By Ken Muthomi - Reporter
US , August 27, 2026 - Google has launched Gemini Omni 1.1 Flash, an upgraded generative AI model that introduces new creative controls and video generation capabilities for developers and professional content creators.
The tech giant said on Thursday that the model makes generative video more controllable, faster to iterate, and suitable for real-world production through the Gemini API in Google AI Studio.
Google said Omni 1.1 is now available through Google AI Studio and the Gemini Enterprise Agent Platform, alongside developer documentation, a cookbook and prompting guides for integrating its new video capabilities into applications.
The model is also available globally to Google AI Plus, Pro and Ultra subscribers through Google Flow, while the scene extension feature is available to subscribers through the Gemini app.
“Gemini Omni brought real-world reasoning to generative creation, and today’s updates make Omni 1.1 production-ready for professional use via the Gemini API in Google AI Studio,” the company stated.
“Whether you’re building generative video workflows, creative tools, or media editing software, these updates make generative video more controllable, faster to iterate on, and polished for real-world deployment,” it added.
One of the most notable upgrades is scene extension, which allows developers to continue an existing video seamlessly from where it ends. According to Google, the model can analyse up to 10 seconds of previous video context, compared to earlier models that referenced only the final second.
Omni 1.1 also allows developers to specify the first and last frames of a shot, enabling the model to generate video between two keyframes. Google said the feature can be used for camera movements such as orbits and zooms, as well as creating seamless looping clips.
The company has also introduced a 360p drafting mode, allowing developers to generate lightweight video previews up to 60 per cent faster and at one-third the cost of the standard 720p resolution.
Omni 1.1 can generate 1080p and 4K video outputs, while allowing developers to provide up to three seconds of reference video as multimodal input to maintain visual context and character consistency for professional production.
More from Kenya