Google has launched a new Gemini AI feature that allows you to convert photos into video clips. The new Photo-to-Video feature is powered by Google's VEO 3 video model, allowing you to convert reference images into 8-second video with AI-generated audio including background noise, ambient sounds, audio and more.
According to Google, Gemini video updates are now available for Google AI Ultra and Pro Subscribers “Select Regions.” Starting today, it will be available on mobile devices all week on the web.
Gemini users can access the feature by clicking on the “Tools” option in the prompt bar, selecting “Video” and uploading it along with a text description of how to move photos. Audio descriptions can also be included in dialogue, sound effects, and ambient noise. This states that Google “will sync perfectly with the visual.” The completed video will be delivered as an MP4 file in 720p resolution and 16:9 landscape format.
“You can become creative by animating everyday objects, bringing drawings and paintings to life, and giving natural scenes movement,” says Google. “All videos generated contain visible watermarks that indicate that AI is being generated and invisible SynthID digital watermarks.”
Similar features are already available in Flow. This is a generator AI filmmaking tool launched by Google in March, but allows Gemini users to animate photos without opening another app. According to Google, Flow will be launching Gemini's new video feature, as well as incorporating its “new video capabilities” today.
