Qwen-Mixed style

LORA
Original


Updated:

This is the Lora style, a fusion of various Qwen Lora images I've created, primarily in a digital illustration style, but also incorporating other styles. It will add diversity to the Qwen imagery. During the testing phase, I will experiment with different styles from the training set to create more creative images.

Recommended: Qwen-Image Lightning Lora: 0.4-1,8-10 steps, cfg1, Euler

Regular: 0.4-1, 30 steps, cfg4-6, Euler

I used segmented natural language annotation, with manual bilingual annotation in Chinese and English. This should facilitate Chinese recognition and understanding.

Version Detail

Trained by Tensor
Qwen-Image
16
Recommended: Qwen-Image Lightning Lora: 0.4-1,8-10 steps, cfg1, Euler Regular: 0.4-1, 30 steps, cfg4-6, Euler Recommend: 0.6-0.7

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