Gemini’s New Tool Brings Still Images to Videos Using AI-Powered Video Generation
Google’s Gemini now lets paid users turn photos into 8-second AI-generated videos with sound, using its powerful Veo 3 model for creative storytelling.

Google's Gemini AI assistant now has an amazing new feature: it can turn still photographs into short, animated videos with sound. People who pay for the Google AI Pro and Ultra plans in specific regions can now use this photo-to-video capability.The feature is now available on the web and will be available on the Gemini mobile app within a week.
Users upload a picture through the Gemini web interface, write in a short prompt describing the scene they want to animate, and Google's AI takes care of the rest.The final outcome is an MP4 video with sound that continues for eight seconds and is 720p resolution. The video is in landscape format (16:9), which makes it easy to share across several platforms.
This feature uses Google's Veo 3 model, which was first shown off at Google I/O in May. Since then, it powered over 40 million videos through Gemini and Flow, Google's AI filmmaking tool. Users only need to click "Videos" on Gemini's chat, upload an image, and describe the animation they wish to use the tool. It works especially well with sketching, artwork, objects, and natural landscapes, bringing static photos to life.
But the tool isn't perfect. Bloomberg's tests showed that it had trouble with complicated prompts like making breakdancing characters and sometimes modified the skin tones or facial features of people in pictures.Google recognizes to these problems and claims it is working on making faces look more lifelike and animations look better in future releases.
Google is stepping up its game against video-making AI tools like OpenAI's Sora and Runway, as well as Alibaba and Kuaishou.This change highlights how quickly AI creativity tools are changing and how people are at the heart of this new wave of visual innovation.
Information referenced in this article is from CNBC