[examples/advanced_diffusion_training] bug fixes and improvements for LoRA Dreambooth SDXL advanced training script #5935
imports and readme bug fixes
2ad98373
bug fix - ensures text_encoder params are dtype==float32 (when using …
bf783ff7
added pivotal tuning to readme
cdceaa6a
mapping token identifier to new inserted token in validation prompt (…
0bbffa9b
linoytsaban
marked this pull request as ready for review 1 year ago
linoytsaban
changed the title bug fixes and improvements for LoRA Dreambooth SDXL advanced training script [examples/advanced_diffusion_training] bug fixes and improvements for LoRA Dreambooth SDXL advanced training script 1 year ago
correct default value of --train_text_encoder_frac
b83a846e
change default value of --adam_weight_decay_text_encoder
d53be8ff
validation prompt generations when using pivotal tuning bug fix
6edc0f5a
style fix
3c2afc59
textual inversion embeddings name change
9265cb09
style fix
0af8f447
bug fix - stopping text encoder optimization halfway
e53a84ad
readme - will include token abstraction and new inserted tokens when …
9092ab28
Merge branch 'huggingface:main' into advanced_lora
03fd5bf2
style fix
9868e675
Assignees
No one assigned
Login to write a write a comment.
Login via GitHub