Google ships Gemini Omni 1.1 Flash with production-grade video controls

Google has released Gemini Omni 1.1 Flash, an update to its generative-video model aimed at developers building creative and media-editing tools, now available through the Gemini API in Google AI Studio. The headline changes are about control and iteration speed rather than raw generation. Scene extension now conditions on up to 10 seconds of preceding footage instead of just the final frame, improving continuity when stitching clips, and lets creators extend videos in 10-second steps to a 40-second ceiling. New keyframe controls let developers pin the first and last frames of a shot so the model fills in continuous motion between them, and a video-reference feature accepts up to three seconds of source clip to hold character and visual consistency.

The release also leans on a cost-and-speed tier. A lightweight 360p draft mode renders previews up to 60% faster and at roughly a third of the cost of the standard 720p output, targeting rapid storyboarding and prototyping, while finished work can be upscaled to 1080p or 4K for production delivery. Together these features position Omni 1.1 as a workflow tool rather than a one-shot generator.

Distribution is broad: the model is rolling out across Google AI Studio, the Gemini Enterprise Agent Platform API, and Google Flow for AI Plus, Pro, and Ultra subscribers, with scene extension additionally surfacing in the Gemini app. The framing throughout is enterprise readiness — controllable, cheaper to iterate on, and pitched squarely at competing generative-video pipelines from rivals like OpenAI’s Sora and Runway.