Runway, a startup that helped develop the Stable Diffusion AI art generator, has announced that its first public test for its Gen-2 AI video model will be going live soon. The company claims that it is the first publicly available text-to-video model, but another group may have beaten them to the punch.
Google and Meta are also working on their own text-to-image generators, but they have not yet released any information about them. Runway’s Gen-2 model will allow users to create 3-second videos from scratch based on simple text prompts. The company has not yet released any footage of the model in action, but they have shared a few clips based on prompts like “a close up of an eye” and “an aerial shot of a mountain landscape.”
It is unclear how well Runway’s Gen-2 model will perform, but it is an exciting development in the field of AI-generated content. If it is successful, it could revolutionize the way we create videos.