VividToon - SampleTest

VividToon

LORA
Original


Updated:

Version Detail

Trained by Tensor
Z-Image
3000
10
A versatile, high-fidelity stylized model that blends bold, tapered linework with soft-surface digital painting. It features "semi-chibi" proportions—enlarged eyes and simplified anatomy—while maintaining a sense of weight and cinematic lighting. It has a tilt shift blur effect to the background and foreground to create a sense of depth. As of now this is trained on only 100 images 3 repeats, 10 epochs. I need to expand the dataset dramatically to get a more reliable and consistent output for my full release and get a reliable effect to proc for more stuff. For now this model is best when used on portraits of characters. I'm looking to expand the effects as I continue working on it. There is a triggerword of "ffstyle" for now, my goal is to eventually make that unnecessary as I continue to build this model out.

Project Permissions

Reprinting is strictly prohibited

    Use Permissions

  • Use in TENSOR Online

  • As a online training base model on TENSOR

  • Use without crediting me

  • Share merges of this model

  • Use different permissions on merges

    Commercial Use

  • Sell generated contents

  • Use on generation services

  • Sell this model or merges

Related Posts