Google has introduced a powerful new photo-to-video feature in its Gemini AI platform, allowing users to transform static images into animated video clips complete with sound.
The feature is powered by Google’s Veo 3 video model and is now rolling out to Gemini Ultra and Pro subscribers in select regions.
With this new tool, users can generate eight-second MP4 videos in 720p resolution and 16:9 format. Alongside photo uploads, users can include text and audio descriptions to guide how the visuals move and what sounds play—ranging from background noise and ambient effects to speech. Google says the audio is “perfectly synced with the visuals.”
To access the feature, Gemini users simply click the “tools” icon in the prompt bar, select “video,” upload an image, and describe the animation and sounds they want. The finished videos include both a visible watermark and an invisible SynthID digital watermark to indicate they were AI-generated.
The update is already available on the web and will arrive on mobile throughout the week. Google also announced that Flow, its AI filmmaking tool, will be launching in 75 more countries starting today.
If this article helped you, please consider supporting our work. Every small contribution keeps Abijita.com independent and running.
