Runway wants to turn AI video generation into a live stream you control in real time
Runway previews research on real-time AI video generation using its GWM-1 world model to cut wait times and GPU costs.
Runway outlined its research into streaming AI video in real time, building on GWM-1, its first General World Model introduced in December 2025, which generates video frame by frame from camera movements, robot commands, or audio. The approach targets minimal time-to-first-frame and lower GPU costs, and addresses compounding visual errors by training on the model's own outputs; Decart's MirageLSD and DeepMind's Genie 3 take similar approaches. A research preview developed with Nvidia runs on the Vera Rubin platform and targets a first frame in under 100 milliseconds, but Runway has not announced an availability timeline.
- GWM-1, Runway's first General World Model introduced December 2025, builds on Gen-4.5 and generates video frame by frame.
- Each new segment uses all prior frames as context, so small errors can compound into major distortions over time.
- Runway trains models on their own outputs to teach self-correction, similar to Decart's MirageLSD approach.
- A real-time model built with Nvidia runs on Vera Rubin and targets first-frame latency under 100 milliseconds.
- Use cases include interactive media, gaming, education, and robotics simulation; no release timeline was given.
- Organizations
- RunwayNvidiaDecartGoogle DeepMindWaymo
From the original article
3 min read at the-decoder.com
Runway wants to stream AI video as users prompt it, rather than make them wait for finished clips. The approach builds on GWM-1, its world model that generates video frame by frame. Beyond creative tools, Runway sees uses in robotics and autonomous driving.
By Jonathan Kemper · the-decoder.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.