Google has announced the rollout of a new photo-to-video capability in its Gemini AI platform, empowering users to transform still images into dynamic, eight-second video clips with sound. 

The feature is now available to Google AI Pro and Ultra subscribers in 150 countries.

This innovation builds on the momentum of Veo 3, Google's advanced video generation model launched in May.

In just seven weeks, users have generated more than 40 million videos using Veo 3 across both the Gemini app and Flow, Google’s AI-powered filmmaking tool.

"We’re thrilled by the explosion of creativity we’ve seen from our users," said a Google spokesperson. "From reimagining classic fairy tales through a modern lens to experimenting with ASMR concepts like slicing through lava, Gemini continues to push the boundaries of visual storytelling."

The new photo-to-video tool allows users to animate photos and artworks. To create a video, select 'Videos' from the tool menu in Gemini's prompt box, upload a photo, describe the desired animation and audio details, and the AI converts into a video clip.

Users can animate everything from hand-drawn sketches and nature photography to imaginative scenes, then download or share the results directly from the app.

This functionality is also being introduced in Flow, providing filmmakers and creatives with new ways to prototype and tell stories using AI.

Google claims the video generation system undergoes rigorous "red teaming" and evaluations to detect and address potential risks before launch. All AI-generated videos feature "a visible watermark to indicate AI generation" and "an invisible SynthID watermark for secure tracking and authenticity."