Gemini Omni 1.1 Flash lets you build with more control

Google has released Gemini Omni 1.1 Flash, a production-ready update for developers that enhances AI-driven video generation. The model now supports scene extension, allowing users to continue video clips seamlessly from prior context of up to 10 seconds, improving visual consistency. Videos can be extended in 10-second increments up to a cumulative length of 40 seconds, enabling longer narratives or new creative directions. Developers can access the model through Google AI Studio or the Gemini Enterprise Agent Platform.

Gemini Omni 1.1 Flash introduces tools for precise camera control, including the ability to specify start and end frames for smooth transitions. This feature supports complex camera movements such as orbits, zoom transitions, and seamless looping clips. The model generates continuous video between keyframes, ensuring flawless continuity without jump cuts. Examples include whip-pans revealing additional performers or zooms into repeating scenes, maintaining a single unbroken shot.

The update includes faster and more cost-effective prototyping with lightweight 360p previews generated up to 60% faster and at one-third the cost of standard 720p outputs. This capability is intended for rapid iteration in storyboard development and quick rendering within developer platforms. The model also supports high-fidelity scientific imaging, such as microscopic views of marine diatoms, maintaining lens effects throughout the video.

Gemini Omni 1.1 Flash now delivers polished, high-resolution outputs in 1080p or 4K, suitable for professional production. The model supports cinematic macro close-ups, such as vibrant Japanese maple leaves in 4K, and dynamic wildlife scenes like a chipmunk darting through a forest. These outputs are designed for integration into creative video workflows, media editing software, and generative video applications.