Google's Gemini AI can now turn your photos into videos
What's the story
Google has unveiled a new feature for Gemini AI, allowing users to convert still images into short video clips. The innovative capability is powered by Veo 3, Google's latest video generation model. It enables Gemini AI Ultra and Pro subscribers in select regions to create eight-second-long videos with sound from a single photo. The feature will be available on the web version of Gemini today and on mobile apps over the coming days.
User guide
How to convert images into videos on Gemini
To use the new feature, Gemini users need to click on the "tools" button in the prompt bar, select "video," and upload their photo with a text description of how they want it to move. They can also add audio descriptions for dialog, sound effects, and ambient noise. The final videos are delivered as MP4 files at 720p resolution in a 16:9 landscape format.
Safety measures
Google has implemented safeguards to prevent misuse
Google has put in place safeguards to prevent misuse of the new feature, focusing on animating objects and nature. The company plans to improve face animation in future updates. "We have taken significant steps behind the scenes to make sure video generation is an appropriate experience," a Google spokesperson said, adding that they are better at animating everyday objects, drawings, paintings, and nature photos right now.
Feature announcement
Take a look at Google's announcement
Google CEO Sundar Pichai announced the new feature in a post on X. He said, "Since I/O in May, you've created 40 million+ videos with Veo 3! Now our new photo to video feature in the @Geminiapp lets you create clips inspired by the world around you." The move positions Google to take on rivals such as OpenAI and Runway AI Inc., a start-up focused on AI-generated video.