Gemini Omni 1.1 Flash

Google DeepMind has introduced Gemini Omni 1.1 Flash, an updated version of its Gemini Omni model that adds studio-quality video production capabilities for developers. The update is available via the Gemini API in Google AI Studio and targets developers building generative video workflows, creative tools, and media editing software.

A key new feature is scene extension, which lets developers take an existing video and continue generating footage seamlessly. Omni 1.1 can analyze up to 10 seconds of prior context—up from only the final second in previous models—improving visual consistency and narrative adherence. Videos can be extended in 10-second increments up to a cumulative length of 40 seconds.

The update also lets developers specify first and last frames to generate continuous video between two keyframes, enabling smooth transitions, camera orbits, zoom transitions, and seamless looping clips. Example prompts show complex shots such as a whip-pan from a drummer to a saxophonist and a camera zoom into a TV screen.

For rapid prototyping, Gemini Omni 1.1 Flash supports 360p previews that generate up to 60% faster and at a third of the cost compared to the standard 720p resolution, based on system throughput. The announcement also mentions crisp 4K upscaling as part of the studio-quality toolkit. Together, these features make Omni 1.1 production-ready for professional use.