Runway, the company behind the famous Stable Diffusion AI image generator, has released an AI model that takes any text description and creates three seconds of matching videos.
Runway is not sharing the model widely at first for safety and business reasons, and it will not be open-sourced like Stable Diffusion. The Gen-2 text-to-video model will be originally available on Discord via a waitlist on the Runway website.
It is not new to use AI to create videos from text inputs. Late last year, Meta Platforms Inc and Google both published study papers on text-to-video AI models. The difference is that Runway’s text-to-video AI model is now accessible to the general public, according to Cristobal Valenzuela, Runway’s CEO.