
* check for assertions.

* update with correct slices.

* okay

* style

* get it ready

* update

* update

* update

---------

Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>
 2024-07-25 14:56:49 +05:30
Dhruv Nair
93983b6780 [CI] Skip flaky download tests in PR CI (#8945) 
update
 2024-07-24 09:25:06 +05:30
Sayak Paul
41b705f42d remove residual i from auraflow. (#8949) 
* remove residual i.

* rename to aura_flow in pipeline test
 2024-07-24 07:31:54 +05:30
Sayak Paul
50d21f7c6a [Core] fix QKV fusion for attention (#8829) 
* start debugging the problem,

* start

* fix

* fix

* fix imports.

* handle hunyuan

* remove residuals.

* add a check for making sure there's appropriate procs.

* add more rigor to the tests.

* fix test

* remove redundant check

* fix-copies

* move check_qkv_fusion_matches_attn_procs_length and check_qkv_fusion_processors_exist.
 2024-07-24 06:52:19 +05:30
Vinh H. Pham
7a95f8d9d8 [Tests] Improve transformers model test suite coverage - Temporal Transformer (#8932) 
* add test for temporal transformer

* remove unused variable

* fix code quality

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-07-23 15:36:30 +05:30
Aritra Roy Gosthipaty
8b21feed42 [Tests] reduce the model size in the audioldm2 fast test (#7846) 
* chore: initial model size reduction

* chore: fixing expected values for failing tests

* requested edits

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-07-23 14:34:07 +05:30
Sayak Paul
af400040f5 [Tests] proper skipping of request caching test (#8908) 
proper skipping of request caching test
 2024-07-22 12:52:57 -10:00
shinetzh
3b04cdc816 fix loop bug in SlicedAttnProcessor (#8836) 
* fix loop bug in SlicedAttnProcessor


---------

Co-authored-by: neoshang <neoshang@tencent.com>
 2024-07-19 18:14:29 -10:00
Sayak Paul
0f09b01ab3 [Core] fix: shard loading and saving when variant is provided. (#8869) 
fix: shard loading and saving when variant is provided.
 2024-07-17 08:26:28 +05:30
Tolga CangΓΆz
e87bf62940 [Cont'd] Add the SDE variant of ~~DPM-Solver~~ and DPM-Solver++ to DPM Single Step (#8269) 
* Add the SDE variant of DPM-Solver and DPM-Solver++ to DPM Single Step


---------

Co-authored-by: cmdr2 <secondary.cmdr2@gmail.com>
 2024-07-16 15:40:02 -10:00
Aryan
bbd2f9d4e9 [tests] fix typo in pag tests (#8845) 
* fix typo in pag tests

* fix typo
 2024-07-12 17:41:34 +05:30
NguyΓͺΜƒn CΓ΄ng Tú Anh
d704b3bf8c add PAG support sd15 controlnet (#8820) 
* add pag support sd15 controlnet

* fix quality import

* remove unecessary import

* remove if state

* fix tests

* remove useless function

* add sd1.5 controlnet pag docs

---------

Co-authored-by: anhnct8 <anhnct8@fpt.com>
 2024-07-12 15:42:56 +05:30
Dhruv Nair
11d18f3217 Add single file loading support for AnimateDiff (#8819) 
* update

* update

* update

* update
 2024-07-12 09:51:57 +05:30
Sayak Paul
2261510bbc [Core] Add AuraFlow (#8796) 
* add lavender flow transformer

---------

Co-authored-by: YiYi Xu <yixu310@gmail.com>
 2024-07-11 08:50:19 -10:00
Álvaro Somoza
87b9db644b [Core] Add Kolors (#8812) 
* initial draft
 2024-07-11 06:09:17 -10:00
Xin Ma
b8cf84a3f9 Latte: Latent Diffusion Transformer for Video Generation (#8404) 
* add Latte to diffusers

* remove print

* remove print

* remove print

* remove unuse codes

* remove layer_norm_latte and add a flag

* remove layer_norm_latte and add a flag

* update latte_pipeline

* update latte_pipeline

* remove unuse squeeze

* add norm_hidden_states.ndim == 2: # for Latte

* fixed test latte pipeline bugs

* fixed test latte pipeline bugs

* delete sh

* add doc for latte

* add licensing

* Move Transformer3DModelOutput to modeling_outputs

* give a default value to sample_size

* remove the einops dependency

* change norm2 for latte

* modify pipeline of latte

* update test for Latte

* modify some codes for latte

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* modify for Latte pipeline

* video_length -> num_frames; update prepare_latents copied from

* make fix-copies

* make style

* typo: videe -> video

* update

* modify for Latte pipeline

* modify latte pipeline

* modify latte pipeline

* modify latte pipeline

* modify latte pipeline

* modify for Latte pipeline

* Delete .vscode directory

* make style

* make fix-copies

* add latte transformer 3d to docs _toctree.yml

* update example

* reduce frames for test

* fixed bug of _text_preprocessing

* set num frame to 1 for testing

* remove unuse print

* add text = self._clean_caption(text) again

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: YiYi Xu <yixu310@gmail.com>
Co-authored-by: Aryan <contact.aryanvs@gmail.com>
Co-authored-by: Aryan <aryan@huggingface.co>
 2024-07-11 15:06:22 +05:30
Sayak Paul
a785992c1d [Tests] fix more sharding tests (#8797) 
* fix

* fix

* ugly

* okay

* fix more

* fix oops
 2024-07-09 13:09:36 +05:30
Xu Cao
35cc66dc4c Add pipeline_stable_diffusion_3_inpaint.py for SD3 Inference (#8709) 
* Add pipeline_stable_diffusion_3_inpaint


