- Google Photos adds a feature that transforms still images into six seconds AI-Generated Videos
- The platform also adds a tool called Remix that will reintroduce images to different styles
- All generated content includes visible and invisible watermarks
Google Photos rolls new generative AI features that can transform still images into short video clips, map brings someone to the image and includes natural looking movement. The video tool image uses Google’s VEO 2 AI video model, the same model implemented on YouTube, Gemini and other parts of Google’s ecosystem. The feature does not make your snapshots fully movie trailers; It just creates six seconds of clips.
When you see the opportunity to turn your photos into videos, just select the image image you want to animate, and then choose either “subtle movements” or “I feel lucky” from the buttons below. As you can imagine, the subtle movement choice has that the people in the picture move around a bit. The model is designed to guess what could have happened in the frozen second. The second choice could do something, maybe even throw confetti in the air.
The update is being rolled out in the US on Android and iOS right now, but there are other AI tools coming later this summer to Google photos. Most notable is the Remix feature that comes in the next few weeks. Remix takes your existing photos and reveals them to look like cartoon panels, anime -setting images, 3D reproductions or pencil sketches. It is an ability that Gemini and its many rivals already offer, but now it will be built directly in your photo gallery and do not need you to write a full prompt for it.
All of this is collected in a new section of the app called The Create Tab, which will serve as a hub for these tools, and all other AI features that Google may be releasing in the coming months. In the short term, it will include the image for video and remix features along with the existing collage and highlighting video creators. But when VEO becomes smarter and Google’s confidence grows, opportunities can expand to any number of AI improvements, such as extended video clips, voiceovers or stories of multiple images.
The packaging is what is crucial here. This is the first time that photo-to-video generation has been embedded in a mainstream app like Google Photos, which the company claims has more than a billion users.
AI-driven video tools such as Sora and VEO have generated headlines for their jaw-taking realism and deep potential. But Google photos don’t throw this update as a creative revolution. It presents it as a memory improvement. That said, Google won’t accidentally fool anyone about where the new photos and videos come from. Therefore, any AI-generated video or remix will carry a visible label showing that the content was created with AI. They will also each include an invisible sight time water mark that identifies AI behind its production, the same as the one used by all Gemini’s image and video generators.
Ai Photo Inspiration
Google is unlikely to simply drop these new features and move on. After all, the company has already implemented VEO 3, the latest iteration of the text-to-video model, to Gemini and YouTube for short quality videos complete with synchronized dialogue and background sound. Tools that animate still images today may well tell them tomorrow.
This is more of a spectacle for those who do not constantly try the latest AI toys, but who like to share photos and look at pictures taken by others. It’s easy to pierc on the idea of getting your selfie moving, but it’s the kind of feature that attracts a lot of users who will see how animated AI can get them.
