Gemini Omni 1.1 Flash: Production-Ready with Scene Extensions, 4K Output, and Developer APIs

From preview to production

Google released Gemini Omni 1.1 Flash on August 27, 2026, marking the model’s transition from developer preview to production-ready status. The model ID changes from gemini-omni-flash-preview to gemini-omni-1.1-flash, and it arrives with capabilities that make generative video substantially more controllable for both developers and creators.

The update is available through Google AI Studio and the Gemini Enterprise Agent Platform, and rolls out to all Google AI Plus, Pro and Ultra subscribers in Google Flow and the Gemini app.

Scene extensions: up to 40 seconds of continuous video

The headline feature is scene extension — take an existing video and continue generating footage seamlessly from where it left off.

Omni 1.1 analyzes up to 10 seconds of prior context, a significant improvement from previous models that only referenced the final second. The result is better visual consistency and narrative adherence, letting you build longer stories or branch into new creative directions. Videos can be extended in 10-second increments up to a total cumulative length of 40 seconds.

Here’s the API pattern for scene extension:

from google import genai

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-omni-1.1-flash",
    previous_interaction_id=previous_video_interaction.id,
    input=[
        {"type": "text", "text": "Continue the scene."}
    ],
    response_format={
        "resolution": "360p",
    },
)

First and last frame specification

Achieve smooth transitions and camera movements by specifying the starting and ending frames of a shot. Omni 1.1 generates continuous video between two keyframes, making it ideal for complex camera orbits, zoom transitions, or seamless looping clips.

This unlocks professional-grade camera control — whip pans, dolly zooms, orbital shots — all generated from just two reference frames and a text prompt.

360p draft mode: iterate faster, spend less

Generate lightweight previews in 360p resolution up to 60% faster and at a third of the cost compared to the standard 720p output. This is built for rapid prototyping, storyboard iteration, and quick rendering in developer platforms.

For production workflows, this means testing ideas at low cost before committing to full-resolution renders.

4K upscaling for production-ready output

When you’re ready for the final cut, Omni 1.1 generates polished 1080p or 4K outputs ready for professional production. Combined with the 360p draft mode, this creates an efficient draft-to-final pipeline: prototype cheaply, then upscale the winning take.

Video references in multimodal input

Reference up to three seconds of video when crafting your scene, allowing you to maintain visual context and character consistency based on video references. Combined with Omni’s existing text and image reference support, this rounds out the multimodal input surface.

Who’s building with Omni 1.1 Flash

The production launch comes with a roster of major integrations:

• Adobe integrated Omni Flash into Adobe Firefly for video editing capabilities.
• Figma Weave uses Omni Flash for multi-version creative workflows — “beyond generating videos to truly directing them,” according to Creative Director Itay Schiff.
• Runway offers Omni Flash as another generation option for users to move quickly between ideas.
• GMI Cloud highlights Omni Flash’s accuracy for educational and explanatory content where reliability matters more than any single feature.

These join existing partners including Picsart, Cartwheel, Astrocade, HubX, Stan, Artlist, Lovart, and Agent Opus.

Updated availability

Omni 1.1 Flash is available across:

Surface	Access
Google AI Studio	Direct API access for developers
Gemini Enterprise Agent Platform	Enterprise-grade API
Google Flow	All AI Plus, Pro and Ultra subscribers
Gemini app	All AI Plus, Pro and Ultra subscribers (scene extension included)
YouTube Shorts / Create	Free for users 18+
Google Vids	AI-powered video creation for work

What this means for the Omni roadmap

The 1.1 Flash release moves Omni from “promising preview” to “production platform.” Developers now have a stable model ID, deterministic scene extension APIs, resolution flexibility from 360p to 4K, and frame-level control — the building blocks for real video production pipelines.

The pieces announced earlier in August remain on track: Omni Pro wider rollout, image and audio output modalities, and Workspace integration are all expected before the end of 2026.

For the full launch history, see our May 2026 release notes and June update. For the August status check including Pro preview details, see our August 2026 update.