Gemini Omni 1.1 Flash lets you build with more control

Details

Gemini Omni 1.1 Flash is a developer-facing update to Google's generative video model, now available via the Gemini API in Google AI Studio. The release introduces four capabilities aimed at professional video workflows. Scene extension is the most technically significant change: the model can now analyze up to 10 seconds of prior video context before generating a continuation, compared to just 1 second in previous versions. This 10x increase allows the model to maintain visual consistency and narrative continuity across longer generated sequences — a meaningful improvement for multi-shot production workflows. First/last frame interpolation lets developers anchor start and end frames, giving programmatic control over camera movement and transitions. This is directly useful for building tools that need deterministic visual connectors between clips. The 4K upscaling feature enables high-resolution final renders, while 360p preview mode lets developers iterate quickly at a fraction of the compute cost before committing to final-quality generation. The update is available immediately through Google AI Studio and the Gemini Enterprise Agent Platform, making it accessible to developers already in the Google AI ecosystem without a separate waitlist. For teams building AI-powered video editing tools or generative media pipelines, Omni 1.1 Flash represents a meaningful step toward controllable, production-ready video generation.