Gemini Omni 1.1 Flash: 5 Powerful New AI Video Features

Google just gave developers a major upgrade to its AI video generation toolkit. Gemini Omni 1.1 Flash, announced August 27, 2026, adds longer scene extensions, precise camera controls, and 4K upscaling to a model Google is now calling “production-ready” for professional use.

1. Scenes Can Now Extend Up to 40 Seconds

The biggest headline feature is scene extension. Where the previous version only referenced the final second of a clip when continuing it, Gemini Omni 1.1 Flash analyzes up to 10 seconds of prior footage, producing more visually consistent continuations that better preserve character identity, lighting, and narrative flow. Extensions happen in 10-second increments, letting a clip grow to a cumulative 40 seconds total.

It’s worth being precise about what that actually means: each individual generation still runs 3 to 10 seconds at 24fps. The 40-second figure isn’t one continuous generation — it’s the result of chaining extensions together, with the model referencing the prior clip each time it continues the story.

2. Developers Can Set First and Last Frames

Gemini Omni 1.1 Flash now lets developers specify the starting and ending frame of a shot, with the model generating everything in between. Google says this is designed for precise camera movements like orbits and zooms, giving far more control over a shot’s composition than a single text prompt alone typically allows.

3. Video References Guide Character and Motion

Developers can now upload up to three seconds of external footage as a reference, letting Omni 1.1 carry over specific movement patterns, visual context, or character consistency into a new generation — useful for keeping a recurring character or style consistent across multiple clips.

4. Cheaper, Faster 360p Drafts

For early-stage prototyping, Omni 1.1 adds a 360p draft mode that runs up to 60% faster and costs a third as much as generating in 720p, Gemini’s default resolution. This lets developers iterate quickly and cheaply before committing to a full-quality render.

5. Upscaling to 1080p and 4K — With a Caveat

Finished clips can now be upscaled to 1080p or 4K for polished, professional-looking output. The important fine print: Google’s own API documentation confirms these resolutions are upscaled rather than natively generated. Gemini Omni 1.1 Flash still generates video at 720p by default, with 4K arriving through post-generation upscaling rather than native rendering.

Pricing and Availability

Gemini Omni 1.1 Flash is priced per second of generated video: $0.03 for 360p, $0.10 for 720p, $0.15 for 1080p, and $0.30 for 4K. It’s available now through the Gemini API in Google AI Studio and Google’s Gemini Enterprise Agent Platform for developers. On the consumer side, it’s rolling out globally in Google Flow for AI Plus, Pro, and Ultra subscribers, with scene extension specifically also available to those subscribers directly in the Gemini app.

Frequently Asked Questions

1.What is Gemini Omni 1.1 Flash?

It’s Google’s updated video generation and editing model, announced August 27, 2026, adding longer scene extensions, camera keyframe controls, and 4K upscaling for developers.

2.Does Gemini Omni 1.1 Flash generate 4K video natively?

No. Google’s documentation confirms 1080p and 4K outputs are upscaled from lower-resolution generations rather than created natively at those resolutions.

3.How long can a Gemini Omni 1.1 Flash video be?

Individual generations run 3 to 10 seconds. Through chained scene extensions in 10-second increments, a clip can reach a cumulative 40 seconds.

4.How much does Gemini Omni 1.1 Flash cost?

Pricing is per second of video generated: $0.03 for 360p, $0.10 for 720p, $0.15 for 1080p, and $0.30 for 4K.

5.Where can I use Gemini Omni 1.1 Flash?

Developers can access it through the Gemini API in Google AI Studio, while consumers can use it in Google Flow with an AI Plus, Pro, or Ultra subscription.

Gemini Omni 1.1 Flash: The 1 Shocking Catch Revealed