Skip to content
Note—001DevelopingModels

Runway Labs shows Project Continuum: a desktop where parts of the screen are generated video instead of code

Runway Labs showed Project Continuum, a desktop where some windows are generated video. The demo is edited and Runway has published no frame rate, hardware or access date.

Drafted by The Generated · Filed by The Generated

Runway Labs posted Project Continuum on Thursday: a desktop where some windows are video generated as you click. In the best moment, a leaf diagram recomposes itself when its window is narrowed instead of squashing. It runs on Solaris, Runway's interface model built on Gen-4.5, the same video model it sells to filmmakers.

What Runway has not shown is how fast any of it runs. There is no frame rate, latency, resolution, hardware or access date, and the five-minute walkthrough is edited: its menu-bar clock reads 3:28 PM at the start, at 1:40 and at 5:00. Runway's own Solaris notes also list legible text and long sessions as unsolved, which makes the demo's crisp leaf labels worth asking about.

In practice, nothing changes for anyone making work this week, because there is nothing to use. Interactive Worlds is the mode to watch: if a still can become a scene you walk through in real time, a director could block a shot inside a generated set, which is live previs.

Source: Runway and Runway Labs on X, Oct 1, 2026; Runway Solaris post, Aug 31, 2026.

Provenance — Runway on X: Introducing Project Continuum; AlphaSignal: Project Continuum turns your desktop into live AI-generated video; Runway: Introducing Solaris · Status: verified: MEDIUM (Runway's own launch post; AlphaSignal/Hermes coverage are rewrites, not independent reporting. Concept
Runway's generated desktop is a demo reel, and its clock never moves
Models

Runway wants a cinematic desktop. For now it lives in a demo reel

Runway Labs showed Project Continuum, a research desktop where some windows are generated video that reshapes itself as you click and resize. It runs on Runway's Solaris model, but the company has published no latency, frame rate or access date, and its own notes say legible text and long sessions are unsolved.

Drafted by The Generated · Filed by The Generated
Illustration of a dark editing desk where one window on a computer monitor dissolves at soft glowing edges into a fog-covered suspension bridge at dawn

Halfway through Runway's five-minute walkthrough of Project Continuum, a cross-section of a leaf sits in a window on an ordinary-looking desktop. Someone drags the window narrower, and instead of squashing the picture, the scene rearranges itself to fit, with the labels for chloroplast, stoma, CO2 in and O2 out still neatly in place. Runway says that window is not an app drawing a diagram. It says the leaf is video, generated on the spot by a model that watches the cursor and decides what the next frame should look like.

Runway posted the demo on X on Thursday afternoon, calling Continuum "a new operating system research application built around real-time video interfaces" from Runway Labs, its internal incubator. The company's own verb was "sharing an early look", and that is the right register for it. There is no blog post, no paper, no product page, no waitlist and no date. What exists is a 52-second sizzle reel, the 5:22 walkthrough on the Runway Labs account and a short thread, and it is a genuinely interesting look at where Runway thinks screens are going.

Keep reading — 6 min

That’s all of Models.

2 Oct · 1 note, filed as the record moved.

Models — archive

Also filed

Grimes' team says AI was one tool among 70+ artists
Grimes' 'Accelerando' video used AI 'sparingly', her team says, with 70+ artists on the crew

Grimes' team says AI was a supplementary tool in the Accelerando video, made by more than 70 artists over two to three months. Which shots used AI, and which tools, has not been disclosed.

Harry Potter, out of the wizarding world and into the dojo
nachos2d: #malfoid Malfoid’s Diary | Ep. 2

nachos2d's 30-second anime short sends Harry Potter to a karate dojo, where every hit pops a little heart out of his mouth. The post names no tools, so neither do we.

Disney bids $20M for Character.AI's code, and hires the people who wrote it
Disney bids $20M to be the stalking horse for Character.AI's assets as the chatbot startup files for Chapter 11

Disney bid $20 million to license some of bankrupt Character.AI's code, while most of the startup's staff joined Disney. The app, its users and their chats are not part of the deal, and rival bids can still top it.