Rough first draft of LoRA fine-tuning training backend, using hugginface PEFT library.

Browse Source

Based on https://github.com/huggingface/diffusers/pull/2479 from haofanwang, then modified to get working.

...

This commit is contained in:

user1 2023-02-27 08:14:56 -08:00

parent 650f4bb58c

commit e28106e556

1 changed files with 1057 additions and 0 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1057

ldm/invoke/training/train_t2i_lora_peft.py Normal file

File diff suppressed because it is too large Load Diff