Gemini Omni 1.1 Flash adds video controls

Google shipped Gemini Omni 1.1 Flash on August 27, an update to its video-generation model that adds developer-facing controls: scene extension now analyzes up to 10 seconds of prior context (versus one second before), letting videos extend in 10-second increments up to 40 seconds total with better visual consistency; a new keyframe control lets developers specify first and last frames and have the model generate the transition between them; and a 360p preview mode renders draft videos far quicker, roughly 60% less render time, at about one-third what a standard 720p render costs, with a 4K upscaling option once a shot is locked. The model is available in Google AI Studio, the Gemini Enterprise Agent Platform, Google Flow (for AI Plus, Pro, and Ultra subscribers), and the Gemini app. Adobe Firefly, Figma Weave, Runway, and GMI Cloud have already integrated it into production workflows.

What it means for you

If you’re building video generation into a product, the 360p preview mode is the practical detail worth testing first: it lets you iterate on shot composition and camera movement cheaply before committing to a full-price 4K render, the same prototype-then-commit pattern that’s become standard across AI creative tools built for business use. Keyframe control also closes a real gap for anyone doing scripted rather than freeform generation, since specifying an exact end frame is more reliable than prompting for one. It’s also another data point in Google’s pattern of shipping Gemini capabilities aggressively now and figuring out the business model later.