Gemini Omni 1.1 Flash introduces production controls for generative video

Google has released Gemini Omni 1.1 Flash, a production-ready update designed to give developers greater control over generative video workflows. Available through Google AI Studio and the Gemini Enterprise Agent Platform, the model brings studio-quality video production capabilities to developer applications.

Extended scene generation

A primary feature of the new release is scene extension, which allows developers to take an existing video clip and continue generating footage seamlessly from where it left off. Previous iterations could only reference the final second of a video, but Omni 1.1 can analyze up to 10 seconds of prior context. This expanded context window — the amount of data the model can process at once — improves visual consistency and narrative flow. Developers can extend videos in 10-second increments up to a total cumulative length of 40 seconds.

Keyframe interpolation and upscaling

The model also introduces first and last frame interpolation, letting creators specify the starting and ending frames of a shot to generate smooth transitions, complex camera orbits, and looping clips. For output quality, developers can generate high-resolution outputs up to 4K resolution for polished, professional results.