Google DeepMind launches Gemini Omni 1.1 Flash
Google DeepMind releases Gemini Omni 1.1 Flash, a production-ready update for developers offering improved control over generative video.
The update
Google DeepMind has released Gemini Omni 1.1 Flash, a production-ready update for developers focused on improved control over generative video. The update introduces a suite of creative controls, including the ability to extend scenes, specify start and end frames for smooth transitions, and generate high-resolution 4K output. Developers can now access the model through Google AI Studio or the Gemini Enterprise Agent Platform.
Why it matters
This release addresses a key friction point in AI video generation: the lack of professional-grade control. By allowing users to define precise camera movements and upscale footage to 4K, the tool aims to move generative video from a novelty to a practical production asset. The inclusion of low-resolution previews (360p) offers a cost-effective way to iterate on ideas during the creative process.
What to watch
Developers will likely integrate these controls into existing video pipelines. The broader impact on the generative video market will depend on the accessibility of the API and the quality of the output compared to competing tools.
Sources
- Google DeepMind Blog — Core release details, feature list, and access points.
- Google Blog — Confirmation of release details and developer access information.