GitLab

create a utility for casting the lora params during training.

* fix: training resume from fp16.

* add: comment

* remove residue from another branch.

* remove more residues.

* thanks to Younes; no hacks.

* style.

* clean things a bit and modularize _set_state_dict_into_text_encoder

* add comment about the fix detailed.

make checkpointing compatible when using torch.compile.

* make it torch.compile comaptible

* make the text encoder compatible too.

* style

* post release

* style

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

* spit diffusers-native format from the get go.

* rejig the peft_to_diffusers mapping.

* initialize alpha too.

* add: test

* remove config parsing

* store rank

* debug

* remove faulty test

* Fix ProdigyOPT in SDXL Dreambooth script

* style

* style

* 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>

remove depcreated method from lora scripts.

* adapt example scripts to use PEFT

* Update examples/text_to_image/train_text_to_image_lora.py

* fix

* add for SDXL

* oops

* make sure to install peft

* fix

* fix

* fix dreambooth and lora

* more fixes

* add peft to requirements.txt

* fix

* final fix

* add peft version in requirements

* remove comment

* change variable names

* add few lines in readme

* add to reqs

* style

* fix issues

* fix lora dreambooth xl tests

* init_lora_weights to gaussian and add out proj where missing

* ammend requirements.

* ammend requirements.txt

* add correct peft versions

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

* Post Release: v0.24.0

* post pone deprecation

* post pone deprecation

* Add model_index.json

* add variant

* add variant

* Apply suggestions from code review

* reformat

* fix: textual_inversion.py

* fix: variant in model_info

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

readme improvement and metadata fix

* readme bug fix

* style fix

---------
Co-authored-by: Linoy Tsaban <linoy@huggingface.co>

* [Lora] Seperate logic

* [Lora] Seperate logic

* [Lora] Seperate logic

* add comments to explain the code better

* add comments to explain the code better

* Additions:
- support for different lr for text encoder
- support for Prodigy optimizer
- support for min snr gamma
- support for custom captions and dataset loading from the hub

* adjusted --caption_column behaviour (to -not- use the second column of the dataset by default if --caption_column is not provided)

* fixed --output_dir / --model_dir_name confusion

* added --repeats, --adam_weight_decay_text_encoder
+ some fixes

* Update examples/dreambooth/train_dreambooth_lora_sdxl.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* Update examples/dreambooth/train_dreambooth_lora_sdxl.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* Update examples/dreambooth/train_dreambooth_lora_sdxl.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* - import compute_snr from diffusers/training_utils.py
- cluster adamw together
- when using 'prodigy', if --train_text_encoder == True and --text_encoder_lr != --learning rate, changes the lr of the text encoders optimization params to be --learning_rate (otherwise errors)

* shape fixes when custom captions are used

* formatting and a little cleanup

* code styling

* --repeats default value fixed, changed to 1

* bug fix - removed redundant lines of embedding concatenation when using prior_preservation (that duplicated class_prompt embeddings)

* changed dataset loading logic according to the following usecases (to avoid unnecessary dependency on datasets)-
1. user provides --dataset_name
2. user provides local dir --instance_data_dir that contains a metadata .jsonl file
3. user provides local dir --instance_data_dir that contains only images
in cases [1,2] we import datasets and use load_dataset method, in case [3] we process the data same as in the original script setting

* styling fix

* arg name fix

* adjusted the --repeats logic

* -removed redundant arg and 'if' when loading local folder with prompts
-updated readme template
-some default val fixes
-custom caption tests

* image path fix for readme

* code style

* bug fix

* --caption_column arg

* readme fix

---------
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: Linoy Tsaban <linoy@huggingface.co>

* Set usedforsecurity=False in hashlib methods (FIPS compliance)

* update version dependency

* bump hfh version

* bump hfh version

* refactor loaders.py to make it cleaner and leaner.

* refactor loaders init

* inits.

* textual inversion to the init.

* inits.

* remove certain modules from the main init.

* AttnProcsLayers

* fix imports

* avoid circular import.

* fix circular import pt 2.

* address PR comments

* imports

* fix: imports.

* remove from main init for avoiding circular deps.

* remove spurious deps.

* fix-copies.

* fix imports.

* more debug

* more debug

* Apply suggestions from code review

* Apply suggestions from code review

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

* post release

* fix: variant test

* up

* fix: test

post release

* fix error reported 'find_unused_parameters' running in mutiple GPUs or NPUs

* fix code check of importing module by its alphabetic order

---------
Co-authored-by: jiaqiw <wangjiaqi50@huawei.com>
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>

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

* chore: fix typos

* Update src/diffusers/pipelines/shap_e/renderer.py
Co-authored-by: psychedelicious <4822129+psychedelicious@users.noreply.github.com>

---------
Co-authored-by: psychedelicious <4822129+psychedelicious@users.noreply.github.com>

* use loralinear instead of depecrecated lora attn procs.

* fix parameters()

* fix saving

* add back support for add kv proj.

* fix: param accumul,ation.

* propagate the changes.

* fix: how print training resume logs.

* propagate changes to text-to-image scripts.

* propagate changes to instructpix2pix.

* propagate changes to dreambooth

* propagate changes to custom diffusion and instructpix2pix

* propagate changes to kandinsky

* propagate changes to textual inv.

* debug

* fix: checkpointing.

* debug

* debug

* debug

* back to the square

* debug

* debug

* change condition order.

* debug

* debug

* debug

* debug

* revert to original

* clean

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

* [Release 0.21] Bump version

* fix & remove

* fix more

* fix all, upload

* fix sdxl dreambooth lora checkpointing.

* style

* Make sue fp16-fix is used as default

* fix vae

* finish

* fix

fix batch size lora

* correct

* correct blocks

* finish

* finish

* finish

* Apply suggestions from code review

* fix

* up

* up

* up

* Update examples/dreambooth/README_sdxl.md
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* Apply suggestions from code review

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

* Add rank argument to train_dreambooth_lora_sdxl.py

* Update train_dreambooth_lora_sdxl.py

* sdxl lora changes.

* better name replacement.

* better replacement.

* debugging

* debugging

* debugging

* debugging

* debugging

* remove print.

* print state dict keys.

* print

* distingisuih better

* debuggable.

* fxi: tyests

* fix: arg from training script.

* access from class.

* run style

* debug

* save intermediate

* some simplifications for SDXL LoRA

* styling

* unet config is not needed in diffusers format.

* fix: dynamic SGM block mapping for SDXL kohya loras (#4322)

* Use lora compatible layers for linear proj_in/proj_out (#4323)

* improve condition for using the sgm_diffusers mapping

* informative comment.

* load compatible keys and embedding layer maaping.

* Get SDXL 1.0 example lora to load

* simplify

* specif ranks and hidden sizes.

* better handling of k rank and hidden

* debug

* debug

* debug

* debug

* debug

* fix: alpha keys

* add check for handling LoRAAttnAddedKVProcessor

* sanity comment

* modifications for text encoder SDXL

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* denugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* up

* up

* up

* up

* up

* up

* unneeded comments.

* unneeded comments.

* kwargs for the other attention processors.

* kwargs for the other attention processors.

* debugging

* debugging

* debugging

* debugging

* improve

* debugging

* debugging

* more print

* Fix alphas

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* clean up

* clean up.

* debugging

* fix: text

---------
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: Batuhan Taskaya <batuhan@python.org>

* honor the original license.

* train_instruct_pix2pix_xl -> train_instruct_pix2pix_sdxl

* 0.20.0dev0

* make style

* up

* Apply suggestions from code review

* Apply suggestions from code review

* up