Runway's Solaris generates app interfaces as video, not code
Runway's Solaris renders an application's interface at 720p frame by frame as a user clicks, drags, and types, pairing a language model for reasoning with a world model built on its Gen-4.5 video model. Autoregressive generation plus distilled few-step diffusion holds latency under half a second at a small fraction of standard video-diffusion cost, which makes generated interfaces a plausible training environment for agents that today overfit to one fixed layout. Access is early-access by request, and Runway names stable legible text, coherence over long sessions, and screen-reader support as unsolved — a research bet, not a shipping runtime.
Source: runway.com ↗
Every piece of software built today still requires a translation: the visual design must first be converted into an intermediate representation (e.g. code) before it can do anything.
Why this matters
- → Eliminates intermediate code layer; interfaces become directly renderable visual artifacts
- → Agents train on dynamic layouts instead of fixed interfaces; improves generalization across variations
- → Real-time frame generation at <500ms latency unlocks interactive experiences previously impossible