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
3,587 Commits 740 Branches 94 Tags
318556b20e8fff45ccfb4a0004e513ee4c2d73eb
Commit Graph

911 Commits

Author SHA1 Message Date
YiYi Xu
318556b20e fix dpm related slow test failure (#6680) 
fix

Co-authored-by: yiyixuxu <yixu310@gmail,com>
 2024-01-22 18:52:05 -10:00
Dhruv Nair
6620eda357 Standardise outputs for video pipelines (#6626) 
* update

* update

* update

* update

* update

* update

* update

* clean up

* clean up
 2024-01-23 10:07:07 +05:30
Sayak Paul
1f0705adcf [Big refactor] move unets to unets module 🦋 (#6630) 
* move unets to  module 🦋

* parameterize unet-level import.

* fix flax unet2dcondition model import

* models __init__

* mildly depcrecating models.unet_2d_blocks in favor of models.unets.unet_2d_blocks.

* noqa

* correct depcrecation behaviour

* inherit from the actual classes.

* Empty-Commit

* backwards compatibility for unet_2d.py

* backward compatibility for unet_2d_condition

* bc for unet_1d

* bc for unet_1d_blocks
 2024-01-23 08:57:58 +05:30
Dhruv Nair
d66d554dc2 Add tearDown method to LoRA tests. (#6660) 
* update

* update
 2024-01-22 14:00:37 +05:30
Junsong Chen
c7df846dec add Sa-Solver (#5975) 
* add Sa-Solver



---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: scxue <xueshuchen17@mails.ucas.edu.cn>
Co-authored-by: jschen <chenjunsong4@h-partners.com>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: yiyixuxu <yixu310@gmail,com>
 2024-01-21 21:37:44 -10:00
YiYi Xu
e2773c6255 fix SDXL-kdiffusion tests (#6647) 
🤞🤞🤞

Co-authored-by: yiyixuxu <yixu310@gmail,com>
 2024-01-19 17:37:29 -10:00
YiYi Xu
ac61eefc9f fix DPM Scheduler with use_karras_sigmas option (#6477) 
* fix

---------

Co-authored-by: yiyixuxu <yixu310@gmail,com>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
 2024-01-19 07:08:22 -10:00
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
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
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
YiYi Xu
fefed44543 update slow test for SDXL k-diffusion pipeline (#6588) 
update expected slice
 2024-01-15 18:54:33 -10:00
jquintanilla4
da843b3d53 .load_ip_adapter in StableDiffusionXLAdapterPipeline (#6246) 
* Added testing notebook and .load_ip_adapter to XLAdapterPipeline

* Added annotations

* deleted testing notebook

* Update src/diffusers/pipelines/t2i_adapter/pipeline_stable_diffusion_xl_adapter.py

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

* code clean up

* Add feature_extractor and image_encoder to components

---------

Co-authored-by: YiYi Xu <yixu310@gmail.com>
 2024-01-11 13:04:08 +05:30
antoine-scenario
3e8b63216e Add IP-Adapter to StableDiffusionXLControlNetImg2ImgPipeline (#6293) 
* add IP-Adapter to StableDiffusionXLControlNetImg2ImgPipeline

Update src/diffusers/pipelines/controlnet/pipeline_controlnet_sd_xl_img2img.py

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

fix tests

* fix failing test

---------

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-01-09 22:02:11 -10:00
YiYi Xu
6313645b6b add StableDiffusionXLKDiffusionPipeline (#6447) 
---------

Co-authored-by: yiyixuxu <yixu310@gmail,com>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
 2024-01-09 16:29:01 -10:00
Patrick von Platen
5bacc2f5af [SAG] Support more schedulers, add better error message and make tests faster (#6465) 
* finish

* finish

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-01-09 09:24:38 +05:30
Sayak Paul
ae060fc4f1 [feat] introduce unload_lora(). (#6451) 
* introduce unload_lora.

