File size: 307 Bytes
73d1d52 17bdca4 689261f a6e2bcc 689261f |
1 2 3 4 5 6 7 |
---
tags:
- Text-to-Video
---
Modelscope without the watermark, trained in 320x320, 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 |