Style lora trained from arts - SERAZIEL.
Source author: https://x.com/Seraziel/media. Please support the original artist!
Dataset have ~1500 imgs. Naturally aimed at furry but good ones will depict unusual "equipment" ;3. Trained on IllustriousXL v0.1
It's recommended to use illu with NoobAI, as it's trained on the e621 dataset (with abnormal ), but it works fairly well with a regular fine-tune like NovaAnime.
Recommended weight: 0.85-1.15 (higher for greater color saturation).
If anyone knows how to do it better, I'm open to advice in DM.
Description
Initi model!
Details
Downloads
8
Platform
SeaArt
Platform Status
Available
Created
7/12/2026
Updated
7/12/2026
Deleted
-
Trigger Words:
serazielstyle
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.
