TLDR: Google Photos has rolled out an update integrating its advanced generative AI video model, Veo 3, allowing users to transform their static images into dynamic videos. This feature, available in the ‘Create’ tab, offers options for subtle movement or an ‘I’m feeling lucky’ approach, with enhanced capabilities for Google AI Pro and Ultra subscribers. The update positions Google Photos alongside other leading AI video generation tools, emphasizing accessibility and creative potential.
Google Photos has significantly upgraded its image-to-video capabilities by integrating Veo 3, Google’s highly regarded generative AI video model. As of Thursday, September 4, 2025, this enhancement allows users to effortlessly convert their favorite photographs into short, animated video clips directly within the Google Photos application. This follows an initial introduction of an image-to-video feature for U.S. users in July, which is now powered by the more sophisticated Veo 3.
Veo 3 is widely considered one of the most advanced AI video models currently available, competing with offerings from other tech giants and startups such as OpenAI’s Sora, xAI’s Grok, Runway, Pika, Freepik, and Kling AI. The integration into Google Photos makes this cutting-edge technology accessible to a broader audience, enabling users to bring cherished memories to life or create novel content for social media.
Users can access this new functionality through the ‘Create’ tab in Google Photos. Upon selecting a photo, they are presented with two primary prompts: ‘Subtle movement’ or ‘I’m feeling lucky,’ offering a streamlined approach to video generation. While image and video models are resource-intensive to operate, Google Photos provides a limited number of daily generations for standard users. Subscribers to Google AI Pro ($20 per month) and Google AI Ultra ($200 per month) benefit from higher daily generation limits, reflecting the premium nature of the service.
Beyond Google Photos, Veo 3’s capabilities are also integrated into the Gemini app, where users can upload images and provide text prompts to generate videos, complete with audio. These generated videos are typically eight seconds long and rendered in 720p resolution at 24 frames per second, making them ideal for sharing on social media platforms. Google has also addressed concerns regarding misinformation by ensuring all videos generated by Veo 3 include both a visible watermark and an invisible SynthID watermark.
Also Read:
- NVIDIA Unveils AI Blueprint for Enhanced 3D-Guided Generative Image Creation
- Google Unleashes ‘Jules’ Autonomous AI Coding Agent, Intensifying AI Development Race
This update builds upon Google Photos’ existing suite of generative AI-powered photo editing features, which include remixing photos into new styles, creating and editing collages, generating video highlight reels, transforming photos into 3D Cinematic Photos, and animating still images into GIFs. The continuous evolution of these tools underscores Google’s commitment to leveraging artificial intelligence to enhance user creativity and interaction with their digital memories.
