odyssey-3 generative world model goes public
odyssey launched odyssey-3, a generative world model that creates interactive environments from text prompts in real time, for free public use. this affects ai researchers and developers.
odyssey, a california-based ai company, launched a public research preview of odyssey-3, a generative world model that creates interactive environments from text prompts in real time. the model uses an autoregressive diffusion transformer to generate new video frames based on previous frames and user actions. odyssey-3 has 14 billion parameters and generates video at 832 × 480 pixels. the model scored 66.1 points on the physics-iq verified benchmark, though the result comes with caveats. odyssey-3 affects ai researchers and developers working on robotics, autonomous driving, and video games.