New update lets users create 8-second AI-generated video clips from still images
Google has added a new photo-to-video feature to its Gemini platform, allowing users to convert static images into eight-second AI-generated videos complete with sound. The feature is part of Gemini’s expanding creative toolset and follows the recent India launch of Veo 3, Google’s advanced video generation model.
Since its debut in May, Veo 3 has powered the creation of over 40 million videos globally through the Gemini app and Flow, Google’s AI filmmaking tool. The new update is now rolling out to Google AI Pro and Ultra subscribers in select markets.
The feature enables users to animate still images-such as turning nature photos into dynamic scenes or bringing sketches to life. To access the tool, users simply select ‘Videos’ in the Gemini prompt bar, upload a photo, and describe the desired visuals and audio. The AI then generates a clip that can be downloaded or shared instantly.
Google emphasized its commitment to safety and transparency, noting that all AI-generated videos include visible and invisible watermarks, along with robust content moderation systems to ensure responsible use.
