Google is letting Gemini Advanced subscribers try out Veo 2, its text-to-video AI model that it says is capable of creating high-resolution clips with “cinematic realism.” Starting today, subscribers can select Veo 2 from the Gemini model dropdown on the web and mobile, where they can enter a prompt to generate an eight-second video in 720p.

Google's Imagen 3 is a powerful AI text-to-image generator that earned ZDNET's pick as the best image generator -- even against competitors like Midjourney and OpenAI. As a result, the release of its Veo 2 text-to-video generator has been highly anticipated.