Odyssey
AI video you can both watch and interact with in real-time
589 followers
AI video you can both watch and interact with in real-time
589 followers
Odyssey is a new AI lab launching a research preview of real-time interactive video. Powered by a world model, it generates explorable video experiences you can influence.
This is the 3rd launch from Odyssey. View more
Odyssey-2 Max
Launched this week
Odyssey-2 Max is Odyssey’s largest general-purpose world model yet, built for real-time interactive simulation. It uses autoregressive next-state prediction to improve physical accuracy, long-horizon stability, and open-ended interaction across worlds that evolve with user actions.
Free Options
Launch Team
Flowtica Scribe
Hi everyone!
I like @Odyssey’s framing of this as pretrained physical intelligence.
The model learns how scenes evolve, how objects move, how interactions play out, and how the world holds together over time. Odyssey-2 Max is still early, but this direction makes the robotics, gaming, simulation, and interactive systems angle much easier to understand.
Interesting, when will compact world models with low costs for robots appear? When that happens, offline professions will also be replaced by AI.