Google has updated its Gemini Omni Flash video model to version 1.1, introducing changes to how scenes are extended and priced. The new system now analyses up to ten seconds of existing footage rather than just the final second to improve visual consistency. Developers can extend scenes in ten-second blocks reaching a maximum of forty seconds. External clips of three seconds serve as style references for characters or motion, while users can set start and end frames to define camera movements between keyframes. A draft mode generates 360p video up to sixty percent faster at one third the cost of 720p output. Final clips upscale to 1080p or 4K. Current per-second rates stand at $0.03 for 360p, $0.10 for 720p, $0.15 for 1080p, and $0.30 for 4K. The model is available via Google AI Studio and developer documentation.
These updates lower the barrier for creating longer, higher-quality video content without significant financial overhead. The extended analysis window reduces the likelihood of visual drift during generation, making the tool more practical for professional workflows. Lower pricing for draft resolutions allows rapid iteration before finalising high-definition exports.
* Ten-second analysis window replaces single-second input
* External three-second clips act as style references
* Draft mode runs 60% faster at one third the cost
