Google has announced a significant update to its Gemini AI platform, introducing a new feature that allows users to transform their photos into dynamic eight-second video clips with sound. The tool, powered by Google's latest video generation model Veo 3, is now available to Google AI Pro and Ultra subscribers in over 150 countries, with the company highlighting rapid uptake and creative experimentation since the model's initial launch.
David Sharon, Multimodal Generation Lead for Gemini Apps, said, "We launched our state-of-the-art video generation model Veo 3 in May - and last week, we expanded access to Google AI Pro subscribers in over 150 countries. Now, with a new photo-to-video capability in Gemini, you can now transform your favourite photos into dynamic eight-second video clips with sound."
Describing the process, Sharon added, "To turn your photos into videos, select 'Videos' from the tool menu in the prompt box and upload a photo. Then, describe the scene and any audio instructions, and watch as your still image transforms into a dynamic video. You can get creative by animating everyday objects, bringing your drawings and paintings to life or adding movement to nature scenes. Once your video is complete, tap the share button or download it to share with friends and family."
According to Google, the reception from users has been swift and enthusiastic. "The explosion of creativity from users has been truly remarkable, with over 40 million Veo 3 videos generated across the Gemini app and Flow over the last seven weeks. From reimagining fairy tales through the eyes of a modern influencer, to ASMR videos exploring what it would sound like to cut through a piece of cooling lava, your imagination is the limit when you create videos with Gemini," Sharon said.
The new photo-to-video feature is being rolled out alongside broader access to Veo 3, Google's latest iteration in text-to-video artificial intelligence. Veo 3 is already recognised for its ability to produce high-definition video clips with synchronised sound and lifelike motion, generated entirely from user prompts. The model delivers results in eight-second clips, integrating both visuals and audio without the need for post-production editing.
Google is positioning Veo 3 as both a creative and enterprise solution, with businesses able to access the technology through the Google Cloud Vertex AI platform. Creative professionals and app developers have begun using Veo 3 to accelerate workflows, generate marketing assets, and prototype video content in a fraction of the time previously required.
The company also emphasises its commitment to responsible AI development and safety. "When you use our video generation tools, we want you to feel confident in the results. That's why we take significant steps behind the scenes to make sure video generation is an appropriate experience," Sharon explained. This includes what Google describes as "extensive 'red teaming,' in which we proactively test our systems and aim to fix potential issues before they arise," as well as "thorough evaluations to understand how our tools might be used and how to prevent any misuse."
Safety measures extend to content labelling, as Sharon detailed: "All generated videos include a visible watermark to show they are AI-generated and an invisible SynthID digital watermark." Users are also encouraged to provide feedback on generated content, with Sharon stating, "Use the thumbs up and down buttons on your generated videos to give us feedback, which we'll use to make ongoing improvements to our safety measures and overall experience."
Access to the new photo-to-video capability begins rolling out today for Google AI Pro and Ultra subscribers in select countries. The same functionality is also available in Flow, Google's AI filmmaking tool, with the company continuing to expand availability to additional regions.
"Your imagination is the limit when you create videos with Gemini," said Sharon.
