Imagen Video builds upon Google’s previous text-to-image system, Imagen, launched in May. Instead of a single still picture, the AI-powered system builds a video out of multiple frames of output. Like Meta’s Make-A-Video, the quality of Google’s Imagen video is somewhat fuzzy, and the resolution isn’t great yet. Boffins at Google Brain described the system as being ‘temporally-coherent’ and ‘well-aligned’ in a non-peer reviewed research paper [PDF] An internal Google dataset made up of 14 million video-text samples and 60 million image-text pairs, as well as information from the publicly available LAION-400M image-Text dataset, was used to train . . .
Read more at www.theregister.com