Google adds image-to-video feature to Veo 3 via Gemini App

Google has introduced an image-to-video generation feature to its Veo 3 AI video model through the Gemini app, the company announced on Thursday. The feature, which allows users to create video clips from static images, is now available to Google AI Ultra and Google AI Pro subscribers.

The image-to-video capability was first introduced via Google's AI video tool Flow, launched at the I/O developer conference in May. As of last week, Veo 3-powered video generation is accessible in over 150 countries.

Users can access the feature by selecting the “Videos” option from the tool menu within the prompt box and uploading a photo. They can also describe accompanying audio, which will be used to generate sound for the clip. Once rendered, videos can be downloaded or shared directly through the app.

Google said users have created over 40 million videos using the Gemini app and Flow tool since the release of Veo 3 seven weeks ago. Each video generated includes a visible “Veo” watermark and an invisible SynthID digital watermark, which helps verify the content’s AI-generated origin.

The company previously launched a SynthID detection tool to identify AI-generated media, reinforcing transparency around synthetic content.