LoRA trained in Dan Hipp's art style from Marvel Snap video game art.
v1 trained at 512x512 with just trigger word.
v2 trained at 1024x1024 with Florence2 captions.
Still pending to fix some image errors on dataset.
Trained on 1024x1024 with Florence 2 caption.
Use "digital illustration of" or "cartoon character"
Still pending to fix some errors on dataset images
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.