Gemini Omni 1.1 Flash: Scene Extension Up to 40 Seconds Cumulative, Plus 4K Upscaling

Google's video model now reads up to 10 seconds of prior context and extends clips in 10-second steps to 40 seconds total, with keyframe control, 360p previews and 4K output.

Google Gemini video-generation generative-AI developer-tools

Google released Gemini Omni 1.1 Flash for developers on August 27, 2026 ¹. Its scene extension feature analyzes up to 10 seconds of prior context — previous models referenced only the final second — and clips can be extended in 10-second increments up to a total cumulative length of 40 seconds ¹.

The release also adds the ability to specify a shot’s starting and ending frames and generate continuous video between them, and to reference up to three seconds of video as input ¹. Lightweight 360p previews generate up to 60% faster and at a third of the cost compared with the standard 720p, a speed figure Google bases on system throughput of 360p versus 720p ¹. Final output can be rendered at 1080p or 4K ¹.

It is available through the Gemini API in Google AI Studio and the Gemini Enterprise Agent Platform, with the model ID gemini-omni-1.1-flash. In Google Flow it is available to Google AI Plus, Pro and Ultra subscribers globally starting the same day ¹.