How to Create AI Videos from Photos with Google Gemini: A Step-by-Step Guide

Google has launched an exciting new feature in its Gemini apps, allowing users to create short AI-generated videos from photos or text descriptions. This tool, powered by the Veo 3 AI model, simplifies video creation and makes the process more accessible. Users can access this feature on their computers, Android phones, and iPhones. To use the feature, personal account holders need a Google AI Pro or Google AI Ultra subscription, while those with work or school accounts need a qualifying Workspace license. The feature is available in most countries with a Google AI Pro subscription, though it is currently not available in the European Economic Area, Switzerland, or the United Kingdom. To generate a video, users can visit the Gemini website or open the app on their mobile device, choose the video icon, and upload a photo or enter a text prompt describing the desired video. The videos created are typically 8 seconds long and take 1 to 2 minutes to generate. Users are also limited in the number of videos they can create, with higher limits for those subscribed to Google AI Ultra. Google has stated that videos violating its Terms of Service may be removed.