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
3,427 Commits 742 Branches 94 Tags
2686fddbf1e358dd017ccd43cfc587f9c481463d
Commit Graph

3427 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Dhruv Nair
2686fddbf1 update 2023-12-22 13:54:32 +00:00
Dhruv Nair
2afad1541b Merge branch 'main' into refactor-single-file 2023-12-22 11:44:58 +00:00
Bingxin Ke
3369bc810a [Community Pipeline] Add Marigold Monocular Depth Estimation (#6249) 
* [Community Pipeline] Add Marigold Monocular Depth Estimation

- add single-file pipeline
- update README

* fix format - add one blank line

* format script with ruff

* use direct image link in example code

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2023-12-22 15:41:46 +05:30
Pedro Cuenca
7fe47596af Allow diffusers to load with Flax, w/o PyTorch (#6272) 2023-12-22 09:37:30 +01:00
Dhruv Nair
59d1caa238 Remove peft tests from old lora backend tests (#6273) 
update
 2023-12-22 13:35:52 +05:30
Dhruv Nair
c022e52923 Remove ONNX inpaint legacy (#6269) 
update

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2023-12-22 13:35:21 +05:30
Will Berman
4039815276 open muse (#5437) 
amused

rename

Update docs/source/en/api/pipelines/amused.md

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

AdaLayerNormContinuous default values

custom micro conditioning

micro conditioning docs

put lookup from codebook in constructor

fix conversion script

remove manual fused flash attn kernel

add training script

temp remove training script

add dummy gradient checkpointing func

clarify temperatures is an instance variable by setting it

remove additional SkipFF block args

hardcode norm args

rename tests folder

fix paths and samples

fix tests

add training script

training readme

lora saving and loading

non-lora saving/loading

some readme fixes

guards

Update docs/source/en/api/pipelines/amused.md

Co-authored-by: Suraj Patil <surajp815@gmail.com>

Update examples/amused/README.md

Co-authored-by: Suraj Patil <surajp815@gmail.com>

Update examples/amused/train_amused.py

Co-authored-by: Suraj Patil <surajp815@gmail.com>

vae upcasting

add fp16 integration tests

use tuple for micro cond

copyrights

remove casts

delegate to torch.nn.LayerNorm

move temperature to pipeline call

upsampling/downsampling changes
 2023-12-21 11:40:55 -08:00
Sayak Paul
5b186b7128 [Refactor] move ldm3d out of stable_diffusion. (#6263) 
ldm3d.
 2023-12-21 18:59:55 +05:30
Sayak Paul
ab0459f2b7 [Deprecated pipelines] remove pix2pix zero from init (#6268) 
remove pix2pix zero from init
 2023-12-21 18:17:28 +05:30
Sayak Paul
9c7cc36011 [Refactor] move panorama out of stable_diffusion (#6262) 
* move panorama out.

* fix: diffedit

* fix: import.

* fix: impirt
 2023-12-21 18:17:05 +05:30
Sayak Paul
325f6c53ed [Refactor] move attend and excite out of stable_diffusion. (#6261) 
* move attend and excite out.

* fix: import

* fix diffedit
 2023-12-21 16:49:32 +05:30
Benjamin Bossan
43979c2890 TST Fix LoRA test that fails with PEFT >= 0.7.0 (#6216) 
See #6185 for context.

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2023-12-21 11:50:05 +01:00
Sayak Paul
9ea6ac1b07 [Refactor] move sag out of stable_diffusion (#6264) 
move sag out of .
 2023-12-21 16:09:49 +05:30
Sayak Paul
2c34c7d6dd [Refactor] move gligen out of stable diffusion. (#6265) 
* move gligen out of stable diffusion.

