enrue1893/Synthetic-Ref-to-Urban-Video-Pairs-Town1-6 download history

enrue1893/Synthetic-Ref-to-Urban-Video-Pairs-Town1-6 is an image to video dataset on the Hugging Face Hub. In the last 30 days it was downloaded 26 times (8 in the last 7 days), and 760 times in total. It ranks #307,308 among datasets by monthly downloads.

Synthetic Reference-to-Urban-Video Pairs (Town 1–6) Reference-conditioned training data for the Seoul World Model. The model generates an urban driving video — the target — conditioned on a set of reference frames. This repository provides both roles so a complete (reference, target)

Open enrue1893/Synthetic-Ref-to-Urban-Video-Pairs-Town1-6 on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.