Google has introduced a groundbreaking photo-to-video feature within its Gemini AI assistant, allowing users to effortlessly turn images into eight-second video clips. This feature, now accessible to Gemini Advanced subscribers on the Ultra and Pro plans in select regions, utilizes the Veo 3 AI video model, offering enhanced capabilities previously found only in the standalone Flow platform. Users can upload a photo and provide accompanying text and audio prompts, generating videos complete with AI-generated sound effects and speech, delivered in 720p MP4 format. The Gemini interface lets users choose “video,” upload their image, and describe its movement. Videos generated include both a visible AI watermark and an invisible SynthID watermark. With this update, Google aims to compete with AI video solutions from companies like OpenAI and Runway AI, while promoting safe usage by restricting sensitive imagery and harmful content. As Flow expands to 75 additional countries, Gemini enhances accessibility to AI video generation.
Source link
Share
Read more