This is a text2video model for diffusers, fine-tuned with a [ModelScope](https://huggingface.co/damo-vilab/text-to-video-ms-1.7b) to have an anime-style appearance.
It was trained at 512x512 resolution.  
The usage is the same as with the original ModelScope model.

Please note that there is a possibility of unintended unpleasant results!  
The usage limitation of the model follow the ModelScope rules of the original model.  


推奨ポジティブ
anime
推奨ネガティブ
text, nude