Runway pushes real-time AI video with GWM-1

Runway first discussed this real-time approach in March with Runway Characters, and it uses GWM-1, the company's first "General World Model," which Runway introduced in December 2025. GWM-1 builds on Gen-4.5, generates video frame by frame, and accepts camera movements, robot commands, or audio as controls. Just a few weeks ago, Runway showed Solaris, a system that uses Gen-4.5 to generate user interfaces frame by frame. In March, Runway also showed a research preview of a real-time model developed with Nvidia at the chipmaker's GTC conference, running on the Vera Rubin platform and designed to deliver the first frame in under 100 milliseconds.

Runway argues that real-time generation shifts the compute load from training to use, with the model needing to produce each frame fast enough to keep up with playback while running on hardware shared by several sessions at once. It also points to lower costs, saying faster models use less GPU time, and that the cost per output at a given quality level determines which applications make economic sense. Runway sees interactive applications as the biggest long-term use case for AI-generated media, citing education, gaming, and robotics, and it previously introduced GWM Robotics, a variant of GWM-1 that generates synthetic training data for robots.

The outcome appears to hinge on whether Runway can deliver frames fast enough for smooth playback while multiple sessions share the same hardware, and on whether cost per output drops low enough to make previously unprofitable applications viable. For video creators, the appeal is less time generating and revising clips; for robotics and autonomous driving teams, the appeal is environments that respond instantly to edge cases. Runway hasn't announced a timeline for availability.