Google has introduced a new feature in its AI tool Gemini that allows users to transform still photos into eight-second video clips with sound. The capability was announced in a company blog post by David Sharon, the Multimodal Generation Lead for Gemini Apps.
The feature is powered by Veo 3, Google’s latest video generation model. Users can upload a photo and add a text prompt to describe the desired animation and audio instructions. Gemini then generates a dynamic video from the static image. This photo-to-video function is currently rolling out to Google AI Pro and Ultra subscribers in select countries. According to Google, all generated videos include visible and invisible watermarks to identify them as AI-generated content.