RunwayML Launches Solaris: AI Generates Interactive UIs from Video
Runway shared research on its first Interface World Model for generating UIs.
TLDR
Runway posted about new research on Solaris, which it describes as an Interface World Model that generates interactive user interfaces frame by frame in real time with no code. The company said this marks an early step toward end-to-end neural software that streams interfaces directly as video. Cristóbal Valenzuela noted interfaces will be generated rather than coded, with chat and gestures as input. Several creators and investors posted reactions calling the work a step toward video models replacing traditional UI code. Runway stated it released a technical report and opened limited access.
Combined views
874K
14 Sources, first seen 28d ago
Sources
CV 
Cristóbal Valenzuela@c_valenzuelabInterfaces that are generated, not coded. Excited to finally share Solaris. Video is the universal interface. Eventually, all UI will be chat and gestures in, chat and video out. Solaris opens new ways to build websites, apps and other interfaces. And most importantly, it…
- likes: 903
- replies: 55
- bookmarks: 639
- reposts: 64
GR Gokul Rajaram@gokulrExciting new research: video models as interfaces. First time this has ever been done. Huge congrats @c_valenzuelab and @runwayml team! https://twitter.com/c_valenzuelab/status/2094477304768405608
- likes: 111
- replies: 5
- bookmarks: 77
- reposts: 13
MA martin_casado@martin_casadoWow. Quite impressive. It does feel like pixel models are now moving to greater and greater precision for editing (away from language) https://twitter.com/c_valenzuelab/status/2094477304768405608
- likes: 257
- replies: 14
- bookmarks: 82
- reposts: 15
CV Cristóbal Valenzuela@c_valenzuelabThis is a real-time interactive application. The image is the interface. The interface is a live stream of pixels. Everything is simulated as you interact with any part of the screen. There’s no conversion step, there’s no loss. The entire frame becomes the interface.…
- likes: 408
- replies: 19
- bookmarks: 193
- reposts: 26
RS Robert Scoble@ScobleizerAn interface world model won the day in AI on X. https://twitter.com/agermanidis/status/2094466649399451768
- likes: 207
- replies: 6
- bookmarks: 115
- reposts: 14
RU Rufus@nintendobenzo@c_valenzuelab “Eventually, all UI will be chat and gestures in, chat and video out” gonna have to doubt you on that one. Not all interfaces can or should be generative or require or even involve video or image output. This is chasing dollars. Looks kinda neat I guess