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

Based on https://github.com/huggingface/diffusers/pull/2479 from haofanwang, then modified to get working.
2024-08-30 20:32:17 +00:00 · 2023-02-27 08:14:56 -08:00
1 changed files with 1057 additions and 0 deletions
--- a/ldm/invoke/training/train_t2i_lora_peft.py
+++ b/ldm/invoke/training/train_t2i_lora_peft.py