Google DeepMind Unveils Gemini Omni 1.1 Flash with Advanced Video Controls

Google DeepMind has released Gemini Omni 1.1 Flash, a production-ready update to its generative video model, offering developers enhanced control over video creation. The update introduces scene extension, allowing videos to be extended in 10-second increments up to a total of 40 seconds, with the model analyzing up to 10 seconds of prior context for improved visual consistency. Developers can specify first and last frames to generate smooth transitions and camera movements, and can use 360p previews for faster, cheaper iteration (up to 60% faster and at a third of the cost of 720p). Final outputs can be upscaled to 1080p or 4K resolution. The model also supports video references in multimodal input, enabling character consistency. Gemini Omni 1.1 Flash is available via Google AI Studio and the Gemini Enterprise Agent Platform, and is integrated into products like Adobe Firefly, Figma Weave, GMI Cloud, and Runway. Notable quotes include Itay Schiff of Figma Weave praising its directing capabilities, Louisa Guo of GMI Cloud highlighting its accuracy, and Jamie Umpherson of Runway noting its natural fit. The update is part of Google's broader push into AI-driven creative tools, with availability for Google AI Plus, Pro, and Ultra subscribers globally in Google Flow and the Gemini app.