Google’s artificial intelligence can now turn still images into stunning videos.
Google has added a new feature to Gemini that allows users to generate 8-second videos from a single photo. This feature is built on the Veo 3 video model and, in addition to creating visuals, simultaneously produces audio such as dialogue, sound effects, and ambient noise.
The new Gemini feature is currently available to Ultra and Pro subscribers in selected regions. It is rolling out on the web version starting today and will soon be released for mobile.
To use Gemini’s video generation tool, simply select the “Video” option from the tools menu in Gemini, upload your desired image, and enter a description for motion or audio. The final video is delivered in MP4 format, with 720p resolution and a 16:9 aspect ratio. Google says the feature is useful for bringing illustrations to life, animating landscapes, or adding motion to everyday objects.
All generated videos include a visible watermark and an invisible digital watermark using SynthID. A similar feature was previously available in the Flow video creation tool, but now Gemini users can access it directly without needing a separate app. Flow is also expanding today to 75 more countries.
