* 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>
* Change LCMScheduler.set_timesteps to pick more evenly spaced inference timesteps.
* Change inference_indices implementation to better match previous behavior.
* Add num_inference_steps=26 test case to test_inference_steps.
* run CI
---------
Co-authored-by: patil-suraj <surajp815@gmail.com>
* fix an issue that ipex occupy too much memory, it will not impact performance
* make style
---------
Co-authored-by: root <jun.chen@intel.com>
Co-authored-by: Meng Guoqing <guoqing.meng@intel.com>
An upcoming change to JAX will include non-local (addressable) CPU devices in jax.devices() when JAX is used multicontroller-style, where there are multiple Python processes.
This change preserves the current behavior by replacing uses of jax.devices("cpu"), which previously only returned local devices, with jax.local_devices("cpu"), which will return local devices both now and in the future.
This change is always safe (i.e., it should always preserve the previous behavior), but it may sometimes be unnecessary if code is never used in a multicontroller setting.
Co-authored-by: Peter Hawkins <phawkins@google.com>
* fix: UnboundLocalError with image_latents
* chore: run make style, quality, fix-copies
* revert changes from make fix-copies
* revert changes from make fix-copies
---------
Co-authored-by: YiYi Xu <yixu310@gmail.com>
* add also peft latest on peft CI
* up
* up
* up
* Update .github/workflows/pr_test_peft_backend.yml
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
* begin doc
* fix examples
* add in toctree
* fix toctree
* improve copy
* improve introductions
* add lcm doc
* fix filename
* Apply suggestions from code review
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
* address Sayak's comments
* remove controlnet aux
* open in colab
* move to Specific pipeline examples
* update controlent and adapter examples
---------
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
* improvement: docs and type hints
* improvement: docs and type hints
minor refactor
* improvement: docs and type hints
* update with suggestions from review
Co-Authored-By: Dhruv Nair <dhruv.nair@gmail.com>
---------
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>
* Fix typos, update, add Copyright info, and trim trailing whitespace
* Update docs/source/en/api/pipelines/text_to_video_zero.md
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
* 1 second is not a long video, but 6 seconds is
* Update text_to_video_zero.md
* Update text_to_video_zero.md
* Update text_to_video_zero.md
* Update wuerstchen.md
---------
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
* does this fix things?
* attention mask use
* attention mask order
* better masking.
* add: tesrt
* remove mask_featur
* test
* debug
* fix: tests
* deprecate mask_feature
* add deprecation test
* add slow test
* add print statements to retrieve the assertion values.
* fix for the 1024 fast tes
* fix tesy
* fix the remaining
* Apply suggestions from code review
* more debug
---------
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
