Description

(for best results, read the full description - usage guide below)

This is a lora which is based on cartoon models to achieve a linear cartoony illustration style, more similar to what you would actually see in illustrations as opposed to the more common hyper-detailed anime models.

Usage Guide

very important!! use high resolution repair when you generate images from text,or you may get a very weird face.

• (highly recommended) Use parameters below for best results

  • model: Counterfeit or other anime models（you can try other models for different effect and welcome for feedbacks)

  • VAE(if you feel the color is too bright,use KIF8Anime2 )

  • Sampler:Euler

  • weight: 0.8-1.0