Gemini Omni 1.1 Flash: scene extension, keyframe control, and 4K output

Google released Gemini Omni 1.1 Flash on August 27, 2026. It is a production-ready update to the Omni generative video model, built for developers who need more control over the output. The original Gemini Omni brought real-world reasoning to generative creation. Version 1.1 adds creative controls that make the model usable in professional video workflows.

The update is available now on vega.chat and through the api.vega.chat API, with no geographical restrictions. Users in Russia get the same access as everyone else, through the same chat interface and the same OpenRouter-compatible API.

Extend scenes up to 40 seconds

Scene extension takes an existing video and continues generating footage from where it stopped.

Omni 1.1 can analyze up to 10 seconds of prior context, up from one second in the previous model. That extra context improves visual consistency and narrative adherence when you build longer stories or branch into new directions. Videos extend in 10-second increments, up to a total cumulative length of 40 seconds.

Specify first and last frames

You can set the starting and ending frames of a shot, and Omni 1.1 generates continuous video between the two keyframes. This works for complex camera orbits, zoom transitions, and seamless looping clips. The full-context reasoning lets you get camera moves that read as real.

Draft videos in 360p

Lightweight previews in 360p resolution render up to 60% faster and cost about a third of the standard 720p output, based on system throughput comparisons. The 360p mode is useful for rapid prototyping, storyboard iteration, and quick rendering when you are still deciding on a direction.

Upscale to 4K

For the final output, Omni 1.1 can produce 1080p or 4K video. You iterate on drafts in 360p, lock in the result, then upscale to the resolution you need for delivery.

Video references in multimodal input

You can attach up to three seconds of video as a reference when crafting a scene. The model uses the reference to maintain visual context and character consistency. The same request can combine video references, image references, and a text prompt.

Try Gemini Omni 1.1 Flash on vega.chat

Gemini Omni 1.1 Flash is available now on vega.chat and through the api.vega.chat API. You can test it in the chat interface, generate and extend video clips, or integrate it into your applications via the OpenRouter-compatible API at api.vega.chat. Access is open to all users, including those in Russia, with no VPN or foreign account required.