Commits · e02ec27e51751a28a4fa1e0d95537f824d523bbe · renzhc / diffusers_dcu

18 Jul, 2024 2 commits
- [Core] remove `resume_download` from Hub related stuff (#8648) · e02ec27e
  Sayak Paul authored Jul 18, 2024
```
* remove resume_download

* fix: _fetch_index_file call.

* remove resume_download from docs.
```
  e02ec27e
- [Chore] add disable forward chunking to SD3 transformer. (#8838) · a41e4c50
  Sayak Paul authored Jul 18, 2024
```
add disable forward chunking to SD3 transformer.
```
  a41e4c50
12 Jul, 2024 2 commits
- [Docs] add AuraFlow docs (#8851) · 973a62d4
  Sayak Paul authored Jul 12, 2024
```
* add pipeline documentation.

* add api spec for pipeline

* model documentation

* model spec
```
  973a62d4
- Add single file loading support for AnimateDiff (#8819) · 11d18f32
  Dhruv Nair authored Jul 12, 2024
```
* update

* update

* update

* update
```
  11d18f32
11 Jul, 2024 4 commits

Add VAE tiling option for SD3 (#8791) · d2df40c6
Dhruv Nair authored Jul 12, 2024
```
update
```
d2df40c6

Sayak Paul authored Jul 11, 2024



* add lavender flow transformer

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

2261510b

Latte: Latent Diffusion Transformer for Video Generation (#8404) · b8cf84a3

Xin Ma authored Jul 11, 2024



* 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>

b8cf84a3

Reformat docstring for `get_timestep_embedding` (#8811) · 673eb60f

Alan Du authored Jul 10, 2024



* Reformat docstring for `get_timestep_embedding`


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

673eb60f

08 Jul, 2024 2 commits

Remove unnecessary lines (#8569) · 57084dac

Tolga Cangöz authored Jul 08, 2024



* Remove unused line


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

57084dac

[Alpha-VLLM Team] Add Lumina-T2X to diffusers (#8652) · 98388670

PommesPeter authored Jul 08, 2024




---------
Co-authored-by: zhuole1025 <zhuole1025@gmail.com>
Co-authored-by: YiYi Xu <yixu310@gmail.com>

98388670

06 Jul, 2024 1 commit

fix loading sharded checkpoints from subfolder (#8798) · 9e9ed353

YiYi Xu authored Jul 06, 2024



* fix load sharded checkpoints from subfolder{

* style

* os.path.join

* add a small test

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

9e9ed353

04 Jul, 2024 1 commit
- [Tests] fix sharding tests (#8764) · 31adeb41
  Sayak Paul authored Jul 04, 2024
```
fix sharding tests
```
  31adeb41
03 Jul, 2024 4 commits

[Tencent Hunyuan Team] Add checkpoint conversion scripts and changed controlnet (#8783) · 6b6b4bcf

XCL authored Jul 04, 2024



* add conversion files; changed controlnet for hunyuandit

* style

---------
Co-authored-by: xingchaoliu <xingchaoliu@tencent.com>
Co-authored-by: yiyixuxu <yixu310@gmail.com>

6b6b4bcf

[Chore] add dummy lora attention processors to prevent failures in other libs (#8777) · 06ee4db3
Sayak Paul authored Jul 03, 2024
```
add dummy lora attention processors to prevent failures in other libs
```
06ee4db3
Revert "[LoRA] introduce `LoraBaseMixin` to promote reusability." (#8773) · 984d3405
Sayak Paul authored Jul 03, 2024
```
Revert "[LoRA] introduce `LoraBaseMixin` to promote reusability. (#8670)"

This reverts commit a2071a18.
```
984d3405

[LoRA] introduce `LoraBaseMixin` to promote reusability. (#8670) · a2071a18

Sayak Paul authored Jul 03, 2024

* 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

a2071a18

02 Jul, 2024 3 commits

correct `attention_head_dim` for `JointTransformerBlock` (#8608) · d9f71ab3

YiYi Xu authored Jul 02, 2024



* 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>

d9f71ab3

Fix warning in UNetMotionModel (#8756) · c104482b

Dhruv Nair authored Jul 02, 2024



* 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>

c104482b

[hunyuan-dit] refactor `HunyuanCombinedTimestepTextSizeStyleEmbedding` (#8761) · 8b1e3ec9
YiYi Xu authored Jul 01, 2024
```
up
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
```
8b1e3ec9

