What you need to know
In a significant advancement for digital memory-making, Google has unveiled its latest feature in the Gemini app, allowing users to transform still images into dynamic videos. This innovative capability, powered by the Veo 3 technology, enables subscribers of Google AI Pro or Ultra to simply upload a photo and provide a detailed text description of their desired video output. Users can even specify unique soundscapes to accompany their creations, enhancing the overall experience.
Earlier this year, Google Cloud introduced a similar photo-to-video feature for Honor’s 400 series, utilizing the Veo 2 model. This earlier iteration allowed users to generate brief animated clips from their photos, mirroring the functionality now available in Gemini. However, the Honor version required a subscription for ongoing use after an initial trial period.
During the recent I/O 2025 event, Veo 3 was showcased as a standout technology, highlighting its impressive audio capabilities and lifelike video generation. As Gemini embraces this new feature, it appears that YouTube is also keen on integrating Veo 3 into its Shorts platform, signaling a broader application of this technology across Google’s ecosystem.
Google has emphasized its commitment to user safety with these AI tools, stating that it has implemented significant measures to ensure a responsible and appropriate user experience. As Gemini continues to evolve, it stands poised to redefine how users engage with their memories, turning static images into vibrant narratives.
