An attempt to recreate the style of cartoonish model.
A proof of concept for Flux Lora training.
Training Set: 20 stable diffusion generated images.
Training Steps: 1000.
Recommended strength: 0.5 - 1.0 .
Try your prompt first, if the result is too realistic, add "anime style", if the result is too illustration-like, add "real photo". Tweaking lora strength may also help.
First Version Release
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.