Gemini Omni 1.1 Flash launches with scene extension, 4k upscaling and keyframe transitions

Google has introduced Gemini Omni 1.1 Flash, a set of generative-video controls available through the Gemini API in Google AI Studio and in Google Flow. The company says the release is ready for professional use in video workflows, creative tools, and media-editing software.

For longer sequences, scene extension can analyze up to 10 seconds of earlier footage, rather than only the final second in previous models. Developers can add footage in 10-second increments, with a cumulative video limit of 40 seconds. Google says the added context is intended to preserve visual consistency and narrative continuity.

Alongside scene extension, Omni 1.1 can generate a continuous shot between supplied starting and ending frames. This keyframe workflow supports transitions, camera orbits, zooms, and looping clips. The model also accepts video references of up to three seconds for retaining visual context and character consistency.

For iteration, Google offers 360p previews that it says are up to 60% faster and cost one-third as much as standard 720p generation. The option is aimed at prototyping, storyboards, and quick renders in developer platforms. Higher-resolution generation is also available at 1080p and 4K for production output.