TLDR: Google has rolled out an experimental AI feature for YouTube Shorts and Google Photos, allowing users to transform still images into dynamic video clips. This new capability, powered by the Veo 2 AI model, offers options for subtle movements or more creative transformations, and is part of a broader push to integrate generative AI into Google’s visual platforms. The features are initially available in select regions with plans for wider rollout.
Google has introduced a significant update to its YouTube Shorts and Google Photos platforms, integrating experimental artificial intelligence capabilities that enable users to generate video content directly from still photographs. This innovative feature, which leverages Google’s advanced video generation AI model, Veo 2, marks a strategic move by the tech giant to enhance user engagement and facilitate dynamic visual storytelling.
For Google Photos users, the new ‘Photo to Video’ feature allows for the conversion of static images into short, six-second video clips. Users can select a photograph from their gallery and choose between two primary options: ‘Subtle movements’ for a gentle animation or ‘I’m feeling lucky’ for a more surprising, AI-driven outcome. Google has indicated that photos featuring people tend to yield the best results with this tool. Additionally, Google Photos is gaining a ‘Remix’ feature, which can transform images into various artistic styles, including 3D animations, comics, and sketches. Both the ‘Photo to Video’ and ‘Remix’ functionalities will be accessible through a new ‘Create’ tab within the Google Photos app, consolidating creative tools in one convenient location.
YouTube Shorts is also receiving a substantial AI-powered upgrade. The platform now allows users to add movement to landscape photos, animate everyday pictures, and convert group photos into videos. A new ‘AI Playground’ within YouTube Shorts, accessible via a sparkle icon in the camera, will house these generative AI creation tools, offering pre-suggested prompts and inspiration for users to generate videos, images, and even music. Generative effects will also be available, allowing for transformations such as turning a selfie video into an underwater scene or converting drawings into images, with Google promising ‘constantly refreshing’ options.
This integration of AI builds upon Google’s earlier introduction of video generation tools in Google Gemini. While the current features are powered by Veo 2, YouTube CEO Neal Mohan has announced plans to integrate the more advanced Veo 3 into YouTube Shorts in late summer 2025, further expanding the platform’s generative capabilities. Google emphasizes transparency and safety with these new experimental features, implementing invisible SynthID watermarks on all AI-generated content and encouraging user feedback to refine the tools and address potential issues. A ‘Red Team’ of security experts is also actively assessing potential problems and monitoring for abuse.
Also Read:
- Google’s Gemini AI Now Generates Crochet-Style Images from Text Prompts
- Google Integrates AI Mode Directly into Android Search Widget for Broader Access
Initial availability for the YouTube Shorts features includes users in the U.S., Canada, Australia, and New Zealand. The Google Photos features are rolling out to Android and iOS users in the U.S. over the coming week, with a broader global rollout anticipated in the second half of 2025.
