RESEARCH · RESEARCH · #692
Runway previews GWM-1 research to stream AI-generated video in real time
Runway shared research into real-time video generation that streams frames as users describe scenes, aiming to minimize time to first frame and let users iteratively steer output rather than re-running batch generation. The work builds on Runway's GWM-1 (a General World Model based on Gen-4.5), trains the model on its own outputs to reduce compounding errors, and includes a Nvidia-powered preview targeting a first frame under 100 ms; Runway has not announced availability timing.
KEY POINTS
- Runway shared research into real-time video generation that streams frames as users describe scenes, aiming to minimize time to first frame and let users iteratively steer output rather than re-running batch generation.
- The work builds on Runway's GWM-1 (a General World Model based on Gen-4.5), trains the model on its own outputs to reduce compounding errors, and includes a Nvidia-powered preview targeting a first frame under 100 ms; Runway has not announced availability timing.
- If realized, real-time generation shortens the loop between idea and result, enabling interactive applications (education, gaming, robotics), lowering GPU time per output, and changing how models are trained and used.
WHY IT MATTERS
If realized, real-time generation shortens the loop between idea and result, enabling interactive applications (education, gaming, robotics), lowering GPU time per output, and changing how models are trained and used.