Make-A-Video.

Make-A-Video is a revolutionary AI system that can generate videos from text. It uses images with descriptions to learn about the world, and unlabeled videos to learn how the world moves. With this data, Make-A-Video lets you create unique videos with just a few words or lines of text. It can also add motion to a single image or fill in the motion between two images. Make-A-Video also has 3x better representation of text input and 3x higher quality than the previous state of the art. If you're interested in trying it out, you can sign up and get access to future releases. Meta AI is committed to developing responsible AI and making sure this technology is used safely.