* [Peft] fix saving / loading when unet is not "unet"
* Update src/diffusers/loaders/lora.py
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
* undo stablediffusion-xl changes
* use unet_name to get unet for lora helpers
* use unet_name
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
* remove validation args from textual onverson tests
* reduce number of train steps in textual inversion tests
* fix: directories.
* debig
* fix: directories.
* remove validation tests from textual onversion
* try reducing the time of test_text_to_image_checkpointing_use_ema
* fix: directories
* speed up test_text_to_image_checkpointing
* speed up test_text_to_image_checkpointing_checkpoints_total_limit_removes_multiple_checkpoints
* fix
* speed up test_instruct_pix2pix_checkpointing_checkpoints_total_limit_removes_multiple_checkpoints
* set checkpoints_total_limit to 2.
* test_text_to_image_lora_checkpointing_checkpoints_total_limit_removes_multiple_checkpoints speed up
* speed up test_unconditional_checkpointing_checkpoints_total_limit_removes_multiple_checkpoints
* debug
* fix: directories.
* speed up test_instruct_pix2pix_checkpointing_checkpoints_total_limit
* speed up: test_controlnet_checkpointing_checkpoints_total_limit_removes_multiple_checkpoints
* speed up test_controlnet_sdxl
* speed up dreambooth tests
* speed up test_dreambooth_lora_checkpointing_checkpoints_total_limit_removes_multiple_checkpoints
* speed up test_custom_diffusion_checkpointing_checkpoints_total_limit_removes_multiple_checkpoints
* speed up test_text_to_image_lora_sdxl_text_encoder_checkpointing_checkpoints_total_limit
* speed up # checkpoint-2 should have been deleted
* speed up examples/text_to_image/test_text_to_image.py::TextToImage::test_text_to_image_checkpointing_checkpoints_total_limit
* additional speed ups
* style
* fix RuntimeError: Input type (float) and bias type (c10::Half) should be the same
* format source code
* format code
* remove the autocast blocks within the pipeline
* add autocast blocks to pipeline caller in train_text_to_image_lora.py
* [Community Pipeline] Add Marigold Monocular Depth Estimation
- add single-file pipeline
- update README
* fix format - add one blank line
* format script with ruff
* use direct image link in example code
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
* separate out upsamplers and downsamplers.
* import all the necessary blocks in resnet for backward comp.
* move upsample2d and downsample2d to utils.
* move downsample_2d to downsamplers.py
* apply feedback
* fix import
* samplers -> sampling
* EulerAncestral add `rescale_betas_zero_snr`
Uses same infinite sigma fix from EulerDiscrete. Interestingly the
ancestral version had the opposite problem: too much contrast instead of
too little.
* UT for EulerAncestral `rescale_betas_zero_snr`
* EulerAncestral upcast samples during step()
It helps this scheduler too, particularly when the model is using bf16.
While the noise dtype is still the model's it's automatically upcasted
for the add so all it affects is determinism.
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
* 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>
* fix: init for vae during pixart tests
* print the values
* add flatten
* correct assertion value for test_inference
* correct assertion values for test_inference_non_square_images
* run styling
* debug test_inference_with_multiple_images_per_prompt
* fix assertion values for test_inference_with_multiple_images_per_prompt
Typo: The script for LoRA training is `train_text_to_image_lora_prior.py` not `train_text_to_image_prior_lora.py`.
Alternatively you could rename the file and keep the README.md unchanged.
Kashif Rasul