GitLab

* [Dreambooth] Editable number of class images

* 'class_num=None' bug fix

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

* add lora

* Update examples/research_projects/lora/README.md

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

Co-authored-by: mishka <gartsocial@gmail.com>

* Added multitoken training for textual inversion

* Updated assertion

* Removed duplicate save code

* Fixed undefined bug

* Fixed save

* Added multitoken clip model +util helper

* Removed code splitting

* Removed class

* Fixed errors

* Fixed errors

* Added loading functionality

* Loading via dict instead

* Fixed bug of invalid index being loaded

* Fixed adding placeholder token only adding 1 token

* Fixed bug when initializing tokens

* Fixed bug when initializing tokens

* Removed flawed logic

* Fixed vector shuffle

* Fixed tokenizer's inconsistent __call__ method

* Fixed tokenizer's inconsistent __call__ method

* Handling list input

* Added exception for adding invalid tokens to token map

* Removed unnecessary files and started working on progressive tokens

* Set at minimum load one token

* Changed to global step

* Added method to load automatic1111 tokens

* Fixed bug in load

* Quality+style fixes

* Update quality/style fixes

* Cast embeddings to fp16 when loading

* Fixed quality

* Started moving things over

* Clearing diffs

* Clearing diffs

* Moved everything

* Requested changes

Support revision in Flax text-to-image training.

* community controlnet inpainting pipelines

* add community member attribution re: @pcuenca

* add  intermediate logging
---------
Co-authored-by: yiyixuxu <yixu310@gmail,com>

* Update textual_inversion_flax.py

* Update textual_inversion_flax.py

* Typo

sorry.

* Format source

* unclip img interpolation poc

* Added code sample and refactoring.

* Initial commit

* removed images

* Made logging the same as save

* Removed logging function

* Quality fixes

* Quality fixes

* Tested

* Added support back for validation_epochs

* Fixing styles

* Did changes

* Change to log_validation

* Add extra space after wandb import

* Add extra space after wandb
Co-authored-by: Will Berman <wlbberman@gmail.com>

* Fixed spacing

---------
Co-authored-by: Will Berman <wlbberman@gmail.com>

* Fix tensorboard tracking with `accelerate` @ `main`

* Fix `train_unconditional.py` with accelerate from main.

* Update train_text_to_image_lora.py

* Update train_text_to_image_lora.py

* add xformers 0.0.16 warning message

* fix version check to check whole version string

This reverts commit 024c4376.

* Fix EMA

* up

* update

correctly locate 3rd file; also correct misleading docs

* add total number checkpoints to training scripts

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

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

replace type hints

* Log Unconditional Image Generation Samples to WandB

* Check for wandb installation and parity between onnxruntime script

* Log epoch to wandb

* Check for tensorboard logger early on

* style fixes

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

* UnCLIP Text Interpolation Pipeline

* Formatter fixes

* Changes based on feedback

* Formatting fix

* Formatting fix

* isort formatting fix(?)

* Remove duplicate code

* Formatting fix

* Refactor __call__ and change example in readme.

* Update examples/community/unclip_text_interpolation.py

Refactor to linter formatting
Co-authored-by: Will Berman <wlbberman@gmail.com>

---------
Co-authored-by: Will Berman <wlbberman@gmail.com>

* [LoRA] Freezing the model weights

Freeze the model weights since we don't need to calculate grads for them.

* Apply suggestions from code review
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* Apply suggestions from code review

---------
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: Suraj Patil <surajp815@gmail.com>

Resolves ValueError: `num_inference_steps`: 1000 cannot be larger than `self.config.train_timesteps`: 50 as the unet model trained with this scheduler can only handle maximal 50 timesteps.

* [Examples] Test all examples on CPU

* add

* correct

* Apply suggestions from code review