Google has launched a new Gemini AI feature that allows users to transform photos into eight-second video clips, incorporating AI-generated audio, such as background noises and speech. This capability is powered by Google's Veo 3 video model and is available to Gemini AI Ultra and Pro subscribers in selected regions. Users can activate the feature by selecting 'video' in the tools bar and providing a photo along with a description. The videos are delivered in MP4 format at 720p and include visible and invisible watermarks to indicate AI generation. Gemini adds ease by allowing users to animate photos directly without needing separate apps.
The Gemini AI feature transforms photos into eight-second video clips with AI-generated audio, including background noises and speech, using Google’s Veo 3 video model.
Users can access the video transformation by uploading a photo and providing a text description of desired movement, including audio for dialogue and sound effects.
The finished products are MP4 files at 720p resolution, with animations allowing creativity in showcasing everyday objects, drawings, and nature scenes.
All generated videos feature a visible watermark for being AI-generated and an invisible SynthID digital watermark, ensuring authenticity in digital content.
Collection
[
|
...
]