Startup behind Stable Diffusion releases AI system for generating videos from text

Runway, the startup that co-created the favored Stable Diffusion AI picture generator, has launched an AI mannequin that takes any textual content description – equivalent to “turtles flying in the sky” – and generates three seconds of matching video footage.

Citing security and business causes, Runway will not be releasing the mannequin broadly to start out, nor will or not it’s open-sourced like Stable Diffusion. The text-to-video mannequin, dubbed Gen-2, will initially be accessible on Discord through a waitlist on the Runway web site.

Using AI to generate movies from textual content inputs will not be new. Meta Platforms Inc and Google each launched analysis papers on text-to-video AI fashions late final yr. However, the distinction is that Runway’s text-to-video AI mannequin is being made accessible to most of the people, mentioned Cristobal Valenzuela, Runway’s chief government.

Runway hopes that creatives and filmmakers will use the product, Valenzuela mentioned.

Stay on high of know-how and startup news that issues. Subscribe to our day by day e-newsletter for the newest and must-read tech news, delivered straight to your inbox.