Real-time video
GWM Worlds 2
Generate and steer an audiovisual world continuously at 24 FPS.
Product insights
GWM Worlds 2 at a glance
Value proposition
Runway’s research preview generates continuous 720p video at 24 FPS with 48 kHz audio, responding to text actions and camera movement as the world runs.
Problem solved
Traditional video generation often makes you wait for a finished clip. Real-time video products bring feedback and control back into the generation loop.
Audience
For creative technologists, developers, and product teams building live visual experiences.
Pricing and access
Hosted access is available through the official website. Plans, credits, regions, and API terms vary by product.
Market
- Real-time video
- Real-time world
- Action-conditioned
- Generated audio
Tech stack
- Official hosted product
- Real-time video stream
- Browser / API access
01Why it is here
What is GWM Worlds 2?
GWM Worlds 2 is Runway’s real-time autoregressive video-and-audio world model. It keeps generating without a preset duration while text actions and continuous camera motion change the world.
02Workflow
How to use GWM Worlds 2
- 01
Define the world
Set the environment, subjects, visual style, physical rules, ambience, and first frame.
- 02
Steer subjects and camera
Send text actions while continuous camera input moves through the world.
- 03
Continue without a fixed clip
Each new input continues the generated world rather than restarting a fixed video.
03Capabilities
Key features of GWM Worlds 2
- Continuous 720p video at 24 FPS
- Generated 48 kHz audio
- Immediate action and camera control
04Use cases
What is GWM Worlds 2 best for?
- Interactive entertainment
- Virtual characters
- Embodied-agent simulation
05Questions
FAQ about GWM Worlds 2
What makes GWM Worlds 2 real time?
The official preview says it generates 720p video at 24 FPS while user actions take effect immediately and generation keeps running.
Official website snapshot
runway.com
Runway’s research preview generates continuous 720p video at 24 FPS with 48 kHz audio, responding to text actions and camera movement as the world runs.