---
tags:
- Text-to-Video
license: cc-by-nc-4.0
---
Modelscope without the watermark, trained in 320x320 from the [original weights](https://huggingface.co/damo-vilab/modelscope-damo-text-to-video-synthesis), with no skipped frames for less flicker.
This updated version fixes stretching issues present in v1, but produces different results overall
Model was trained on a subset of the vimeo90k dataset + a selection of music videos