Oasis: A Universe in a Transformer

Julian Hector Quevedo, Quinn McIntyre, Spruce Campbell, Xinlei Chen

Abstract:

We're excited to announce Oasis, the first experiential, realtime, open-world AI model. It's an interactive video experience, but entirely generated by AI. Oasis is the first step in our research towards more complex interactive worlds.

Oasis takes in user keyboard input and generates a real-time experience, including physics, rules, and graphics. You can move around, jump, pick up items, break blocks, and more. There is no physics engine; just a foundation model.

We believe fast transformer inference is the missing link to making generative video a reality. Using Decart's inference engine, we show that real-time video is possible. When Etched's transformer ASIC, Sohu, is released, we can run models like Oasis in 4K. Today, we're releasing Oasis's code, the weights of a 500M parameter model you can run locally, and a live demo of a larger checkpoint.