To generate videos, they trained Diffusion Forcing on Minecraft gameplay & colorful digital environments created w/i Google's DeepMind Lab Simulator.

When given a single frame of footage, the method produced more stable, higher-resolution videos than comparable baselines,… pic.twitter.com/x4ETG13DZJ

— MIT CSAIL (@MIT_CSAIL) 17 octobre 2024

To generate videos, they trained Diffusion Forcing on Minecraft gameplay & colorful digital environments created w/i Google's DeepMind Lab Simulator. When given a single frame of footage, the method produced more stable, higher-resolution videos than comparable baselines,

→ View original post on X — @mit_csail