Google introduces image-to-video feature in Gemini AI app
Google has launched a new feature in its Gemini app that allows users to generate videos from static images, powered by its advanced Veo 3 model.
The image-to-video generation tool is available to Google’s AI Pro and AI Ultra subscribers, marking the first time the feature has been extended beyond the AI Ultra tier.
Previously exclusive to AI Ultra users, the Veo 3 model is now being made more widely accessible to those with a Google AI Pro subscription.
That dog in your photo? He's got something to say. 🐶
Turn your images into eight-second video clips with sound effects and speech in the @GeminiApp and Flow from @GoogleLabs. This feature uses Veo 3 to generate motion that reflects real world physics and includes a new… pic.twitter.com/Zth5hyRut8The tool enables users to create eight-second video clips at 720p resolution, with audio that is synced to the generated video.
However, Google has limited the video output to a 16:9 landscape format, meaning it may not be ideal for social media platforms, unlike TikTok’s AI Alive feature.
To use the feature, Gemini users can select the “video” option under the “tools” prompt on the app.
The addition of image-to-video generation is also integrated into Google's Flow, its AI filmmaking app, which has expanded to 75 new countries today.
Since I/O in May, you've created 40M+ videos with Veo 3!
Now our new photo to video feature in the @Geminiapp lets you create clips inspired by the world around you. Here’s how I imagine our resident dino Stan roams the Google campus when we’re not looking:) Ultra/Pro… pic.twitter.com/2VBirMyFtOThis feature is rolling out for desktop users first, with mobile access expected by the end of the week.
Google's AI Pro subscription costs $20 per month, while the more advanced AI Ultra plan is available for $250 per month.