GitLab

* make safetensors default

* set default save method as safetensors

* update tests

* update to support saving safetensors

* update test to account for safetensors default

* update example tests to use safetensors

* update example to support safetensors

* update unet tests for safetensors

* fix failing loader tests

* fix qc issues

* fix pipeline tests

* fix example test

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

Update README_sdxl.md

* Make sue fp16-fix is used as default

* fix vae

* finish

* fix

fix batch size lora

Co-authored-by: mrlzla <noname@noname.com>

* 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>

[SDXL] Make watermarker optional under certain circumstances to improve usability of SDXL 1.0 (#4346)

* improve sdxl

* more fixes

* improve sdxl

* improve sdxl

* improve sdxl

* finish

* 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

* add automatic licensing.

* debugging

* debugging

* more debugging

* more debugging.

* run make fix-copies.

* change to default tracker.

* Allow low precision sd xl

* finish

* finish

* feat: initial draft for supporting text encoder lora finetuning for SDXL DreamBooth

* fix: variable assignments.

* add: autocast block.

* add debugging

* vae dtype hell

* fix: vae dtype hell.

* fix: vae dtype hell 3.

* clean up

* lora text encoder loader.

* fix: unwrapping models.

* add: tests.

* docs.

* handle unexpected keys.

* fix vae dtype in the final inference.

* fix scope problem.

* fix: save_model_card args.

* initialize: prefix to None.

* fix: dtype issues.

* apply gixes.

* debgging.

* debugging

* debugging

* debugging

* debugging

* debugging

* add: fast tests.

* pre-tokenize.

* address: will's comments.

* fix: loader and tests.

* fix: dataloader.

* simplify dataloader.

* length.

* simplification.

* make style && make quality

* simplify state_dict munging

* fix: tests.

* fix: state_dict packing.

* 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>

fix: Typo in dreambooth example README.md

add rank in dreambooth

* Multiply lr scheduler steps by `num_processes`.

* Stop multiplying steps by gradient accumulation.

* add dreambooth lora script for SDXL incorporating latest changes.

* remove use_auth_token=True.

* add: documentation

* remove unneeded cli.

* increase the number of training steps in the readme.

* add LoraLoaderMixin to the subclassing mix.

* add sdxl lora dreambooth test.

* add: inference code sample.

* add: refiner output.

* add LoraLoaderMixin to the mix of classes of StableDiffusionXLImg2ImgPipeline.

* change default resolution of DreamBoothDataset.

* better sdxl report path.

* Apply suggestions from code review
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

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

* refactor to support patching LoRA into T5

instantiate the lora linear layer on the same device as the regular linear layer

get lora rank from state dict

tests

fmt

can create lora layer in float32 even when rest of model is float16

fix loading model hook

remove load_lora_weights_ and T5 dispatching

remove Unet#attn_processors_state_dict

docstrings

* text encoder monkeypatch class method

* fix test

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

* manual check for checkpoints_total_limit instead of using accelerate

* remove controlnet_conditioning_embedding_out_channels

* relax tolerance slightly

* correct incorrect naming

* Post release

* Post release

Apply deprecations

* feat: add lora attention processor for pt 2.0.

* explicit context manager for SDPA.

* switch to flash attention

* make shapes compatible to work optimally with SDPA.

* fix: circular import problem.

* explicitly specify the flash attention kernel in sdpa

* fall back to efficient attention context manager.

* remove explicit dispatch.

* fix: removed processor.

* fix: remove optional from type annotation.

* feat: make changes regarding LoRAAttnProcessor2_0.

* remove confusing warning.

* formatting.

* relax tolerance for PT 2.0

* fix: loading message.

* remove unnecessary logging.

* add: entry to the docs.

* add: network_alpha argument.

* relax tolerance.

Correct multi gpu

* dreambooth if docs - stage II, more info

* Update docs/source/en/training/dreambooth.mdx
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* Update docs/source/en/training/dreambooth.mdx
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* Update docs/source/en/training/dreambooth.mdx
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* download instructions for downsized images

* update source README to match docs

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