README
Modelscope without the watermark, trained in 320x320 from the original weights, with no skipped frames for less flicker. See comparison here: https://www.youtube.com/watch?v=r4tOc30Zu0w Model was trained on a subset of the vimeo90k dataset + a selection of music videos
Similar repos
README
Modelscope without the watermark, trained in 320x320 from the original weights, with no skipped frames for less flicker. See comparison here: https://www.youtube.com/watch?v=r4tOc30Zu0w Model was trained on a subset of the vimeo90k dataset + a selection of music videos