Modelscope without the watermark, trained in 320x320 from the original weights, 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
- Downloads last month
- 26
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no pipeline_tag.