---------

Co-authored-by: Xu Cao <xucao2@jrehg-work-01.cs.illinois.edu>
Co-authored-by: IrohXu <irohcao@gmail.com>
Co-authored-by: YiYi Xu <yixu310@gmail.com>
 2024-07-08 15:53:02 -10:00
Tolga CangΓΆz
57084dacc5 Remove unnecessary lines (#8569) 
* Remove unused line


---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-07-08 10:42:02 -10:00
PommesPeter
98388670d2 [Alpha-VLLM Team] Add Lumina-T2X to diffusers (#8652) 
---------

Co-authored-by: zhuole1025 <zhuole1025@gmail.com>
Co-authored-by: YiYi Xu <yixu310@gmail.com>
 2024-07-07 17:12:09 -10:00
YiYi Xu
9e9ed353a2 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>
 2024-07-06 11:32:04 -10:00
Dhruv Nair
0bab9d6be7 [Single File] Allow loading T5 encoder in mixed precision (#8778) 
* update

* update

* update

* update
 2024-07-05 10:29:38 +05:30
Sayak Paul
31adeb41cd [Tests] fix sharding tests (#8764) 
fix sharding tests
 2024-07-04 08:50:59 +05:30
Aryan
a7b9634e95 Fix minor bug in SD3 img2img test (#8779) 
fix minor bug in sd3 img2img
 2024-07-03 07:45:37 -10:00
Sayak Paul
984d340534 Revert "[LoRA] introduce LoraBaseMixin to promote reusability." (#8773) 
Revert "[LoRA] introduce `LoraBaseMixin` to promote reusability. (#8670)"

This reverts commit a2071a1837.
 2024-07-03 07:05:01 +05:30
Sayak Paul
a2071a1837 [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
 2024-07-03 07:04:37 +05:30
Shauray Singh
8690e8b9d6 add PAG support for SD architecture (#8725) 
* add pag to sd pipelines
 2024-06-29 09:26:11 -10:00
Dhruv Nair
150142c537 [Tests] Fix precision related issues in slow pipeline tests (#8720) 
update
 2024-06-28 08:13:46 +05:30
Mathis Koroglu
3e0d128da7 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
 2024-06-27 11:11:29 +05:30
vincedovy
a536e775fb 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>
 2024-06-27 10:30:55 +05:30
Dhruv Nair
effe4b9784 Update xformers SD3 test (#8712) 
update
 2024-06-26 10:24:27 -10:00
XCL
fa2abfdb03 [Tencent Hunyuan Team] Add Hunyuan-DiT ControlNet Inference (#8694) 
* add controlnet support

---------

Co-authored-by: xingchaoliu <xingchaoliu@tencent.com>
Co-authored-by: yiyixuxu <yixu310@gmail,com>
 2024-06-26 00:43:03 -10:00
Dhruv Nair
0f0b531827 Add decorator for compile tests (#8703) 
* update

* update

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-06-26 11:26:47 +05:30
YiYi Xu
540399f540 add PAG support (#7944) 
* first draft


---------

Co-authored-by: yiyixuxu <yixu310@gmail,com>
Co-authored-by: Junhwa Song <ethan9867@gmail.com>
Co-authored-by: Ahn Donghoon (μ•ˆλ™ν›ˆ / suno) <suno.vivid@gmail.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
 2024-06-25 08:40:02 -10:00
Sayak Paul
f088027e93 [Marigold tests] add is_flaky decorator to some Marigold tests (#8696) 
okay
 2024-06-25 06:27:28 -10:00
Linoy Tsaban
c6e08ecd46 [Sd3 Dreambooth LoRA] Add text encoder training for the clip encoders (#8630) 
* add clip text-encoder training

* no dora

* text encoder traing fixes

* text encoder traing fixes

* text encoder training fixes

* text encoder training fixes

* text encoder training fixes

* text encoder training fixes

* add text_encoder layers to save_lora

* style

* fix imports

* style

* fix text encoder

* review changes

* review changes

* review changes

* minor change

* add lora tag

* style

* add readme notes

* add tests for clip encoders

* style

* typo

* fixes

* style

* Update tests/lora/test_lora_layers_sd3.py

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

* Update examples/dreambooth/README_sd3.md

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

* minor readme change

---------

Co-authored-by: YiYi Xu <yixu310@gmail.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-06-25 18:00:19 +05:30
Sayak Paul
4ad7a1f5fd [Chore] create a utility for calculating the expected number of shards. (#8692) 
create a utility for calculating the expected number of shards.
 2024-06-25 17:05:39 +05:30
Tolga CangΓΆz
f040c27d4c Errata - Fix typos and improve style (#8571) 
* Fix typos

* Fix typos & up style

* chore: Update numbers

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-06-24 10:07:22 -07:00
Tolga CangΓΆz
138fac703a Discourage using deprecated revision parameter (#8573) 
* Discourage using `revision`

* `make style && make quality`

* Refactor code to use 'variant' instead of 'revision'

* `revision="bf16"` -> `variant="bf16"`

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-06-24 10:06:49 -07:00
Dong
3fca52022f 🎨 fix xl playground device (#8550) 
* 🎨 fix xl playground device

* 🎨 run `make fix-copies`

* 🎨 run `make fix-copies`

* edit xl_controlnet_img2img file

* edit playground img2img test slow

* Update tests/pipelines/stable_diffusion_xl/test_stable_diffusion_xl_img2img.py

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-06-24 16:49:55 +05:30