Google Upgrades Gemini Omni With 4K Video and Longer Scenes

Google has released an upgraded version of its AI video generation and editing model, Gemini Omni 1.1 Flash, with several notable enhancements. The new model supports longer scene extensions, allowing creators to extend videos up to 40 seconds in length with maintained characters, environments, and storylines. It also offers first and last frame controls, enabling users to generate continuous videos connecting two keyframes.

Additionally, Gemini Omni 1.1 Flash can create 4K output and features a 360p draft mode, which generates lower-resolution drafts up to 60% faster and at one-third the cost of standard 720p drafts. The model accepts up to three seconds of reference video as input, allowing creators to transfer movement or visual information from existing clips.

Gemini Omni 1.1 Flash is now generally available to developers via the Gemini API in Google AI Studio, with enterprise access through the Gemini Enterprise Agent Platform. The upgraded model is already integrated into products from Adobe, Figma, GMI Cloud, and Runway, as well as Google Flow for AI Plus, Pro, and Ultra subscribers.