Google today introduced Gemini Omni 1.1 Flash, an update to its generative video toolkit that adds creative controls and production-ready features for developers. Gemini Omni previously brought real-world reasoning into generative creation; the Omni 1.1 update is positioned for professional use through the Gemini API in Google AI Studio.
Key features in the update
-
Scene extension for longer storytelling: Scene extension lets developers continue generating footage from an existing video. Omni 1.1 can now analyze up to 10 seconds of prior context, up from earlier models that only referenced the final second. This improves visual consistency and narrative continuity; extensions happen in 10-second increments up to a cumulative 40 seconds.
-
Specify first and last frames for smooth camera moves: Omni 1.1 generates continuous video between two keyframes, making it possible to create complex camera orbits, zoom transitions, and seamless looping clips without jump cuts.
-
Faster, cheaper drafts at 360p: Developers can produce lightweight 360p previews up to 60% faster (based on system throughput comparisons) and at roughly one-third the cost of standard 720p generation. This is intended for rapid prototyping, storyboard iteration, and quick renders.
-
Upscale to 1080p and 4K: The model supports producing polished outputs at 1080p or 4K suitable for professional production.
-
Video references in multimodal input: You can now include up to three seconds of reference video so the model can maintain visual context and character consistency from supplied footage.
How developers can use it
Google outlines practical scenarios where these capabilities can be combined into tools and workflows: apps that accept a first and last frame to automatically generate realistic camera moves using Omni’s full-context reasoning; interfaces that move a camera through rooms without inventing new objects; and a Draft Room workflow in which creators generate several low-cost 360p variations and compare them side by side to find the right direction.
Customer integrations and feedback
Google says customers are already using Gemini Omni Flash in production via the Agent Platform API. The announcement highlights integrations and quotes from partners including Adobe, Figma Weave, GMI Cloud and Runway.
Notable partner quotes (original wording retained):
-
Itay Schiff, Creative Director, Figma Weave: “Gemini Omni Flash is one of the strongest video models available in Figma Weave, where the canvas helps creative teams build on every generation — attaching references, branching different versions, and shaping something unique. With extensions, richer reference material, and 4K resolution, Gemini Omni Flash takes teams beyond generating videos to truly directing them.”
-
Louisa Guo, VP of Marketing, GMI Cloud: “At GMI Cloud, we give creators centralized access to the world’s most capable models. What stands out about Gemini Omni Flash is its accuracy: the details hold up under scrutiny. For customers creating educational and explanatory content, where getting things right is essential, that reliability matters more than any single feature. Omni has made AI video viable for a segment that previously couldn’t rely on it.”
-
Jamie Umpherson, Chief Creative Officer, Runway: “Omni Flash fits naturally into how people already use Runway: start with a prompt, an image or a video, then generate or edit from there. It's another way for our users to move quickly between ideas.”
Availability and rollout
Gemini Omni 1.1 Flash is rolling out across Google’s developer ecosystem: it can be tried directly in Google AI Studio via the Gemini API, and enterprises can build with Omni 1.1 through the Agent Platform API. The update is also available to Google AI Plus, Pro and Ultra subscribers globally in Google Flow, and scene extension is available to those subscribers in the Gemini app.
The announcement references a pricing table for Gemini Omni 1.1 Flash but does not include specific prices in the release.
Why it matters
By extending contextual memory to 10 seconds, enabling keyframe-based transitions, speeding up low-resolution drafts and supporting 4K output, Omni 1.1 aims to make generative video more controllable and reliable for professional workflows. Google’s partner feedback emphasizes accuracy and integration into existing creative pipelines as reasons the update could broaden the practical use cases for AI-generated video.
Resources
Google points developers to the official documentation, the cookbook, and prompting guides to learn how to integrate scene extension, video references, and upscaling into their applications.
(Note: the announcement was published "today"; for exact publication date and detailed pricing, consult Google’s documentation.)
