Google Updates Gemini Omni 1.1 Flash With 4K Video Controls

Google has rolled out Gemini Omni 1.1 Flash, a production-ready update designed to give developers greater authority over generative video workflows. Available through Google AI Studio and the Gemini Enterprise Agent Platform, the updated model introduces tools aimed at making AI-generated video more consistent, high-resolution, and cost-effective to produce.

A key addition is scene extension, which allows users to lengthen existing videos in 10-second increments up to a cumulative total of 40 seconds. To maintain visual consistency, the model now analyzes up to 10 seconds of prior context, a significant increase from the single second of context supported by previous models. Additionally, developers can specify start and end frames to guide camera movements and transitions, or upload up to three seconds of reference video to preserve character details and visual style across shots.

For practitioners looking to optimize their budgets, Gemini Omni 1.1 Flash introduces 360p preview generations. These low-resolution drafts render up to 60 percent faster and cost only one-third of the price of standard 720p outputs, allowing for rapid prototyping before committing resources. Once a concept is finalized, developers can upscale their projects to polished 1080p or 4K resolutions suitable for professional distribution.

These capabilities are already being integrated by industry partners. Adobe has incorporated the model into Adobe Firefly, while platforms like Figma Weave, GMI Cloud, and Runway are utilizing the API to help creative teams refine and guide their video generations. The update is also available to Google AI Plus, Pro, and Ultra subscribers within Google Flow and the Gemini app, signaling a shift toward highly controllable, professional-grade AI media editing.