This is a text2video model for diffusers, fine-tuned with a modelscope to have an anime-style appearance.
It was trained at 448x384 resolution.
The usage is the same as with the original modelscope model.
The main difference from version 0.1 is only the resolution.
- Downloads last month
- 5
Inference API (serverless) does not yet support diffusers models for this pipeline type.