Type
LORA
Publish Time
2023-09-21
Base Model
SD 1.5
Trigger Words
hiratsuka shizuka
s2_style
Copy
Version Introduction
Improved face tags (see attached grid)
Higher steps, network dimension, network alpha





Trained on 70-80 anime screencaps and few artworks.
Recommended weight 0.9-1.0.
Source models are Anything V3 (Season 1 ver.) and Anything V5 (Season 2 ver.).
Check out individual version descriptions for more info.
Improved face tags (see attached grid)
Higher steps, network dimension, network alpha
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
