Google releases Gemini Omni 1.1 Flash with more control over video generation
Scenes can now be extended in ten-second increments to 40 seconds total, and a 360p draft mode renders previews at roughly a third of standard-resolution cost.
- Models & capabilities
- Minor
Google released Gemini Omni 1.1 Flash, an update to the video-focused Gemini Omni model it introduced in May 2026. The update adds controls aimed at production workflows rather than one-shot generation: scenes can now be extended in ten-second increments up to a total of 40 seconds, with the model analysing up to ten seconds of prior context to keep each extension visually consistent, and users can set a first and last frame and have the model generate a continuous transition between them.
The update also added a 360p draft mode, which Google said rendered previews up to 60% faster and at roughly a third of the cost of standard 720p generation, meant for iterating on a concept before committing to a final render, alongside native upscaling to 1080p or 4K for finished output. The company framed the changes as giving developers and creators more precision over generation rather than expanding what the model could depict.
The model is available through Google AI Studio and the API-based Gemini Enterprise Agent Platform for developers, and through the consumer Flow app for Plus, Pro and Ultra subscribers, with scene extension also reaching Gemini app subscribers. The staged rollout across developer, enterprise and consumer surfaces followed the pattern set by the original Omni launch, which had shipped simultaneously inside YouTube Shorts Remix.
In the commentary
What people were saying around this time — external links, from the record's commentary rail.