Dragon Ball Super Style LoRA - Qwen Image

LORA
Original


Updated:

Dragon Ball Super - Qwen Image

This was my first attempt at training a LoRA for Qwen Image. The results are promising for the overall anime style, but character faces perform average.

Trigger Word: dragon_ball_super

Coverage

  • Almost all Dragon Ball Super (DBS) characters were included.

  • Not all have been tested yet.

Works Well When

  • Resolution: Use 1280x720 landscape (dataset was trained only on this resolution).

  • Prompts: Describe character by name and appearance.

    • Example: Bulma, a woman with short blue hair

  • Character Count: Solo characters or maximum 2.

  • LoRA Strength: 0.8 – 0.9

Gotchas

  • Goku and Vegeta often get mixed up → use negative prompts.

  • Always describe famous characters’ look and outfit explicitly.

Other Versions: https://huggingface.co/ksol8/dragon_ball_super_qwen_image/tree/main

Version Detail

Qwen-Image
2500

Project Permissions

    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