Gemini Omni 1.1 Flash Extends Video to 40 Seconds, and Upscales to 4K

Image: blog.google
Google announced Gemini Omni 1.1 Flash on August 27, 2026.
Scene extension works in 10-second increments up to a cumulative 40 seconds, and the model now reads up to 10 seconds of preceding video as context. Earlier versions referenced only the final second, which is the change Google credits for the improvement in visual and narrative continuity.
The release also adds first-and-last-frame control, generating the video between two supplied keyframes, and accepts up to three seconds of reference video in multimodal input for character consistency. A 360p draft mode renders up to 60% faster and at one third the cost of standard 720p output.
One detail is easy to misread from the headline figures: 1080p and 4K are produced by upscaling, not generated natively at those resolutions.
It is available through Google AI Studio and the Gemini Enterprise Agent Platform API. Consumer access arrives through Google Flow for AI Plus, Pro and Ultra subscribers, with scene extension also available in the Gemini app.
Related AI News
Enjoyed this? Get more in your inbox.
Up to ten of the week's AI news stories, by email once a week.