Google teases its own AI text-to-video model: Imagen Video

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 . . .

[su_button url=’https://www.theregister.com/2022/10/06/google_ai_imagen_video/’ target=’_blank’ style=’ghost’ background=’#010066′ color=’#010066′ size=’2′ wide=’no’ center=’no’ radius=’auto’]Read more at www.theregister.com[/su_button]