Google Upgrades Gemini AI Video: What Omni 1.1 Changes for Creators

Google has enhanced its AI video generator, Gemini Omni 1.1 Flash, with new capabilities aimed at providing more control to creators. The update allows developers to extend existing video footage in 10-second increments, up to a combined total of 40 seconds, while maintaining visual and narrative consistency. This improvement addresses the challenge of creating longer AI video clips without introducing inconsistencies.

Developers can also control how generated sequences transition between two points by specifying the first and last frames. However, the model still has limitations, generating only 3–10 seconds of video in a single pass, requiring multiple extensions to reach the 40-second maximum. Additionally, video inputs for reference are limited to short inputs of 3 seconds.

The new features are available across Google's developer and creator tools, including Google AI Studio, the Gemini API, Google Flow, and the Gemini Enterprise Agent Platform. The cheaper 360p option is designed for experimentation, allowing developers to generate lower-resolution previews while testing prompts and visual elements before moving to higher-quality outputs.

Omni 1.1's controls can make the generation process more predictable, potentially moving AI video creation a step closer to being a practical tool for creators.