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
3,793 Commits 740 Branches 94 Tags
01ee0978cc7e56c1ba7ff0e455ec416bcdeb69dc
Commit Graph

3793 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Linoy Tsaban
01ee0978cc [advanced dreambooth lora sdxl] add DoRA training feature (#7072) 
* add is_dora arg

* style

* add dora training feature to sd 1.5 script

* added notes about DoRA training

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-03-04 11:07:54 +01:00
Sayak Paul
56b68459f5 Update requirements.txt to remove huggingface-cli (#7202) 
Internal message: https://huggingface.slack.com/archives/C03Q18WK18T/p1709529892062479
 2024-03-04 11:29:01 +05:30
Vinh H. Pham
2ca264244b adding callback_on_step_end for StableDiffusionLDM3DPipeline (#7149) 
* refactor callback

* run make style

* add copy

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-03-03 18:44:14 -10:00
Sayak Paul
b9e1c30d0e [Docs] more elaborate example for peft torch.compile (#7161) 
more elaborate example for peft torch.compile
 2024-03-04 08:55:30 +05:30
Sayak Paul
03cd62520f feat: add ip adapter benchmark (#6936) 
* feat: add ip adapter benchmark

* sdxl support too.

* Empty-Commit
 2024-03-03 15:10:55 +05:30
Álvaro Somoza
001b14023e [ip-adapter] fix problem using embeds with the plus version of ip adapters (#7189) 
* initial

* check_inputs fix to the rest of pipelines

* add fix for no cfg too

* use of variable

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-03-02 21:37:00 -10:00
Junsong Chen
f55873b783 Fix PixArt 256px inference (#6789) 
* feat 256px diffusers inference bug

* change the max_length of T5 to pipeline config file

* fix bug in convert_pixart_alpha_to_diffusers.py

* Update scripts/convert_pixart_alpha_to_diffusers.py

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

* remove multi_scale_train parser

* Update src/diffusers/pipelines/pixart_alpha/pipeline_pixart_alpha.py

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

* Update src/diffusers/pipelines/pixart_alpha/pipeline_pixart_alpha.py

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

* styling

* change `model_token_max_length` to call argument.

* Refactoring

* add: max_sequence_length to the docstring.

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: YiYi Xu <yixu310@gmail.com>
 2024-03-03 10:31:21 +05:30
Sayak Paul
ccb93dcad1 Support EDM-style training in DreamBooth LoRA SDXL script (#7126) 
* add: dreambooth lora script for Playground v2.5

* fix: kwarg

* address suraj's comments.

* Apply suggestions from code review

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

* apply suraj's suggestion

* incorporate changes in the canonical script./

* tracker naming

* fix: schedule determination

* add: two simple tests

* remove playground script

* note about edm-style training

* address pedro's comments.

* address part of Suraj's comments.

* Apply suggestions from code review

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

* remove guidance_scale.

* use mse_loss.

* add comments for preconditioning.

* quality

* Update examples/dreambooth/train_dreambooth_lora_sdxl.py

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

* tackle v-pred.

* Empty-Commit

* support edm for sdxl too.

* address suraj's comments.

* Empty-Commit

---------

Co-authored-by: Suraj Patil <surajp815@gmail.com>
 2024-03-03 09:28:57 +05:30
YiYi Xu
ec953047bc [stalebot] fix a bug (#7156) 
fix

Co-authored-by: yiyixuxu <yixu310@gmail,com>
 2024-03-01 09:44:00 -10:00
Oleh
9a2600ede9 Map speedup (#6745) 
* Speed up dataset mapping

* Fix missing columns

* Remove cache files cleanup

* Update examples/text_to_image/train_text_to_image_sdxl.py

* make style

* Fix code style

* style

* Empty-Commit

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: Quentin Lhoest <42851186+lhoestq@users.noreply.github.com>
Co-authored-by: Quentin Lhoest <lhoest.q@gmail.com>
 2024-03-01 21:38:21 +05:30
Sayak Paul
5f150c4cef fix: loading problem for sdxl lora dreambooth (#7166) 2024-03-01 19:30:48 +05:30
Quentin Lhoest
66f8bd6869 Fix vae_encodings_fn hash in train_text_to_image_sdxl.py (#7171) 
Update train_text_to_image_sdxl.py
 2024-03-01 16:56:54 +05:30
Dhruv Nair
64a8cd627a [CI] Remove max parallel flag on slow test runners (#7162) 
update
 2024-03-01 11:38:21 +05:30
Sayak Paul
5d3923b670 Fix LCM benchmark test (#7158) 
* make workflow dispatchable.

