Imagine AI that can simulate anything—possible or impossible.
Our video generation models act as world simulators, driving breakthroughs in embodied AI by enabling infinite explorations in synthetic realities. Video is the ultimate medium for human-AI interaction, seamlessly integrating text, audio, images, and 3D into one unified experience.
Our team includes the original creators of DDPM, DreamFusion, and Emu Video.
Mochi 1, our first public open-source release, is licensed under Apache 2.0 for both individual and commercial use.
Video is the language of the future. Help us write the script.
CEO of Typeface
CEO of Replit
Investor and author
BAG, long time executive at Google
VP of AI at Replit
UC Berkeley, Databricks Co-Founder
UC Berkeley, Deep RL pioneer, Covariant AI
UC Berkeley, SysML pioneer
Work with us to build the best open video models.