Google Releases Gemini Omni 1.1 Flash: More Control Over Video Generation

Google has announced the release of Gemini Omni 1.1 Flash — an updated version of its generative video model aimed at developers. According to the company, the release is production-ready and available through the Gemini API in Google AI Studio, as well as on the Gemini Enterprise Agent Platform.

What's New

The main emphasis is on controllability. The scene extension feature lets you continue an existing video from the point where it left off. Google claims the model now analyzes up to 10 seconds of prior context — versus one second in earlier versions — which improves visual coherence and adherence to the storyline. A clip can be extended in 10-second steps, up to a total length of 40 seconds.

It's now possible to set the first and last frames: the model generates a continuous video between two keyframes. This is handy for complex camera fly-throughs, push-ins and seamlessly looping clips. You can also pass in up to three seconds of video as a reference, to preserve visual context and character consistency.

Cheaper Drafts, Polished Results

For rapid prototyping, the model offers lightweight previews at 360p resolution — according to Google, these generate up to 60% faster and are three times cheaper than standard 720p. The final material can be upscaled to 1080p or 4K.

Google illustrates the capabilities with example prompts and scenarios: an app that walks a camera through the rooms of a house “at the perfect time of day, without adding furniture that isn't there”; a “Draft Room,” where you can generate three or four variants in 360p, changing one parameter at a time, and compare them side by side.

Partners

The company cites testimonials from customers already using the model. Adobe has built Gemini Omni Flash into Firefly, and the model is available in Figma Weave and in Runway. A representative from GMI Cloud singles out the model's accuracy — in his words, for educational and explanatory content, reliability matters more than any single feature.

Omni 1.1 is rolling out across Google's ecosystem: in addition to AI Studio and the Agent Platform, the model is available to Google AI Plus, Pro and Ultra subscribers in the Google Flow service, and scene extension is available in the Gemini app.

Source: Hacker News