obscura/diffusers
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
3,793 Commits 711 Branches 93 Tags
5b2ab4c2698c09b47dbfffee7e6c2d5bf20f50cf
Commit Graph

3793 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Linoy Tsaban 5b2ab4c269 [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>
 2024-12-23 13:02:08 +05:30
Sayak Paul 48a9e62978 Update requirements.txt to remove huggingface-cli (#7202) 
Internal message: https://huggingface.slack.com/archives/C03Q18WK18T/p1709529892062479
 2024-12-23 13:02:08 +05:30
Vinh H. Pham d6bf73aaf5 adding callback_on_step_end for StableDiffusionLDM3DPipeline (#7149) 
* refactor callback

* run make style

* add copy

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-12-23 13:02:08 +05:30
Sayak Paul ba756dd5ea [Docs] more elaborate example for peft torch.compile (#7161) 
more elaborate example for peft torch.compile
 2024-12-23 13:02:08 +05:30
Sayak Paul 0e6ce9dad9 feat: add ip adapter benchmark (#6936) 
* feat: add ip adapter benchmark

* sdxl support too.

* Empty-Commit
 2024-12-23 13:02:08 +05:30
Álvaro Somoza ec8dabf5c9 [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>
 2024-12-23 13:02:08 +05:30
Junsong Chen ac66c913c7 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>
 2024-12-23 13:02:08 +05:30
Sayak Paul 0c693ca240 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>
 2024-12-23 13:02:08 +05:30
YiYi Xu 1943ad4079 [stalebot] fix a bug (#7156) 
fix

Co-authored-by: yiyixuxu <yixu310@gmail,com>
 2024-12-23 13:02:08 +05:30
Oleh 58294f94a9 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>
 2024-12-23 13:02:08 +05:30
Sayak Paul 64694545de fix: loading problem for sdxl lora dreambooth (#7166) 2024-12-23 13:02:08 +05:30
Quentin Lhoest 5575578b38 Fix vae_encodings_fn hash in train_text_to_image_sdxl.py (#7171) 
Update train_text_to_image_sdxl.py
 2024-12-23 13:02:08 +05:30
Dhruv Nair f1916222ef [CI] Remove max parallel flag on slow test runners (#7162) 
update
 2024-12-23 13:02:08 +05:30
Sayak Paul 1022f5a0bd Fix LCM benchmark test (#7158) 
* make workflow dispatchable.

* fix: lcm lora compile
 2024-12-23 13:02:08 +05:30
Sayak Paul 0222544269 [Urgent][Docker CI] pin uv version for now and a minor change in the Slack notification (#7155) 
pin uv version for now.
 2024-12-23 13:02:08 +05:30
Sayak Paul 63b79643ba [CI] fix path filtering in the documentation workflows (#7153) 
fix: path
 2024-12-23 13:02:08 +05:30
YiYi Xu f38417fe30 [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>
 2024-12-23 13:02:08 +05:30
M. Tolga Cangöz a3c115949d [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
 2024-12-23 13:02:08 +05:30
Dhruv Nair 91f6646f6a Fix setting fp16 dtype in AnimateDiff convert script. (#7127) 
* update

* update
 2024-12-23 13:02:08 +05:30
Sayak Paul 1e7fcd4e17 add: support for notifying the maintainers about the docker ci status. (#7113) 2024-12-23 13:02:08 +05:30
Sayak Paul 1de9fcb023 limit documentation workflow runs for relevant changes. (#7125) 2024-12-23 13:02:08 +05:30
Sayak Paul 7d1d1afab6 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
 2024-12-23 13:02:08 +05:30
Aryan f95a5ceb91 [docs] unet type hints (#7134) 
update
 2024-12-23 13:02:08 +05:30
elucida 14bb45e4e8 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>
 2024-12-23 13:02:08 +05:30
YiYi Xu ad6a21585a [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>
 2024-12-23 13:02:08 +05:30
Dhruv Nair cda7b5a298 [Diffusers CI] Switch slow test runners (#7123) 
update
 2024-12-23 13:02:08 +05:30
Sayak Paul 8139fa70c4 fix kwarg in the SDXL LoRA DreamBooth (#7124) 
* fix kwarg

