Type
LORA
Publish Time
2023-03-20
Base Model
SD 1.5
Version Introduction
Finally figured out how to better train LoRA...





Use a LoRA strength of around 0.5. Value too high may start overriding the character features.
Finally able to produce some decent results.
The ???????? most of the time is not actually in pantie.
Finally figured out how to better train LoRA...
1. The rights to reposted models belong to original creators.
2. Original creators should contact SeaArt.AI staff through official channels to claim their models. We are committed to protecting every creator's rights. Click to Claim
