Google launched a new feature in the Gemini app, allowing users to generate videos from static images powered by advanced VEO 3 models.
Image-to-Video generation tool is available to Google's AI Pro and AI Ultra subscribers and is marked when features are first expanded beyond the AI Ultra tier.
Previously excluding AI Ultra users, the VEO 3 model is now more widely accessible for those using Google AI Pro subscriptions.
That dog in your picture? He has something to say. 🐶
Turn the image into an 8-second video clip and use sound effects and speech @geminiapp The flow from @googlelabs. This feature uses VEO 3 to generate movements that reflect real-world physics and include new ones… pic.twitter.com/zth5hyrut8
– Google AI (@googleai) July 10, 2025
This tool allows users to create 8-second video clips at 720p resolution using audio that is synced to the generated video.
However, Google limits video output to a 16:9 landscape format. This means that unlike Tiktok's AI Alive feature, it may not be ideal for a social media platform.
To use this feature, Gemini users can select the “Video” option under the “Tools” prompt in the app.
The addition of image-to-video generation is also integrated into Google's Flow. This is an AI filmmaking app that is expanding to 75 new countries today.
I've created 40m+ videos on VEO 3 since I/O in May!
Now our new photo to video features @geminiapp Create clips inspired by the world around you. Here's how we imagine our resident Dino Stan walking around Google Campus when we're not looking:) Ultra/Pro… pic.twitter.com/2vbirmyfto
– Sundar Pichai (@sundarpichai) July 10, 2025
This feature was first deployed for desktop users, with mobile access expected by the weekend.
Google's AI Pro subscription costs $20 per month, but the AI Ultra Plan will be available for $250 per month.