* fix: lcm lora compile
 2024-03-01 10:33:44 +05:30
Sayak Paul
9451235e5a [Urgent][Docker CI] pin uv version for now and a minor change in the Slack notification (#7155) 
pin uv version for now.
 2024-03-01 10:11:07 +05:30
Sayak Paul
c2b6ac4e34 [CI] fix path filtering in the documentation workflows (#7153) 
fix: path
 2024-03-01 07:18:49 +05:30
YiYi Xu
06b01ea87e [ip-adapter] refactor prepare_ip_adapter_image_embeds and skip load image_encoder (#7016) 
* add

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

---------

Co-authored-by: yiyixuxu <yixu310@gmail,com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-02-29 15:38:49 -10:00
M. Tolga Cangöz
f4fc75035f [Docs] Fix typos (#7131) 
* Add copyright notice to relevant files and fix typos

* Set `timestep_spacing` parameter of `StableDiffusionXLPipeline`'s scheduler to `'trailing'`.

* Update `StableDiffusionXLPipeline.from_single_file` by including EulerAncestralDiscreteScheduler with `timestep_spacing="trailing"` param.

* Update model loading method in SDXL Turbo documentation
 2024-02-29 13:03:01 -08:00
Dhruv Nair
8f2d13c684 Fix setting fp16 dtype in AnimateDiff convert script. (#7127) 
* update

* update
 2024-02-29 22:47:39 +05:30
Sayak Paul
fcfa270fbd add: support for notifying the maintainers about the docker ci status. (#7113) 2024-02-29 19:28:52 +05:30
Sayak Paul
56dac1cedc limit documentation workflow runs for relevant changes. (#7125) 2024-02-29 19:01:54 +05:30
Sayak Paul
3daebe2b44 use uv for installing stuff in the workflows. (#7116) 
* use uv for installing stuff in the workflows.

* fix: from source installation command when using uv.

* fix uv venv issue

* edit editable installation.

* fix quality installation

* checking

* make editable.

* more check

* check

* add: export step

* venv handling.

* checking.

* fix: dependency workflows.

* peft tests.

* proper way to initialize env.

* Empty-Commit

* Empty-Commit
 2024-02-29 08:27:24 +05:30
Aryan
abd922bd0c [docs] unet type hints (#7134) 
update
 2024-02-28 10:39:01 -10:00
elucida
fa633ed6de refactor: move model helper function in pipeline to a mixin class (#6571) 
* move model helper function in pipeline to EfficiencyMixin

---------

Co-authored-by: YiYi Xu <yixu310@gmail.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-02-28 09:26:39 -10:00
YiYi Xu
2cad1a8465 [stalebot] don't close the issue if the stale label is removed (#7106) 
* fix

* fix

* remove stalebot's ability to close issues

---------

Co-authored-by: yiyixuxu <yixu310@gmail,com>
 2024-02-28 08:04:28 -10:00
Dhruv Nair
e6cf21906d [Diffusers CI] Switch slow test runners (#7123) 
update
 2024-02-28 22:15:04 +05:30
Sayak Paul
7db935a141 fix kwarg in the SDXL LoRA DreamBooth (#7124) 
* fix kwarg

* Empty-Commit
 2024-02-28 10:21:28 +05:30
Sayak Paul
fa9bc029b4 [Tests] make test steps dependent on certain things and general cleanup of the workflows (#7026) 
make tests conditional and other things.
 2024-02-28 08:26:46 +05:30
Beinsezii
2e31a759b5 DPMSolverMultistep add rescale_betas_zero_snr (#7097) 
* DPMMultistep rescale_betas_zero_snr

* DPM upcast samples in step()

* DPM rescale_betas_zero_snr UT

* DPMSolverMulti move sample upcast after model convert

Avoids having to re-use the dtype.

* Add a newline for Ruff
 2024-02-27 11:37:34 -10:00
M. Tolga Cangöz
e51862bbed [Docs] Fix typos (#7118) 
Fix typos, formatting and remove trailing whitespace
 2024-02-27 12:38:00 -08:00
Suraj Patil
8492db2332 add DPM scheduler with EDM formulation (#7120) 
* add DPM scheduler with EDM formulation

* set sigmas in init

* add _compute_sigmas

* Apply suggestions from code review

Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

* address some review comments

* up,

* add tests

---------

Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
 2024-02-27 23:39:38 +05:30
Suraj Patil
f57e7bd92c Add EDMEulerScheduler (#7109) 
* Add EDMEulerScheduler