01 Jul, 2024 2 commits

Allow from_transformer in SD3ControlNetModel (#8749) · 0bae6e44
Haofan Wang authored Jul 02, 2024
```
* Update controlnet_sd3.py

---------
Co-authored-by: YiYi Xu <yixu310@gmail.com>
```
0bae6e44

[Tencent Hunyuan Team] Add HunyuanDiT-v1.2 Support (#8747) · a3904d7e

XCL authored Jul 01, 2024



* add v1.2 support

---------
Co-authored-by: xingchaoliu <xingchaoliu@tencent.com>
Co-authored-by: yiyixuxu <yixu310@gmail.com>

a3904d7e

27 Jun, 2024 2 commits

[Chore] perform better deprecation for vqmodeloutput (#8719) · d5dd8df3
Sayak Paul authored Jun 27, 2024
```
perform better deprecation for vqmodeloutput
```
d5dd8df3

Motion Model / Adapter versatility (#8301) · 3e0d128d

Mathis Koroglu authored Jun 27, 2024

* 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

3e0d128d

26 Jun, 2024 2 commits
- [Chore] remove deprecation from transformer2d regarding the output class. (#8698) · 10b4e354
  Sayak Paul authored Jun 26, 2024
```
* remove deprecation from transformer2d regarding the output class.

* up

* deprecate more
```
  10b4e354
- [Tencent Hunyuan Team] Add Hunyuan-DiT ControlNet Inference (#8694) · fa2abfdb
  XCL authored Jun 26, 2024
```
* add controlnet support

---------
Co-authored-by: xingchaoliu <xingchaoliu@tencent.com>
Co-authored-by: yiyixuxu <yixu310@gmail,com>
```
  fa2abfdb
25 Jun, 2024 1 commit

add PAG support (#7944) · 540399f5

YiYi Xu authored Jun 25, 2024



* first draft


---------
Co-authored-by: yiyixuxu <yixu310@gmail,com>
Co-authored-by: Junhwa Song <ethan9867@gmail.com>
Co-authored-by: Ahn Donghoon (안동훈 / suno) <suno.vivid@gmail.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

540399f5

24 Jun, 2024 1 commit

Errata - Fix typos & improve contributing page (#8572) · c375903d

Tolga Cangöz authored Jun 24, 2024



* Fix typos & improve contributing page

* `make style && make quality`

* fix typos

* Fix typo

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

c375903d

21 Jun, 2024 2 commits

[LoRA] get rid of the legacy lora remnants and make our codebase lighter (#8623) · 8eb17315

Sayak Paul authored Jun 21, 2024

* get rid of the legacy lora remnants and make our codebase lighter

* fix depcrecated lora argument

* fix

* empty commit to trigger ci

* remove print

* empty

8eb17315

a few fix for shard checkpoints (#8656) · c71c19c5
YiYi Xu authored Jun 20, 2024
```
fix
Co-authored-by: yiyixuxu <yixu310@gmail,com>
```
c71c19c5

