* unwrap text encoder when saving hook only for full text encoder tuning
* unwrap text encoder when saving hook only for full text encoder tuning
* save embeddings in each checkpoint as well
* save embeddings in each checkpoint as well
* save embeddings in each checkpoint as well
* Update examples/advanced_diffusion_training/train_dreambooth_lora_sdxl_advanced.py
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
* add documentation for DeepCache
* fix typo
* add wandb url for DeepCache
* fix some typos
* add item in _toctree.yml
* update formats for arguments
* Update deepcache.md
* Update docs/source/en/optimization/deepcache.md
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
* add StableDiffusionXLPipeline in doc
* Separate SDPipeline and SDXLPipeline
* Add the paper link of ablation experiments for hyper-parameters
* Apply suggestions from code review
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
* Make WDS pipeline interpolation type configurable.
* Make the VAE encoding batch size configurable.
* Make lora_alpha and lora_dropout configurable for LCM LoRA scripts.
* Generalize scalings_for_boundary_conditions function and make the timestep scaling configurable.
* Make LoRA target modules configurable for LCM-LoRA scripts.
* Move resolve_interpolation_mode to src/diffusers/training_utils.py and make interpolation type configurable in non-WDS script.
* apply suggestions from review
* debug
* debug test_with_different_scales_fusion_equivalence
* use the right method.
* place it right.
* let's see.
* let's see again
* alright then.
* add a comment.
* I added a new doc string to the class. This is more flexible to understanding other developers what are doing and where it's using.
* Update src/diffusers/models/unet_2d_blocks.py
This changes suggest by maintener.
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
* Update src/diffusers/models/unet_2d_blocks.py
Add suggested text
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
* Update unet_2d_blocks.py
I changed the Parameter to Args text.
* Update unet_2d_blocks.py
proper indentation set in this file.
* Update unet_2d_blocks.py
a little bit of change in the act_fun argument line.
* I run the black command to reformat style in the code
* Update unet_2d_blocks.py
similar doc-string add to have in the original diffusion repository.
* Batter way to write binarize function
* Solve check_code_quality error
* My mistake to run pull request but not reformated file
* Update image_processor.py
* remove extra variable and space
* Update image_processor.py
* Run ruff libarary to reformat my file
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: YiYi Xu <yixu310@gmail.com>
* add: test to check if peft loras are loadable in non-peft envs.
* add torch_device approrpiately.
* fix: get_dummy_inputs().
* test logits.
* rename
* debug
* debug
* fix: generator
* new assertion values after fixing the seed.
* shape
* remove print statements and settle this.
* to update values.
* change values when lora config is initialized under a fixed seed.
* update colab link
* update notebook link
* sanity restored by getting the exact same values without peft.
* change timesteps used to calculate snr when --with_prior_preservation is enabled
* change timesteps used to calculate snr when --with_prior_preservation is enabled (canonical script)
* style
* revert canonical script to before snr gamma change
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
* Add unload_ip_adapter method
* Update attn_processors with original layers
* Add test
* Use set_default_attn_processor
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
* Fix gradient-checkpointing option is ignored in SDXL+LoRA training. (#6388)
* Fix gradient-checkpointing option is ignored in SD+LoRA training.
* Fix gradient checkpoint is not applied to text encoders. (SDXL+LoRA)
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Linoy Tsaban