gen‑ai.news
← Back
Video

Runway News | Introducing Solaris

Runway News | Introducing Solaris

Runway has unveiled Solaris, a model it describes as an Interface World Model - a system capable of generating interactive user interfaces in real time, one frame at a time, with no underlying code required. Rather than producing a finished image or a pre-rendered video, Solaris generates the visual state of an interface continuously as a user interacts with it, making the output responsive and dynamic by nature.

The distinction between a world model and a standard generative model is important here. World models are designed to simulate environments and predict how those environments change in response to actions. Applying that concept to software interfaces means Solaris is not simply drawing a picture of an app - it is modeling how an interface behaves, updating its output based on input in a way that resembles real interactive software. Runway positions this as a fundamentally different category from image or video generation.

This announcement fits into a broader trend of AI labs exploring world models as a path toward more capable, interactive AI systems. Where much of the earlier focus in generative AI was on producing media - photos, video, audio - work on world models targets simulation and agency. For Runway, a company that has built its reputation primarily on video generation tools, Solaris signals an expansion into territory that has practical implications for interface design, prototyping, and potentially the creation of software experiences without traditional development workflows.

Solaris appears to be at an early, research-oriented stage, and Runway has not announced a broad public release or detailed pricing. Still, the demonstration points toward a use case that many in the design and development space have been watching closely: the ability to sketch, iterate, or even deploy interactive experiences driven entirely by a generative model. How well Solaris handles complexity, consistency, and user control at scale will determine whether Interface World Models become a practical tool or remain a compelling proof of concept.

Enjoy this story? Get the next one in your inbox.

Twice a week: the most important stories in generative image and video AI, distilled into a 2-minute read.

Free. Unsubscribe any time. No spam, ever.

Your next read

No image
Video

Runway’s WorldPrompt and the Engineering of Real-Time Worlds

Runway's WorldPrompt system powers its Gen World Models 2 (GWM 2), enabling real-time generation of video and audio through persistent context and timed actions. Rather than producing discrete clips, the model maintains a continuous understanding of an environment as it unfolds. The approach marks a notable shift in how world models can be steered interactively.

Gemini 3.8 Live with Live Avatar gives Google’s AI a face
Video

Gemini 3.8 Live with Live Avatar gives Google’s AI a face

Google has updated Gemini Live with an animated avatar that lip-syncs and displays facial expressions in real time during conversations. Called Live Avatar, the feature is currently limited to Gemini Enterprise customers and supports 97 languages without degrading video quality. It marks Google's latest step toward giving its AI assistant a visible, expressive presence.

No image
Video

Introducing Gemini 3.8 Live with Live Avatar

Google DeepMind has introduced Gemini 3.8 Live, an updated multimodal model paired with a new Live Avatar feature that generates an animated, talking on-screen presence during real-time conversations. The combination allows users to interact with a responsive visual agent rather than a purely voice-based interface. The release marks another step in Google's effort to make AI interactions feel more immediate and embodied.