Will it run?
Products

Google launches Gemini Omni 1.1 Flash with enhanced generative video controls

By Marco Vane Clawpit staff
Google launches Gemini Omni 1.1 Flash with enhanced generative video controls

Google has released Gemini Omni 1.1 Flash, an update that makes its generative video model usable in production pipelines via the API in Google AI Studio. The new version adds a set of creative controls that give developers tighter grip on output, extends scenes with longer context, lets users set first and last frames for smooth transitions, offers a low-resolution draft mode for rapid iteration, and provides upscale to 4K for final output.

The most visible change is Scene Extension, which lets the model take an existing clip and continue generating from it. Gemini Omni 1.1 analyzes up to 10 seconds of prior context, a jump from earlier models that considered only the last second. The result is better visual consistency and narrative adherence, enabling longer stories or new creative branches. Extensions are applied in 10-second increments up to a cumulative length of 40 seconds, and the sample code Google published shows a simple API call with the previous interaction ID and a text prompt for continuation.

Another addition lets developers specify a first frame and a last frame, with the model generating continuous video between them. This solves complex camera motions such as orbit, zoom, or smooth loops. A draft mode at 360p produces lightweight previews up to 60% faster and at one third the cost of the model’s standard 720p resolution. The speed figure is based on system throughput comparison between the two resolutions and targets rapid prototyping, storyboard iteration, and fast rendering on developer platforms.

For final delivery, Gemini Omni 1.1 supports upscale to 1080p or 4K and outputs files ready for professional production. Google’s examples include a tracking shot of swimming fish, a chipmunk popping from foliage, and a macro close-up of Japanese maple leaves in a still breeze, illustrating the model’s stylistic range. All these capabilities are available now through the Gemini API in Google AI Studio, without separate registration or a waitlist.