Photos into Video conversion is now possible with Gemini AI
Google has unveiled a powerful new Gemini AI feature that allows users to transform static images into dynamic video clips. This new photo-to-video tool is driven by Google’s advanced Veo 3 video generation model and can create immersive eight-second videos from a single reference photo. The tool doesn’t just animate visuals—it also enhances the experience with AI-generated soundtracks that include ambient background noise, environmental sounds, and even realistic speech if prompted.
Exclusively available to Gemini AI Ultra and Pro users in select regions, this innovative update is being rolled out across web platforms starting today, with mobile device compatibility arriving progressively over the coming week. Users can access this capability directly within the Gemini interface by selecting the “tools” option in the prompt bar. From there, they can choose the “video” feature, upload their image, and provide a descriptive prompt outlining how they want the image to animate. The system also accepts text-based audio cues to integrate synchronized sound effects, dialogue, or natural sounds that align perfectly with the visual sequence.
The produced outputs are provided in MP4 format, which has a cinematic 16:9 landscape aspect and 720p resolution. These videos are marked with a visible watermark that clearly identifies them as AI-generated, along with a hidden SynthID digital watermark for authenticity and traceability.
According to Google, this tool opens up a range of creative possibilities—from animating personal artwork and illustrations to adding life and movement to still nature shots or ordinary objects. The feature is designed to inspire users to explore storytelling and visual creativity using only a photo and their imagination.
This new functionality mirrors similar features found in Google’s generative video creation platform, Flow, launched earlier this year. However, with this integration, users can now animate photos directly within Gemini, removing the need to switch applications. Google also announced that Flow will be expanding to 75 more countries starting today, further widening access to its creative AI tools.
