Google DeepMind is rolling out Gemini Omni 1.1 Flash to make generative video more controllable, faster to iterate on, and more polished for production-grade use. The model is available in Google Flow and related surfaces, with a Google developers blog walkthrough for builders. In the same week's Gemini Drops, the Gemini app added the ability to extend a video from where it left off using Omni 1.1 Flash, so creators can stitch continuous storylines instead of regenerating whole clips. The pitch is control over motion, timing, and visual continuity rather than raw novelty. For coding and product teams, the release matters as part of a broader Gemini 3.x tooling wave: Omni 1.1 Flash for media generation, Gemini 3.7 Flash for multi-step tool use, and Gemini 3.5 Transcribe for speech. Controllable video becomes another actuator an agent can call, not a separate consumer toy.
Key Takeaways
- βOmni 1.1 Flash targets controllable, faster, production-grade video and is live in Flow.
- βThe Gemini app can extend videos from the last frame to build continuous storylines.
- βThe model lands with Gemini 3.7 Flash and 3.5 Transcribe as another agent-callable media actuator.