Unverified Commit b1502763 authored by hlky's avatar hlky Committed by GitHub
Browse files

Fix loading OneTrainer Flux LoRA (#10978)


Co-authored-by: default avatarSayak Paul <spsayakpaul@gmail.com>
parent 6e2a93de
......@@ -654,6 +654,7 @@ def _convert_kohya_flux_lora_to_diffusers(state_dict):
_convert(k, diffusers_key, state_dict, new_state_dict)
remaining_all_unet = False
if state_dict:
remaining_all_unet = all(k.startswith("lora_unet_") for k in state_dict)
if remaining_all_unet:
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment