Google DeepMind has introduced Gemini Omni 1.1 Flash, a new suite of creative controls and generative video capabilities for developers. Available via the Gemini API in Google AI Studio, this update focuses on making video generation more controllable, efficient, and production-ready.

Key features include scene extension, which allows users to take an existing video and continue generating footage seamlessly. The model can now analyze up to 10 seconds of prior context, a significant improvement over previous versions that only referenced the final second. This results in better visual consistency and narrative adherence, enabling longer stories or branching creative directions.

Another feature is the ability to specify first and last frames, allowing for smooth transitions and camera movements. This is ideal for complex camera orbits, zoom transitions, or seamless looping clips. Users can define keyframes to guide the generation process.

Additionally, Gemini Omni 1.1 Flash supports faster drafting in 360p resolution, which is up to 60% faster and costs a third of the standard 720p output. This is useful for rapid prototyping and storyboard iteration. For final outputs, developers can upscale to 1080p or 4K, ensuring professional quality.

The update aims to empower developers to build advanced video workflows with greater precision and efficiency.