Sunnyvale, Calif., Sept. 1, 2026 — Visko announced a $10 million pre-seed round and opened public access to Orbis, its first Live Model: a foundation model that creates living worlds and streams them in real time with persistent memory, interactivity and physics-grounded generation of unbounded length.
Orbis streams interactive 4K video at 24 frames per second, responds to user intervention instantly, and sustains hour-scale generation without evident visual or color drift. Unlike conventional offline video generators that render finished clips from a submitted prompt, Visko describes Live Models as systems that run rather than render: Orbis generates video continuously and allows users to change the prompt during generation, with updates reflected instantly while the video keeps streaming.
Orbis as a real-time, stateful Live Model
Visko’s technical report describes Orbis 1.0 as a real-time, interactive long-video generation system. Generation is grounded in physical dynamics: a latent world model scores candidate futures during inference and steers output toward physically plausible motion and object dynamics. The company says Orbis creates sustained, interactive worlds suitable for hour-scale sessions without evident visual or color drift.
In the report’s evaluations, Orbis leads compared real-time and long-video systems on DOVER aesthetic and technical quality and on VideoAlign visual and motion quality. Orbis also recorded the highest overall-preference and temporal-stability ratings in the report’s long-form human preference study across eight systems. The report additionally discloses dimensions where Orbis trails other systems, with full methodology and results published by Visko.
“Every real-time system before this faced the same wall: the longer a world runs, the more it falls apart. We built Orbis to hold together — physically, visually and narratively — for as long as you want to stay inside it. Starting today, anyone can see that for themselves at visko.ai,” said Qing (Will) Yin, founder and chief executive officer of Visko.
Dr. Michael I. Jordan, chairman of Visko’s advisory board and professor at UC Berkeley, commented: “Visko is pursuing one of the most ambitious directions in video AI: live, stateful models that continuously perceive, predict, and interact with the world in real time while maintaining physical consistency. Visko delivers a state-of-the-art architecture that has a meaningful technological lead beyond conventional short-clip video generation. The same core capability could support a remarkably broad range of commercial opportunities, from robotics and physical simulation to gaming, live commerce, education, and real-time creative media.”
Visko positions Orbis and its Live Models as distinct from offline generators by emphasizing continuous runtime, interactivity, persistent memory and physics-grounded inference. Public access to Orbis is available at visko.ai.