20 Jun, 2024 1 commit

[LoRA SD3] add support for lora fusion in sd3 (#8616) · 668e34c6

Sayak Paul authored Jun 20, 2024

* add support for lora fusion in sd3

* add test to ensure fused lora and effective lora produce same outpouts

668e34c6

19 Jun, 2024 1 commit
- Support SD3 ControlNet and Multi-ControlNet. (#8566) · e5564d45
  王奇勋 authored Jun 19, 2024
```
* sd3 controlnet



---------
Co-authored-by: haofanwang <haofanwang.ai@gmail.com>
```
  e5564d45
18 Jun, 2024 5 commits
- Fix gradient checkpointing issue for Stable Diffusion 3 (#8542) · 3376252d
  Carolinabanana authored Jun 18, 2024
```
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: YiYi Xu <yixu310@gmail.com>
```
  3376252d
- add sd1.5 compatibility to controlnet-xs and fix unused_parameters error during training (#8606) · 16170c69
  Yongsen Mao authored Jun 19, 2024
```
* add sd1.5 compatibility to controlnet-xs

* set use_linear_projection by base_block

* refine code style
```
  16170c69
- self.upsample = Upsample1D (#8580) · 4408047a
  kkj15dk authored Jun 18, 2024
```
Making self.upsample actually be Upsample1D
```
  4408047a
- [Core] Add `shift_factor` to SD3 tiny autoencoder (#8618) · cd308200
  Sayak Paul authored Jun 18, 2024
```
* shift factor argument to tiny

* remove shift factor rejigging from the sd3 docs
```
  cd308200
- Fix sharding when no device_map is passed (#8531) · 96399c3e
  Marc Sun authored Jun 18, 2024
```
* Fix sharding when no device_map is passed

* style

* add tests

* align

* add docstring

* format

---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
```
  96399c3e
13 Jun, 2024 1 commit
- Fix duplicate variable assignments in SD3's JointAttnProcessor (#8516) · 896fb6d8
  ちくわぶ authored Jun 13, 2024
```
* Fix duplicate variable assignments.

* Fix duplicate variable assignments.
```
  896fb6d8
12 Jun, 2024 3 commits

fix warning log for Transformer SD3 (#8496) · 6cf0be5d
Sayak Paul authored Jun 12, 2024
```
fix warning log
```
6cf0be5d
fix dual transformer2d import (#8491) · ec068f9b
Sayak Paul authored Jun 12, 2024
```
fix
```
ec068f9b

Add Stable Diffusion 3 (#8483) · 04717fd8

Dhruv Nair authored Jun 13, 2024



* up

* add sd3

* update

* update

* add tests

* fix copies

* fix docs

* update

* add dreambooth lora

* add LoRA

* update

* update

* update

* update

* import fix

* update

* Update src/diffusers/pipelines/stable_diffusion_3/pipeline_stable_diffusion_3.py
Co-authored-by: YiYi Xu <yixu310@gmail.com>

* import fix 2

* update

* Update src/diffusers/models/autoencoders/autoencoder_kl.py
Co-authored-by: YiYi Xu <yixu310@gmail.com>

* Update src/diffusers/models/autoencoders/autoencoder_kl.py
Co-authored-by: YiYi Xu <yixu310@gmail.com>

* Update src/diffusers/models/autoencoders/autoencoder_kl.py
Co-authored-by: YiYi Xu <yixu310@gmail.com>

* Update src/diffusers/models/autoencoders/autoencoder_kl.py
Co-authored-by: YiYi Xu <yixu310@gmail.com>

* Update src/diffusers/models/autoencoders/autoencoder_kl.py
Co-authored-by: YiYi Xu <yixu310@gmail.com>

* Update src/diffusers/models/autoencoders/autoencoder_kl.py
Co-authored-by: YiYi Xu <yixu310@gmail.com>

* Update src/diffusers/models/autoencoders/autoencoder_kl.py
Co-authored-by: YiYi Xu <yixu310@gmail.com>

* Update src/diffusers/models/autoencoders/autoencoder_kl.py
Co-authored-by: YiYi Xu <yixu310@gmail.com>

* Update src/diffusers/models/autoencoders/autoencoder_kl.py
Co-authored-by: YiYi Xu <yixu310@gmail.com>

* Update src/diffusers/models/autoencoders/autoencoder_kl.py
Co-authored-by: YiYi Xu <yixu310@gmail.com>

* Update src/diffusers/models/autoencoders/autoencoder_kl.py
Co-authored-by: YiYi Xu <yixu310@gmail.com>

* update

* update

* update

* fix ckpt id

* fix more ids

* update

* missing doc

* Update src/diffusers/schedulers/scheduling_flow_match_euler_discrete.py
Co-authored-by: YiYi Xu <yixu310@gmail.com>

* Update src/diffusers/schedulers/scheduling_flow_match_euler_discrete.py
Co-authored-by: YiYi Xu <yixu310@gmail.com>

* Update docs/source/en/api/pipelines/stable_diffusion/stable_diffusion_3.md
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* Update docs/source/en/api/pipelines/stable_diffusion/stable_diffusion_3.md
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* update'

* fix

* update

* Update src/diffusers/models/autoencoders/autoencoder_kl.py

* Update src/diffusers/models/autoencoders/autoencoder_kl.py

* note on gated access.

* requirements

* licensing

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

04717fd8