Following the popularity of text-to-image generators, Meta announced Make-A-Video , a text-to-video generator that generates video content from text or image cues. Meta demonstrates the effect of generating a video from a text description or a still image, such as a turtle image that is processed into a turtle swimming video. Make-A-Video is based on existing text image generation models, such as OpenAI’s DALL-E. Meta released its own text image model Make-A-Scene in July this year. The company hasn’t revealed when Make-A-Video will be available to the public, and interested users can sign up now.
This article is reprinted from: https://www.solidot.org/story?sid=72936
This site is for inclusion only, and the copyright belongs to the original author.