Turn Any Photo Into a Video Using Gemini's New AI Feature
Google Gemini adds AI feature to turn your photos into HD videos with sound. Animate objects, nature, and scenes easily in just one click.
image for illustrative purpose
Google has introduced a new image-to-video generation tool for its Gemini assistant, available on supported Android devices and the web. The update enables users to convert static images into eight-second video clips using the company’s Veo 3 model.
According to Google, this feature allows for the creation of short, animated videos with audio by uploading a photo and providing a text prompt. The output can include motion effects for elements like nature scenes, everyday objects, and artwork. The generated clips are downloadable and shareable.
Each video includes two types of watermarks—a visible AI-generated tag and an invisible SynthID digital mark, indicating the content is machine-created. Users can also rate the results with a thumbs-up or down.
How to Generate a Video from an Image Using Gemini:
1. Launch Gemini on a device or via the web interface.
2. Tap the ‘Video’ icon in the bottom menu.
3. Upload a still image by selecting the ‘+’ option.
4. Type a description of the desired animation in the text input box.
5. Tap the send icon to initiate the process.
Once submitted, Gemini processes the image and generates a 720p video in landscape format (16:9). Processing time typically ranges from one to two minutes.
During testing, Gemini effectively animated objects, pets, and scenery, but was not able to process real human images. Google has confirmed that the feature is currently restricted to AI Pro and Ultra users and will be rolled out gradually in select regions beginning July 11.
