Google DeepMind releases Gemini Omni 1.1 Flash with expanded generative video controls

Google DeepMind announced Gemini Omni 1.1 Flash, a production-ready update for developers that expands control over generative video workflows. The model is accessible through the Gemini API in Google AI Studio and the Gemini Enterprise Agent Platform.

New capabilities include scene extension, which allows developers to continue generating footage from an existing video using up to 10 seconds of prior context—an increase from prior models that only referenced the final second. This improves visual consistency and narrative flow, enabling extensions in 10-second increments up to a cumulative 40 seconds.

The update also introduces start and end frame controls for smoother camera movements and transitions, as well as 360p previews for faster iteration and cost savings during prototyping. Final outputs can be upscaled to 4K resolution for polished, professional results.