Gemini Omni is a new family of AI models meant to ‘create anything’

Google has announced Gemini Omni, a versatile new family of AI models capable of generating diverse content from various inputs, including text, photos, audio, and video. The first release, Omni Flash, enables users to create video clips up to 10 seconds long, with the ability to incorporate personalized elements such as user likenesses. Unlike Google's existing text-to-video model, Veo, Omni Flash leverages extensive training data from Gemini to provide deeper world knowledge and allows for video-to-video generation. The model is rolling out in the Gemini app, Google Flow, and YouTube Shorts.

(Source：The Verge)