What is the story
Google has announced a new feature in Gemini AI, allowing users to convert still images into short video clips. The innovative feature is powered by Google's latest video generation model, Veo 3. This allows Pro Subscribers from a selected region to create an 8-second video with sound from a single photo. This feature will be available in today's web version of Gemini and in the next few days on the mobile app.
How to convert images to Gemini videos
To use the new feature, Gemini users can use the prompt bar to use the Gemini user.[ツール]Click the button and[ビデオ]You must select and upload the photo with the text description of how to move the photo. You can also add audio descriptions for dialogs, sound effects, and ambient noise. The final video will be delivered as an MP4 file in a 16:9 landscape format at 720p resolution.
Google has implemented a safeguard to prevent misuse
Google has introduced protection measures to prevent misuse of new features, focusing on object and natural animation. The company plans to improve face animation in future updates. “We took important steps behind the scenes to ensure that video generation is the right experience,” a Google spokesperson said, adding that it's great to animate everyday objects, drawings, paintings and nature photos right now.
Check out Google's announcement
Google CEO Sundar Pichai announced a new feature in a post on X. “We've created 40 million+ videos using Veo 3 since I/O in May! With the new photo-to-video feature from @geminiapp, you can create clips inspired by the world around you.” The move will now be adapting to rivals such as Openai and Runway AI Inc., a startup focusing on AI-generated videos.
