Poster
in
Workshop: Text, camera, action! Frontiers in controllable video generation

Jafar: An Open-Source Genie Reimplemention in Jax

Timon Willi ⋅ Matthew T Jackson ⋅ Jakob Foerster

Keywords: World model foundational model Video Generation generative model

Project Page [ OpenReview]

Abstract

We introduce Jafar, an open-source Jax reimplementation of Genie, a foundational world model. Genie was the first world model trained in an unsupervised manner on unlabelled internet data. We follow the reproducibility study in the appendix of Genie and evaluate our reimplementation on the CoinRun environment from the procgen suite. Jafar is implemented in JAX and produces visually consistent video generation and can be trained on a single GPU.

Chat is not available.