Video generation just turned into a place you can walk around. runway's gwm worlds 2, a research…
video generation just turned into a place you can walk around. runway's gwm worlds 2, a research preview from september 3, renders real-time interactive worlds at 720p and 24 fps with text-driven control and multiplayer roles.
the prompt became an environment.
Context
Runway's research post of September 3, 2026 introduces GWM Worlds 2, extending GWM Worlds, which the post says was showcased the previous December. It says the model produces continuous 720p video at 24 fps with audio at 48,000 Hz, responding to inputs, with control by text actions addressed to a subject or the scene plus continuous camera motion, and first-person and third-person navigation including walking, driving and riding. Its multiplayer section describes roles, player 1, player 2 and director, in a demo that uses LiveKit to broadcast video and audio, and the post says sessions have no preset length.
The post calls it a research preview in which real-time generation trades fidelity for speed, with fast camera rotations degrading details and geometry, imperfect long-term memory, and no image references beyond the first frame or prefilled video and audio, and free-form text control can need an external real-time harness. The multiplayer part is described as a demo and not a shipped product. Public access, pricing, an API, interaction latency and hardware requirements were not stated in the text read, so no figures beyond resolution and frame rate are given. The prompt became an environment is the author's take.
Watch next
- Access, pricing and latency details.
Sources
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 22 September 2026 at 09:56 IST. Sources are the papers and datasets the note draws on.
View the original post ↗Embed this note
More notes
The air is now being asked to keep its own ledger
the air is now being asked to keep its own ledger: ecmwf’s aifs compo becomes the first ai model to forecast atmospheric composition globally every three hours, cleanair simulates 365 days of pm2.5 over china in ten seconds, and a unified framework maps six pollutants at one kilometer across the whole country. the air now files its own composition report.
read the note →The current is now being asked to draw its own map
the current is now being asked to draw its own map: china’s langya 2.0 predicts six ocean phenomena including internal waves and mesoscale eddies, a deep net called wenhai resolves eddies globally with air sea flux formulas built in, and scripps infers surface currents from the way temperature patterns deform in satellite images. the ocean now files its own circulation report.
read the note →The soil is now being asked to report its own carbon
the soil is now being asked to report its own carbon: a nix color sensor paired with generative data augmentation predicts soil organic carbon without a lab, random forest drives 74 percent of soil health mapping studies, and sentinel 2 tracks five year carbon change across france and italy from 922 samples. the dirt now files its own carbon account.
read the note →