* fix-copies
 2024-01-05 16:22:11 +05:30
Sayak Paul
0a0bb526aa [LoRA depcrecation] LoRA depcrecation trilogy (#6450) 
* edebug

* debug

* more debug

* more more debug

* remove tests for LoRAAttnProcessors.

* rename
 2024-01-05 15:48:20 +05:30
Sayak Paul
107e02160a [LoRA tests] fix stuff related to assertions arising from the recent changes. (#6448) 
* debug

* debug test_with_different_scales_fusion_equivalence

* use the right method.

* place it right.

* let's see.

* let's see again

* alright then.

* add a comment.
 2024-01-04 12:55:15 +05:30
sayakpaul
6dbef45e6e Revert "debug" 
This reverts commit 7715e6c31c.
 2024-01-04 10:39:38 +05:30
sayakpaul
7715e6c31c debug 2024-01-04 10:39:00 +05:30
sayakpaul
05b3d36a25 Revert "debug" 
This reverts commit fb4aec0ce3.
 2024-01-04 10:38:04 +05:30
sayakpaul
fb4aec0ce3 debug 2024-01-04 10:37:28 +05:30
Sayak Paul
d700140076 [LoRA deprecation] handle rest of the stuff related to deprecated lora stuff. (#6426) 
* handle rest of the stuff related to deprecated lora stuff.

* fix: copies

* don't modify the uNet in-place.

* fix: temporal autoencoder.

* manually remove lora layers.

* don't copy unet.

* alright

* remove lora attn processors from unet3d

* fix: unet3d.

* styl

* Empty-Commit
 2024-01-03 20:54:09 +05:30
Sayak Paul
2e4dc3e25d [LoRA] add: test to check if peft loras are loadable in non-peft envs. (#6400) 
* add: test to check if peft loras are loadable in non-peft envs.

* add torch_device approrpiately.

* fix: get_dummy_inputs().

* test logits.

* rename

* debug

* debug

* fix: generator

* new assertion values after fixing the seed.

* shape

* remove print statements and settle this.

* to update values.

* change values when lora config is initialized under a fixed seed.

* update colab link

* update notebook link

* sanity restored by getting the exact same values without peft.
 2024-01-03 09:57:49 +05:30
Fabio Rigano
86714b72d0 Add unload_ip_adapter method (#6192) 
* Add unload_ip_adapter method

* Update attn_processors with original layers

* Add test

* Use set_default_attn_processor

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-01-02 14:40:46 +01:00
Sayak Paul
61f6c5472a [LoRA] Remove the use of depcrecated loRA functionalities such as LoRAAttnProcessor (#6369) 
* start deprecating loraattn.

* fix

* wrap into unet_lora_state_dict

* utilize text_encoder_lora_params

* utilize text_encoder_attn_modules

* debug

* debug

* remove print

* don't use text encoder for test_stable_diffusion_lora

* load the procs.

* set_default_attn_processor

* fix: set_default_attn_processor call.

* fix: lora_components[unet_lora_params]

* checking for 3d.

* 3d.

* more fixes.

* debug

* debug

* debug

* debug

* more debug

* more debug

* more debug

* more debug

* more debug

* more debug

* hack.

* remove comments and prep for a PR.

* appropriate set_lora_weights()

* fix

* fix: test_unload_lora_sd

* fix: test_unload_lora_sd

* use dfault attebtion processors.

* debu

* debug nan

* debug nan

* debug nan

* use NaN instead of inf

* remove comments.

* fix: test_text_encoder_lora_state_dict_unchanged

* attention processor default

* default attention processors.

* default

* style
 2024-01-02 18:14:04 +05:30
Sayak Paul
6a376ceea2 [LoRA] remove unnecessary components from lora peft test suite (#6401) 
remove unnecessary components from lora peft suite/
 2023-12-30 18:25:40 +05:30
YiYi Xu
4c483deb90 [refactor embeddings] gligen + ip-adapter (#6244) 
* refactor ip-adapter-imageproj, gligen

---------

Co-authored-by: yiyixuxu <yixu310@gmail,com>
 2023-12-27 18:48:42 -10:00
Dhruv Nair
c1e8bdf1d4 Move ControlNetXS into Community Folder (#6316) 
* update

* update

* update

* update

* update

* make style

* remove docs

* update

* move to research folder.