* fix: import

* fix import module
 2023-12-21 15:26:52 +05:30
Sayak Paul
bffadde126 [Refactor] move k diffusion out of stable_diffusion (#6267) 
move k diffusion out of stable_diffusion
 2023-12-21 15:24:24 +05:30
YShow
35a969d297 [Training] remove depcreated method from lora scripts again (#6266) 
* remove depcreated method from lora scripts

* check code quality
 2023-12-21 14:17:52 +05:30
sayakpaul
c5ff469d0e Revert "move attend and excite out of stable_diffusion" 
This reverts commit bcecfbc873.
 2023-12-21 12:35:58 +05:30
sayakpaul
bcecfbc873 move attend and excite out of stable_diffusion 2023-12-21 12:35:09 +05:30
Sayak Paul
6269045c5b [Refactor] move diffedit out of stable_diffusion (#6260) 
* move diffedit out of stable_diffuson

* fix: import

* style

* fix: import
 2023-12-21 12:26:36 +05:30
lvzi
6ca9c4af05 fix: unscale fp16 gradient problem & potential error (#6086) (#6231) 
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2023-12-21 09:09:26 +05:30
dependabot[bot]
0532cece97 Bump transformers from 4.34.0 to 4.36.0 in /examples/research_projects/realfill (#6255) 
Bump transformers in /examples/research_projects/realfill

Bumps [transformers](https://github.com/huggingface/transformers) from 4.34.0 to 4.36.0.
- [Release notes](https://github.com/huggingface/transformers/releases)
- [Commits](https://github.com/huggingface/transformers/compare/v4.34.0...v4.36.0)

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

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
 2023-12-21 09:03:17 +05:30
Sayak Paul
22b45304bf [Refactor upsamplers and downsamplers] separate out upsamplers and downsamplers. (#6128) 
* separate out upsamplers and downsamplers.

* import all the necessary blocks in resnet for backward comp.

* move upsample2d and downsample2d to utils.

* move downsample_2d to downsamplers.py

* apply feedback

* fix import

* samplers -> sampling
 2023-12-20 21:01:33 +05:30
Beinsezii
457abdf2cf EulerAncestral add rescale_betas_zero_snr (#6187) 
* EulerAncestral add `rescale_betas_zero_snr`

Uses same infinite sigma fix from EulerDiscrete. Interestingly the
ancestral version had the opposite problem: too much contrast instead of
too little.

* UT for EulerAncestral `rescale_betas_zero_snr`

* EulerAncestral upcast samples during step()

It helps this scheduler too, particularly when the model is using bf16.

While the noise dtype is still the model's it's automatically upcasted
for the add so all it affects is determinism.

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2023-12-20 13:09:25 +05:30
hako-mikan
ff43dba7ea [Fix] Fix Regional Prompting Pipeline (#6188) 
* Update regional_prompting_stable_diffusion.py

* reformat

* reformat

* reformat

* reformat

* reformat

* reformat

* reformat

* regormat

* reformat

* reformat

* reformat

* reformat

* Update regional_prompting_stable_diffusion.py

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2023-12-20 10:37:19 +05:30
Steven Liu
5433962992 [docs] Batched seeds (#6237) 
batched seed
 2023-12-19 16:50:18 -08:00
raven
df476d9f63 [Docs] Fix a code example in the ControlNet Inpainting documentation (#6236) 
fix document on masked image in inpainting controlnet
 2023-12-19 13:14:37 -08:00
YiYi Xu
3e71a20650 [refactor embeddings]pixart-alpha (#6212) 
pixart-alpha

Co-authored-by: yiyixuxu <yixu310@gmail,com>
 2023-12-19 07:07:24 -10:00
Sayak Paul
bf40d7d82a add peft dependency to fast push tests (#6229) 
* add peft dependency

* add peft dependency at the correct place.
 2023-12-19 13:26:25 +05:30
Dhruv Nair
0105fc4ef3 update 2023-12-19 07:20:24 +00:00
Dhruv Nair
32ff4773d4 ControlNetXS fixes. (#6228) 
update
 2023-12-19 11:58:34 +05:30
Sayak Paul
288ceebea5 [T2I LoRA training] fix: unscale fp16 gradient problem (#6119) 
* fix: unscale fp16 gradient problem

* fix for dreambooth lora sdxl

* make the type-casting conditional.

