ductridev / animov-512x

This is a text2video model for diffusers, fine-tuned with a ModelScope to have an anime-style appearance.

  • Public
  • 237 runs
Run with an API
Playground API Examples README Versions

Run time and cost

This model costs approximately $1.34 to run on Replicate, or 0 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia A100 (80GB) GPU hardware. Predictions typically complete within 16 minutes.

Readme

license: cc-by-nc-4.0 pipeline_tag: text-to-video tags: - anime

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.