This repository has been archived by the owner on May 14, 2024. It is now read-only.
SDXL resume training
#305
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
Is it possible to resume training with Kohya LoRA Trainer XL?
It work really good on free colab but sometime it need to be completed with more processing.
I couldn't find the network_weight parameter to specify a safetensors path like with Kohya LoRA Dreambooth.
Is it possible editing the code manually?
Found this in 1.1 and I don't know if it's related : lora_dir = os.path.join(root_dir, "network_weight")
Thanks for the amazing work.
Beta Was this translation helpful? Give feedback.
All reactions