| license: cc-by-nc-4.0 | |
| task_categories: | |
| - text-to-video | |
| language: | |
| - en | |
| tags: | |
| - anime | |
| 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 384x384 resolution. | |
| It still generates unstable content often. | |
| The usage is the same as with the original modelscope model. | |
| example images are [here](https://imgur.com/a/sCwmKG1). |