Google Photos is updating its image-to-video feature with Veo 3, Google’s popular generative AI video model.
In July, the tech giant introduced a way for U.S. users to turn their photos into videos within Google Photos. As of Thursday, this feature is now powered by Veo 3.
Turning images into videos using generative AI has become a popular novelty for meme-ifying static images or bringing cherished photos to life. Several AI startups like Runway, Pika, Freepik, and Kling AI were among the first to capitalize on the very social media-friendly trend. And tech heavyweights like OpenAI and xAI have gotten into the game with their Sora and Grok models. However, Veo 3 is widely considered to be the most advanced AI video model, at least, for now.
Mashable Light Speed
With the Google Photos feature, users select a photo they want to turn into a video in the Create tab and choose between two prompts: “Subtle movement” or “I’m feeling lucky.” Image and video models are expensive to run, which might explain why users have limited options over how they want to transform the image. Other companies will let users create a video with open-ended descriptions, but require a subscription.
Google Photos users get a limited number of generations every day. But subscribers to Google AI Pro ($20 a month) and Google AI Ultra ($200 a month) get higher daily limits.
In addition to the update launched today, Google Photos has pre-existing photo editing features using generative AI. This includes remixing photos into a new style, creating and editing collages, making a video highlight reel, turning photos into 3D images with Cinematic Photos, and animating still images into a GIF. All of these features are available in the Create tab on Google Photos.
Topics
Artificial Intelligence
Google
