Google Photos AI Remix: Turn Photos into Videos & Styles

Google Photos Receives Significant AI Enhancements

Google Photos is undergoing a substantial upgrade with the integration of advanced artificial intelligence capabilities. On Wednesday, Google unveiled a series of new features designed to enhance user creativity with their photo collections.

These additions include the ability to transform still images into dynamic videos, and to “remix” photographs into diverse artistic styles, such as anime, comic book illustrations, sketches, and 3D animations.

Centralized Creative Tools

The application will now feature a dedicated “Create” tab. This tab will serve as a central hub for accessing both AI-driven and conventional creative tools.

The newly launched photo-to-video and remixing functionalities will be located within this tab, alongside existing options for creating collages and highlight videos.

Expanding AI Accessibility

This update introduces AI functionality to one of Google’s most widely used consumer services. Google Photos currently boasts a user base exceeding 1.5 billion individuals.

This widespread implementation will place AI technology in the hands of a broader audience, including those less familiar with its potential. It also provides Google with a substantial dataset for learning and refinement as users engage with the new features.

User Feedback and Iteration

The company emphasizes that these features are experimental in nature.

Users will be prompted to provide feedback through a simple thumbs-up or thumbs-down system on the AI-generated content. This input will be instrumental in improving the product and the overall user experience.

Photo-to-Video Functionality

The new photo-to-video feature, leveraging Google’s Veo 2 model, allows users to create brief videos from their existing photos.

This capability mirrors similar offerings already available in Gemini and, as of today, YouTube. Previously, animating old photographs required specialized applications like MyHeritage; now, AI is making this process more accessible.

Users can select from two prompts – “Subtle movements” or “I’m feeling lucky” – to generate a six-second video clip from a chosen photograph.

The Photo to Video feature is currently being rolled out to users in the U.S. on both Android and iOS platforms.

Remix Feature with Imagen AI

Powered by Google’s Imagen AI model, the Remix feature enables users to instantly transform any photo from their gallery into a different artistic style.

This feature will become available in the U.S. on Android and iOS devices within the coming weeks.

AI-Generated Content Identification

Both features will incorporate an imperceptible SynthID digital watermark to identify the content as AI-generated.

Google Photos already employs this technique with other AI tools, such as those used in the Reimagine feature. Similarly, generated videos will display a visible watermark, consistent with those produced by Gemini.

Create Tab Launch and Future Updates

The “Create” tab is scheduled to launch in the U.S. in August.

Google intends to continuously update the tab, introducing new tools, experiments, and refinements to existing functionalities over time.

Integration with YouTube Shorts

These AI features are being introduced concurrently with similar tools for YouTube Shorts.

YouTube Shorts is also gaining its own photo-to-video option, along with new AI effects powered by Veo 2. Access to Veo 3 will be provided to Shorts users later this summer, according to Google.