That added context is intended to improve continuity across longer sequences, including character appearance, camera motion and the direction of the scene. Developers can use repeated extensions to continue a single narrative or take the same footage in different directions.
The model also adds first-and-last-frame conditioning. Developers can provide the starting and ending frames of a shot, and Omni 1.1 generates the motion connecting them. Google is positioning the feature for controlled camera moves, transitions and loops where the endpoint matters as much as the initial image.
Another addition is a lower-cost 360p draft mode. Google says these previews can generate up to 60% faster than 720p output and cost one-third as much. The option is designed for workflows where developers want to test several variations before committing to a higher-resolution render. Finished videos can then be produced at 1080p or upscaled to 4K.
Omni 1.1 also accepts up to three seconds of reference video as part of a multimodal prompt. Developers can combine those clips with text and image inputs to guide character appearance, movement or other visual details across a generated scene.
Google showed the feature with an example that used separate dance videos as motion references for three animated characters. The resulting output placed the characters together in one continuous scene while preserving the distinct movements from the source clips.
The company is pitching the update primarily at developers building creative applications, editing tools and generative video workflows rather than as a standalone video generator.
Adobe has already integrated Gemini Omni Flash into Firefly, while Figma Weave and GMI Cloud are also using the model in production. “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,” Figma Weave Creative Director Itay Schiff said. “With extensions, richer reference material, and 4K resolution, Gemini Omni Flash takes teams beyond generating videos to truly directing them.”
GMI Cloud said the model’s accuracy has been particularly important for customers creating educational and explanatory content. “At GMI Cloud, we give creators centralized access to the world’s most capable models,” Louisa Guo, the company’s vice president of marketing, said. “What stands out about Gemini Omni Flash is its accuracy: the details hold up under scrutiny.”
Runway is also making the model available within its existing creation workflow. “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,” Runway Chief Creative Officer Jamie Umpherson said. “It's another way for our users to move quickly between ideas.”
Google is also extending access beyond developers. Omni 1.1 is available globally in Google Flow for AI Plus, Pro and Ultra subscribers starting today. Scene extension is also available to those subscribers in the Gemini app.
The update gives developers more control over how generated footage starts, continues and ends, while adding a cheaper preview workflow for iteration before producing higher-resolution output.
This analysis is based on reporting from Google.
Image courtesy of Google.
This article was generated with AI assistance and reviewed for accuracy and quality.
