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.