Gemini Omni 1.1 Flash lets you build with more control
Google ● Covered by 3 sources
Google DeepMind added Gemini Omni 1.1 Flash with new video controls. It can extend scenes, use keyframes, and upscale to 4K for more polished work.
Based on reporting by Google — read the original for the full story.
Summary, retelling and take written by AI under human oversight; images are AI-generated illustrations. How we work · Report an error
Google DeepMind is pushing Gemini Omni closer to a real production tool. The new Gemini Omni 1.1 Flash adds creative controls for generative video, and the company says it is now production-ready for professional use through the Gemini API in Google AI Studio.
The big shift is control. Developers can extend an existing scene by feeding the model up to 10 seconds of prior context, instead of only the final second as before. Those extensions happen in 10-second steps and can reach a total length of 40 seconds. That should help with longer stories and with keeping the visual thread intact when a scene keeps moving.
There’s also frame control. Omni 1.1 can generate continuous video between a starting frame and an ending frame, which Google says is useful for camera orbits, zooms, and seamless loops. It can also take up to three seconds of video reference, which helps preserve character consistency and visual context when developers are building with multiple clips.
Speed and cost get a bump too. Google says 360p previews can be generated up to 60% faster and at a third of the cost of standard 720p output. Then there’s upscaling: outputs can be polished to 1080p or 4K, which makes the model look less like a demo toy and more like something a production team might actually slot into a workflow.
Omni 1.1 is rolling out across Google’s developer ecosystem, including Google AI Studio and the Gemini Enterprise Agent Platform. It’s also available globally to Google AI Plus, Pro and Ultra subscribers in Google Flow, while scene extension is available in the Gemini app for those same subscribers.
My take — AI-written commentary, not fact-checked reporting
Google is doing the sensible thing here: less magic, more controls. That’s usually the moment generative video stops being a party trick and starts becoming software. The race now is not who can make the flashiest clip, but who can keep a scene from drifting off into nonsense after the third prompt.
Read more about this at: Google