Google Gemini is now capable of transforming still images into dynamic video clips, breathing life into static photos with a new feature that leverages the power of its Veo 3 AI model. This innovative tool allows users to animate their favorite photos, turning them into engaging eight-second videos complete with sound.
The photo-to-video capability is accessible to Google AI Pro and Ultra subscribers in select regions. To use the feature, users can select "Videos" from the Gemini prompt interface, upload a photo, and provide a text description of the desired motion and audio elements. Gemini then generates a short video clip based on these inputs. Google encourages users to experiment with various images, including personal photos, sketches, and landscapes, to animate nature scenes or bring artwork to life.
Veo 3, the third-generation video generation model that powers this new functionality, was announced in May 2025. This model excels at generating high-fidelity video content from multimodal prompts and has already seen widespread adoption, with over 40 million videos created via the Gemini app and Flow in just seven weeks. Users have been exploring creative applications ranging from reimagining fairy tales to creating sensory-rich ASMR clips.
The resulting videos are currently capped at eight seconds in length and output at 720p resolution in a 16:9 landscape format. While these limitations exist, it is expected that social media formats and higher resolution options will become available in the future. All generated videos include a visible watermark to indicate they are AI-generated and an invisible SynthID digital watermark.
Google has implemented several safeguards to mitigate misuse, including red teaming exercises and proactive evaluations for potential abuse scenarios. This commitment to safety aims to ensure a responsible and appropriate experience when using the video generation tools.
The ability to turn photos into videos is straightforward. Users can animate everyday objects, bring drawings and paintings to life, or add movement to nature scenes. Once the video is complete, it can be easily shared with friends and family.
This new feature is also available in Flow, Google's AI filmmaking tool, which offers additional cinematic tools and options. Google AI Pro subscriptions start at $20 per month, while the Ultra subscription costs $250 per month.
Early users of the photo-to-video feature have expressed amazement at the results. The generated videos are described as coherent, cinematic, and remarkably realistic, with Gemini demonstrating an understanding of objects, depth, and context within the photo. The AI can add subtle camera pans, ripple water, create rising steam, or drift clouds across the sky while keeping the rest of the image stable. This level of detail and realistic motion is considered a significant step forward in content creation.
