Google releases Gemini Omni 1.1 Flash with scene extension and 4K video upscaling

Gemini Omni 1.1 Flash adds longer scene extensions, first-and-last-frame control, video references, faster 360p drafts, and 1080p or 4K upscaling.

Quick answer

Google announced Gemini Omni 1.1 Flash on August 27, 2026 as a production-ready update for AI video generation and editing. It can extend scenes in 10-second increments to a cumulative 40 seconds, generate transitions between specified first and last frames, accept short video references, create faster 360p drafts, and upscale finished output to 1080p or 4K. The exact model is not currently verified in Chat AI's model directory.

Download Chat AI Opens the official App Store or Google Play for your device.

Quick answer: what is new in Gemini Omni 1.1 Flash?

Gemini Omni 1.1 Flash is Google's updated generative-video model for developers and creators. The release adds scene extension, first-and-last-frame interpolation, short video references, low-resolution drafts, and higher-resolution finishing. Google says the model is production-ready through the Gemini API and is also rolling out across Google Flow and parts of the Gemini app.

Sources: Google, Google DeepMind

Scene extension can build a video up to 40 seconds

Omni 1.1 can analyze up to 10 seconds of an existing scene and continue it in 10-second increments, up to a cumulative length of 40 seconds. This is intended to preserve more visual and narrative context than a workflow that only generates disconnected clips. Continuity can still vary, so important characters, objects, dialogue, and camera direction should be checked after every extension.

Sources: Google, Google AI for Developers

First and last frames give creators more control over transitions

Creators can provide the starting and ending frames of a shot and ask Omni 1.1 to generate the movement between them. Google positions this for controlled camera moves, loops, and transitions that need a defined destination rather than an open-ended prompt. The model can also use up to three seconds of reference video to carry motion or visual context into a new generation.

Sources: Google, Google DeepMind

Use 360p for drafts, then finish at 1080p or 4K

The release introduces 360p previews for faster and less expensive iteration. Google reports that these drafts can be generated up to 60% faster than standard 720p output and at one-third of the cost, based on its system-throughput comparison. Once the composition and motion are right, the result can be upscaled to 1080p or 4K. Upscaling increases resolution; it does not guarantee that incorrect details in the generated scene will be fixed.

Sources: Google, Google AI for Developers

Where Gemini Omni 1.1 Flash is available

Developers can access Omni 1.1 through Google AI Studio and the Gemini API, while enterprise teams can use the Gemini Enterprise Agent Platform. Google also says the model is available to Google AI Plus, Pro, and Ultra subscribers in Google Flow. Scene extension is rolling out to those subscription tiers in the Gemini app. Availability can depend on product, plan, country, and account rollout.

Sources: Google, Google AI for Developers

Gemini Omni 1.1 Flash is not yet verified in Chat AI

The exact Gemini Omni 1.1 Flash model name is not listed in Chat AI's current verified model directory, so this article does not claim that it is available in the app. Chat AI can still be used for everyday conversations, research, writing, and comparing answers from its listed models; use Google's announced products when the task specifically requires Omni 1.1 video generation or editing.

Sources: Chat AI, Google

Frequently asked questions

What readers usually ask

What is Gemini Omni 1.1 Flash?

It is Google's production-ready update to Gemini Omni Flash for generative video. It supports video generation and editing with scene extension, reference inputs, transition controls, draft resolutions, and high-resolution output.

How long can an extended Omni 1.1 video be?

Google says scenes can be extended in 10-second increments up to a cumulative length of 40 seconds.

Can Omni 1.1 generate video between two images?

Yes. The release supports specifying first and last frames so the model can generate the transition between them.

Does Gemini Omni 1.1 Flash support 4K video?

Google says completed videos can be upscaled to 1080p or 4K. Creators can use 360p previews while iterating before producing a higher-resolution result.

Is Gemini Omni 1.1 Flash available in Chat AI?

The exact model is not currently listed in Chat AI's verified model directory, so its availability in Chat AI is unverified.

Evidence

Sources

  1. Gemini Omni 1.1 Flash release announcementGoogle · Primary source
  2. Gemini Omni model overviewGoogle DeepMind · Primary source
  3. Gemini Omni Flash developer documentationGoogle AI for Developers · Primary source
  4. Chat AI verified model directoryChat AI · Primary source