* fix-copies

* remove _toctree entry.

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2023-12-27 08:15:23 +05:30
Will Berman
0af12f1f8a amused update links to new repo (#6344) 
* amused update links to new repo

* lint
 2023-12-26 22:46:28 +01:00
Justin Ruan
6e123688dc Remove unused parameters and fixed FutureWarning (#6317) 
* Remove unused parameters and fixed `FutureWarning`

* Fixed wrong config instance

* update unittest for `DDIMInverseScheduler`
 2023-12-26 22:09:10 +01:00
Dhruv Nair
2026ec0a02 Interruptable Pipelines (#5867) 
* add interruptable pipelines

* add tests

* updatemsmq

* add interrupt property

* make fix copies

* Revert "make fix copies"

This reverts commit 914b35332b.

* add docs

* add tutorial

* Update docs/source/en/tutorials/interrupting_diffusion_process.md

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

* Update docs/source/en/tutorials/interrupting_diffusion_process.md

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

* update

* fix quality issues

* fix

* update

---------

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2023-12-26 22:39:26 +05:30
dg845
3706aa3305 Add rescale_betas_zero_snr Argument to DDPMScheduler (#6305) 
* Add rescale_betas_zero_snr argument to DDPMScheduler.

* Propagate rescale_betas_zero_snr changes to DDPMParallelScheduler.

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2023-12-26 17:54:30 +01:00
Younes Belkada
3aba99af8f [Peft / Lora] Add adapter_names in fuse_lora (#5823) 
* add adapter_name in fuse

* add tesrt

* up

* fix CI

* adapt from suggestion

* Update src/diffusers/utils/testing_utils.py

Co-authored-by: Benjamin Bossan <BenjaminBossan@users.noreply.github.com>

* change to `require_peft_version_greater`

* change variable names in test

* Update src/diffusers/loaders/lora.py

Co-authored-by: Benjamin Bossan <BenjaminBossan@users.noreply.github.com>

* break into 2 lines

* final comments

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: Benjamin Bossan <BenjaminBossan@users.noreply.github.com>
 2023-12-26 16:54:47 +01:00
Sayak Paul
89459a5d56 fix: lora peft dummy components (#6308) 
* fix: lora peft dummy components

* fix: dummy components
 2023-12-25 11:26:45 +05:30
Dhruv Nair
fe574c8b29 LoRA Unfusion test fix (#6291) 
update

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2023-12-24 14:31:48 +05:30
Sayak Paul
90b9479903 [LoRA PEFT] fix LoRA loading so that correct alphas are parsed (#6225) 
* initialize alpha too.

* add: test

* remove config parsing

* store rank

* debug

* remove faulty test
 2023-12-24 09:59:41 +05:30
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
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
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
Dhruv Nair
32ff4773d4 ControlNetXS fixes. (#6228) 
update
 2023-12-19 11:58:34 +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
Dhruv Nair
781775ea56 Slow Test for Pipelines minor fixes (#6221) 
update
 2023-12-19 00:45:51 +05:30
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
cce1fe2d41 [Text-to-Video] Clean up pipeline (#6213) 
* make style

* make style

* make style

* make style
 2023-12-18 18:21:09 +01:00
Sayak Paul
2d94c7838e [Core] feat: enable fused attention projections for other SD and SDXL pipelines (#6179) 
* feat: enable fused attention projections for other SD and SDXL pipelines

* add: test for SD fused projections.
 2023-12-16 08:45:54 +05:30
Dhruv Nair
f5dfe2a8b0 LoRA test fixes (#6163) 
* update

* update

* update

* update

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2023-12-15 08:39:41 +05:30