Google has just launched an exciting new feature in Gemini, the AI video-making tool, that allows users to transform images into short videos. This feature is available through Veo 3, a component of Gemini, and enables users to generate eight-second video clips from a single image, complete with sound. It’s as simple as selecting ‘Videos’ from the tool menu, uploading an image, and describing the scene along with any desired audio instructions. Once your video is created, you can share or download it. 
Plus, you can provide feedback using thumbs up or down, which will help Google improve the feature over time.
This new image-to-video capability is being rolled out to Google AI Pro and Ultra subscribers in select countries, and the same feature is available within Flow, Google’s AI filmmaking tool. In just seven weeks, over 40 million videos have been generated using Veo 3 and Flow, and this new functionality is expected to significantly increase that number.
Keep in mind that AI-generated videos come with a visible watermark, marking them as created by AI, and an invisible SynthID digital watermark for identification purposes. So, while these videos may seem lifelike, they are still a product of cutting-edge technology.