* Apply suggestions from code review

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

---------

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
 2023-12-19 09:54:17 +05:30
Sayak Paul
9221da4063 fix: init for vae during pixart tests (#6215) 
* fix: init for vae during pixart tests

* print the values

* add flatten

* correct assertion value for test_inference

* correct assertion values for test_inference_non_square_images

* run styling

* debug test_inference_with_multiple_images_per_prompt

* fix assertion values for test_inference_with_multiple_images_per_prompt
 2023-12-18 18:16:57 -10:00
YiYi Xu
57fde871e1 offload the optional module image_encoder (#6151) 
* offload image_encoder

* add test

---------

Co-authored-by: yiyixuxu <yixu310@gmail,com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2023-12-18 15:10:01 -10:00
Fabio Rigano
68e962395c Add converter method for ip adapters (#6150) 
* Add converter method for ip adapters

* Move converter method

* Update to image proj converter

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2023-12-18 13:46:43 -10:00
Dhruv Nair
781775ea56 Slow Test for Pipelines minor fixes (#6221) 
update
 2023-12-19 00:45:51 +05:30
Patrick von Platen
fa3c86beaf [SVD] Fix guidance scale (#6002) 
* [SVD] Fix guidance scale

* make style
 2023-12-18 19:33:24 +01:00
Haofan Wang
7d0a47f387 Update train_text_to_image_lora.py (#6144) 
* Update train_text_to_image_lora.py

* Fix typo?

---------

Co-authored-by: M. Tolga Cangöz <46008593+standardAI@users.noreply.github.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2023-12-18 19:33:05 +01:00
Aryan V S
67b3d3267e Support img2img and inpaint in lpw-xl (#6114) 
* add img2img and inpaint support to lpw-xl

* update community README

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2023-12-18 19:19:11 +01:00
TilmannR
4e77056885 Update README.md (#6191) 
Typo: The script for LoRA training is `train_text_to_image_lora_prior.py` not `train_text_to_image_prior_lora.py`.

Alternatively you could rename the file and keep the README.md unchanged.
 2023-12-18 19:08:29 +01:00
Dhruv Nair
a0c54828a1 Deprecate Pipelines (#6169) 
* deprecate pipe

* make style

* update

* add deprecation message

* format

* remove tests for deprecated pipelines

* remove deprecation message

* make style

* fix copies

* clean up

* clean

* clean

* clean

* clean up

* clean up

* clean up toctree

* clean up

---------

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
 2023-12-18 23:08:29 +05:30
Patrick von Platen
8d891e6e1b [Torch Compile] Fix torch compile for svd vae (#6217) 2023-12-18 18:21:17 +01:00
Patrick von Platen
cce1fe2d41 [Text-to-Video] Clean up pipeline (#6213) 
* make style

* make style

* make style

* make style
 2023-12-18 18:21:09 +01:00
Abin Thomas
d816bcb5e8 Fix t2i. blog url (#6205) 2023-12-18 09:12:28 -08:00
d8ahazard
6976cab7ca Fix possible re-conversion issues after extracting from safetensors (#6097) 
* Fix possible re-conversion issues after extracting from diffusers

Properly rename specific vae keys.

* Whoops
 2023-12-18 11:51:20 +01:00
Dhruv Nair
fcbed3fa79 Fix SDXL Inpainting from single file with Refiner Model (#6147) 
* update

* update

* update
 2023-12-18 11:45:37 +01:00
Sayak Paul
b98b314b7a [Training] remove depcreated method from lora scripts. (#6207) 
remove depcreated method from lora scripts.
 2023-12-18 15:52:43 +05:30
Omar Sanseviero
74558ff65b Nit fix to training params (#6200) 2023-12-18 11:06:16 +01:00
Yudong Jin
49644babd3 Fix the test script in examples/text_to_image/README.md (#6209) 
* Update examples/text_to_image/README.md

* Update examples/text_to_image/README.md

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

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2023-12-18 15:36:00 +05:30
Sayak Paul
56b3b21693 [Refactor autoencoders] feat: introduce autoencoders module (#6129) 
* feat: introduce autoencoders module

* more changes for styling and copy fixing

* path changes in the docs.

* fix: import structure in init.

* fix controlnetxs import
 2023-12-18 12:42:15 +05:30
Sayak Paul
9cef07da5a [Benchmarks] fix: lcm benchmarking reporting (#6198) 
* fix: lcm benchmarking reporting

* fix generate_csv_dict call.
 2023-12-17 15:32:11 +05:30