Announced August 27, 2026, the update to Google's Omni Flash video model extends a scene to 40 seconds, adds first/last-frame control, and lets developers draft cheaply in 360p before upscaling.
2026-08-27 · by Moe Ameen
Google announced Gemini Omni 1.1 Flash on August 27, 2026, an update to Gemini Omni Flash — the fast, cost-efficient tier of the Gemini Omni video family. The original release, from earlier in the summer, was built around conversational editing but capped clips at 10 seconds. The 1.1 update is pitched at developers who want more control over the finished video: longer scenes, exact keyframes, cheaper drafts, and higher-resolution output.
The centerpiece is scene extension. You can now stretch a clip in 10-second increments up to a cumulative 40 seconds, and the model analyzes up to ten seconds of the existing footage — rather than just the last second — so the extension stays visually consistent. Alongside it: first- and last-frame control to steer transitions and camera moves, a new 360p draft mode that renders previews up to 60% faster at about a third of the cost of 720p, and upscaling to 1080p or 4K (both upscaled rather than generated natively, with 720p the default). Generations can take up to three seconds of video as a reference.
Pricing is per second of output and scales with resolution — roughly $0.03 at 360p, $0.10 at 720p, $0.15 at 1080p, and $0.30 at 4K. Like the rest of the Omni family, outputs carry Google's invisible SynthID watermark. The model is available through the Gemini API in Google AI Studio and Google's Gemini Enterprise Agent Platform, with scene extension also surfacing in Google Flow and the Gemini app. Treat specific figures as launch-window details; Google's own materials are the source of truth as they settle.
The most useful thing about this update, for a creator, is that it moves Omni from "shot generator" to "near-complete short generator" — and that makes the finishing line matter more. Draft your scene cheaply at 360p, extend it toward 40 seconds, upscale the keeper to 4K, and then hand only that final to Kompozy. Kompozy does everything the model won't: it burns in branded captions (40 seconds of silent, uncaptioned video dies in-feed), reframes cleanly between vertical and landscape per destination, layers hook text through HyperFrames, and schedules the clip across the eight social platforms plus your blog and email from one queue. You keep Omni's cheap iteration; Kompozy owns the part that actually gets it live.
There is a second play while the launch is searchable. A clean, specific update like this — 40 seconds, 4K, cheaper drafts — is exactly the kind of moment a creator can ride. Feed the facts into Kompozy as a source and it fans one explainer into a package: a blog article that can rank for "Gemini Omni 1.1 Flash," a carousel that walks through what scene extension is, a listicle video of the new specs over a portrait clip, and native text posts sized per platform, all in your voice via your Persona Brief. Omni 1.1 gives you a longer, cheaper shot; Kompozy turns both the clip and the news into a scheduled, on-brand set of posts.
It is an update to Google's Gemini Omni Flash video model, announced on August 27, 2026. It adds 40-second scene extension, first- and last-frame control, a cheap 360p draft mode, and 1080p/4K upscaling — more length and control over the generated clip.
Up to 40 seconds cumulative, extended in 10-second increments. Pricing is per second of output scaled by resolution — roughly $0.03 at 360p, $0.10 at 720p, $0.15 at 1080p, and $0.30 at 4K.
Through the Gemini API in Google AI Studio and Google's Gemini Enterprise Agent Platform, with scene extension also appearing in Google Flow and the Gemini app.
Omni 1.1 generates the clip but does not publish it. Bring the export into Kompozy to add branded captions, reframe it per platform, and schedule and publish it across TikTok, Reels, YouTube Shorts, X, LinkedIn, and more — then fan the same clip into a quote card, text posts, and a thread in your voice.