AI has made remarkable strides in generating still images, with services like Dall-E, Stable Diffusion, and MidJourney creating photorealistic, stunning images. Now a startup, Runway AI, is venturing into the next frontier of generative AI — generating videos from text descriptions. New York-based Runway on Monday announced its Gen 2 system, which generates short videos from a few text prompts from the user. For example, the user enters a cat walking in the rain, and it generates about 3 seconds of video based on it. Users can also upload images to serve as reference points for generating videos. The Gen 2 AI system has not yet opened for testing, but similar to OpenAI provides testers through a waiting list (waitlist).
I am the founder of Urbantechstory, a Technology based blog. where you find all kinds of trending technology, gaming news, and much more.View all posts by Ewen Eagle →