mihirma's picture
Update README.md
36850af verified
metadata
license: cc0-1.0

Jasmine MaskGIT Checkpoint

Pretrained MaskGIT-based world model from the Jasmine codebase.
Trained on the CoinRun dataset for action-conditioned video generation using the Jasmine-base configuration as mentioned in the paper.


Model Details

  • Architecture: ST-Transformer (spatio-temporal transformer)
  • Input: 16-frame sequences (64×64) + latent actions
  • Training Environment: CoinRun (Cobbe et al., 2020)
  • Objective: MaskGIT (Chang et al., 2022)