Google’s Nano Banana brought an AI photo generator that could create images that resembled real people – and now Google is giving the same treatment to generated video. During Google I/O, the tech giant announced Gemini Omni, a new AI that allows users to generate video from existing videos, photos, or text.
Like Gemini 2.5 Flash Image – better known by its viral code name Nano Banana – Gemini Omni aims to keep the likeness of the person in the inspiration photo or video intact, a task that generative AI has historically had difficulty with.