Google updates Gemini Omni Flash for longer video scenes

Google DeepMind released Gemini Omni 1.1 Flash on August 27, 2026, updating the Gemini Omni Flash video generation family available through the Gemini API and Google Vids. A single generation still produces a 3-to-10-second clip at 24 frames per second, with output options listed as 360p, 720p, 1080p, or 4K.

The main change is continuation. Gemini Omni 1.1 Flash can extend scenes in 10-second increments while referencing up to 10 seconds of previous footage, rather than relying on only the final second. Chaining four segments can produce a cumulative 40 seconds of usable footage, though it is not a single continuous render.

The update also adds first and last frame control, letting developers define the opening and closing images of a shot while the model generates the motion between them. The feature is aimed at more predictable camera moves, transitions, and production workflows than text prompts alone.

4K upscaling gives teams a higher delivery option without requiring a native full-resolution base render, positioning the Flash-tier model for lower-cost, high-volume use cases such as ads, demos, explainers, and internal business video. Google has not published a head-to-head benchmark against a named competitor or detailed pricing changes tied specifically to the 1.1 update.