* address review comments

* fix import

* fix test

* add tests

* add co-author

Co-authored-by:  @dg845 dgu8957@gmail.com
 2024-02-27 17:51:19 +05:30
Sayak Paul
3e3d46924b [Dockerfile] remove uv from docker jax tpu (#7115) 
remove uv from docker jax tpu
 2024-02-27 16:25:50 +05:30
Suraj Patil
d71ecad8cd denormalize latents with the mean and std if available (#7111) 
* denormalize latents with the mean and std if available

* fix denormalize

* add latent mean and std in vae config

* address sayak's comment
 2024-02-27 16:20:05 +05:30
Dhruv Nair
ac49f97a75 Add tests to check configs when using single file loading (#7099) 
* update

* update

* update

* update

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-02-27 15:47:23 +05:30
Sayak Paul
04bafcbbc2 move to uv in the Dockerfiles. (#7094) 
move to uv in the Dockerfiles.
 2024-02-27 15:11:28 +05:30
Sayak Paul
7081a25618 [Examples] Multiple enhancements to the ControlNet training scripts (#7096) 
* log_validation unification for controlnet.

* additional fixes.

* remove print.

* better reuse and loading

* make final inference run conditional.

* Update examples/controlnet/README_sdxl.md

Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

* resize the control image in the snippet.

---------

Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
 2024-02-27 09:18:46 +05:30
Sayak Paul
848f9fe6ce [Core] pass revision in the loading_kwargs. (#7019) 
* pass revision in the loading_kwarhs.

* remove revision from load_sub_model.
 2024-02-27 08:52:38 +05:30
Younes Belkada
8a692739c0 FIX [PEFT / Core] Copy the state dict when passing it to load_lora_weights (#7058) 
* copy the state dict in load lora weights

* fixup
 2024-02-27 02:42:23 +01:00
Sayak Paul
5aa31bd674 [Easy] edit issue and PR templates (#7092) 
edit templates to remove patrick's name.
 2024-02-27 07:10:03 +05:30
jinghuan-Chen
88aa7f6ebf Make LoRACompatibleConv padding_mode work. (#6031) 
* Make LoRACompatibleConv padding_mode work.

* Format code style.

* add fast test

* Update src/diffusers/models/lora.py

Simplify the code by patrickvonplaten.

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

* code refactor

* apply patrickvonplaten suggestion to simplify the code.

* rm test_lora_layers_old_backend.py and add test case in test_lora_layers_peft.py

* update test case.

---------

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: YiYi Xu <yixu310@gmail.com>
 2024-02-26 14:05:13 -10:00
M. Tolga Cangöz
ad310af0d6 Fix EMA in train_text_to_image_sdxl.py (#7048) 
* Fix typos
 2024-02-26 10:39:57 -10:00
Dhruv Nair
d603ccb614 Small change to download in dance diffusion convert script (#7070) 
* update

* make style
 2024-02-26 12:05:19 +05:30
jiqing-feng
fd0f469568 Resize image before crop (#7095) 
resize first

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-02-26 11:14:08 +05:30
Stephen
ae84e405a3 Pass use_linear_projection parameter to mid block in UNetMotionModel (#7035) 
* pass linear projection parameter to mid block

* add cond_proj_dim to motion UNet

* run style and quality checks
 2024-02-26 10:49:14 +05:30
Aryan
3a66113306 [Community] Bug fix + Latest IP-Adapter impl. for AnimateDiff img2vid/controlnet (#7086) 
* fix img2vid; update to latest ip-adapter impl

* update README

* update animatediff controlnet to latest impl
 2024-02-26 10:27:42 +05:30
Vinh H. Pham
7f16187182 Modularize Dreambooth LoRA SDXL inferencing during and after training (#6655) 
* modularize log validation

* run make style

* revert import wandb

* fix code quality & import wandb

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-02-26 09:53:12 +05:30
Vinh H. Pham
f11b922b4f Modularize Dreambooth LoRA SD inferencing during and after training (#6654) 
* modulize log validation

* run make style and refactor wanddb support

* remove redundant initialization

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-02-26 09:01:39 +05:30
Steven Liu
3dd4168d4c [docs] Minor updates (#7063) 
* updates

* feedback
 2024-02-25 09:38:02 -08:00
Fabio Rigano
1c47d1fc05 Fix head_to_batch_dim for IPAdapterAttnProcessor (#7077) 
* Fix IPAdapterAttnProcessor

* Fix batch_to_head_dim and revert reshape
 2024-02-25 00:05:46 -10:00