* Empty-Commit
 2024-12-23 13:02:08 +05:30
Sayak Paul 1558485d5f [Tests] make test steps dependent on certain things and general cleanup of the workflows (#7026) 
make tests conditional and other things.
 2024-12-23 13:02:08 +05:30
Beinsezii 1a368d8dc1 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
 2024-12-23 13:02:08 +05:30
M. Tolga Cangöz 59ed616c16 [Docs] Fix typos (#7118) 
Fix typos, formatting and remove trailing whitespace
 2024-12-23 13:02:08 +05:30
Suraj Patil 238e3df52e 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>
 2024-12-23 13:02:08 +05:30
Suraj Patil e4111fdaee Add EDMEulerScheduler (#7109) 
* Add EDMEulerScheduler

* address review comments

* fix import

* fix test

* add tests

* add co-author

Co-authored-by:  @dg845 dgu8957@gmail.com
 2024-12-23 13:02:08 +05:30
Sayak Paul 9618d3363b [Dockerfile] remove uv from docker jax tpu (#7115) 
remove uv from docker jax tpu
 2024-12-23 13:02:08 +05:30
Suraj Patil da2dedc83f 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
 2024-12-23 13:02:08 +05:30
Dhruv Nair dd5bea144d Add tests to check configs when using single file loading (#7099) 
* update

* update

* update

* update

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-12-23 13:02:08 +05:30
Sayak Paul 6d8ffa9ad5 move to uv in the Dockerfiles. (#7094) 
move to uv in the Dockerfiles.
 2024-12-23 13:02:08 +05:30
Sayak Paul 7ccbcb71d4 [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>
 2024-12-23 13:02:08 +05:30
Sayak Paul ac109e895a [Core] pass revision in the loading_kwargs. (#7019) 
* pass revision in the loading_kwarhs.

* remove revision from load_sub_model.
 2024-12-23 13:02:08 +05:30
Younes Belkada 7e2ce58687 FIX [PEFT / Core] Copy the state dict when passing it to load_lora_weights (#7058) 
* copy the state dict in load lora weights

* fixup
 2024-12-23 13:02:08 +05:30
Sayak Paul 58f85d3a14 [Easy] edit issue and PR templates (#7092) 
edit templates to remove patrick's name.
 2024-12-23 13:02:08 +05:30
jinghuan-Chen 037f3234c5 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>
 2024-12-23 13:02:08 +05:30
M. Tolga Cangöz 9b15d87fb5 Fix EMA in train_text_to_image_sdxl.py (#7048) 
* Fix typos
 2024-12-23 13:02:08 +05:30
Dhruv Nair 0ab7713d0a Small change to download in dance diffusion convert script (#7070) 
* update

* make style
 2024-12-23 13:02:08 +05:30
jiqing-feng 862caee47a Resize image before crop (#7095) 
resize first

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-12-23 13:02:08 +05:30
Stephen f804aecbcc 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
 2024-12-23 13:02:08 +05:30
Aryan be2e28383a [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
 2024-12-23 13:02:08 +05:30
Vinh H. Pham 1e6a865d37 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>
 2024-12-23 13:02:08 +05:30
Vinh H. Pham 4ff83c7f4f 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>
 2024-12-23 13:02:08 +05:30
Steven Liu d6e432c38a [docs] Minor updates (#7063) 
* updates

* feedback
 2024-12-23 13:02:08 +05:30
Fabio Rigano 00f2d5ca47 Fix head_to_batch_dim for IPAdapterAttnProcessor (#7077) 
* Fix IPAdapterAttnProcessor

* Fix batch_to_head_dim and revert reshape
 2024-12-23 13:02:08 +05:30