Google has launched a new photo-to-video feature in Veo 3, its advanced AI video generation model, enabling users to transform static images into dynamic eight-second video clips with audio. The feature is now available to Google AI Pro and Ultra subscribers in select countries through the Gemini app and the Flow video creation tool.
How the Photo-to-Video Feature Works
To create a video from a photo using Veo 3:
- Select the ‘Videos’ option in the prompt box.
- Upload a photo.
- Describe the scene and optionally provide audio cues or instructions.
- Gemini then animates the image, generating a short video that can include moving objects, animated landscapes, or even bring hand-drawn art to life. The final output can be downloaded or shared directly from the app.
Since its launch in May 2025, users have generated over 40 million videos with Veo 3 across Gemini and Flow, exploring creative themes from modern fairy tales to ASMR soundscapes.
Safety and Content Integrity
Google emphasizes robust safety measures for AI-generated content:
- Extensive “red teaming” is used to proactively test the system and address potential risks before public release.
- Ongoing evaluations and policy enforcement guard against misuse and unsafe content.
- Every AI-generated video includes a visible watermark and an invisible SynthID digital watermark to ensure transparency and traceability.
Users are encouraged to provide feedback using thumbs up/down tools to help improve future updates and maintain content quality.
Availability
The photo-to-video feature is rolling out gradually to Google AI Pro and Ultra subscribers in over 150 countries. It is accessible via gemini.google.com and through Flow, Google’s AI video creation platform.
This update positions Veo 3 as a powerful tool for creators, educators, and anyone looking to bring still images to life with AI-powered video and audio generation.