Overview

This is a text2video model for diffusers, fine-tuned with a ModelScope to have an anime-style appearance. The model now has a much more anime-style look compared to the previous version. It was trained at a resolution of 512x512.

example video and prompts

But it is still unstable and the usability is not good yet. Please note that there is a possibility of unintended unpleasant results!

Prompt

• Mandatory prompt anime
• Recommended negative prompt noise, text, nude

Limitaion

The usage limitation of the model follow the ModelScope rules of the original model.