Google has introduced Gemini Omni 1.1 Flash, an update to its generative video model aimed at giving developers and creative teams more control over how clips are made, extended and refined. The company is adding scene continuation, keyframe-based video generation, low-cost draft rendering, video references and output options up to 4K.
The update addresses a common limitation of AI video: maintaining a coherent look and action beyond a short clip. Gemini Omni 1.1 Flash can now use up to 10 seconds of earlier footage when extending a scene. Google says earlier versions considered only the final second. Users can add 10-second continuations until a video reaches a cumulative length of 40 seconds.
That feature could help teams build longer sequences from an initial clip or test several narrative directions without starting again. A prompt can instruct the model to continue the scene, alter camera movement or add dialogue. However, generated results will still require review, particularly when a project depends on accurate visual details, continuity or spoken content.
More control over camera movement and references
Google is also introducing a first-and-last-frame workflow. Users provide the opening and closing images of a shot, then ask the model to create the movement between them. The company positions this as a way to make transitions, camera pushes, zooms, orbits and looping sequences feel more continuous.
Another addition allows up to three seconds of video reference material in a multimodal prompt. The reference can provide visual context for a new scene, including the appearance of characters or the pattern of a movement. This may be useful for editors and creative-tool makers that need generated footage to align with existing visual material.
For faster experimentation, Gemini Omni 1.1 Flash offers 360p drafts. Google says this mode can generate video up to 60% faster than the model’s standard 720p option and costs one-third as much. The company frames the setting as a tool for storyboards, rapid iterations and comparing several creative variations before rendering a final version.
Finished outputs can be generated or upscaled at 1080p and 4K. According to Matthias Bastian’s report for The Decoder, Google lists per-second pricing of $0.03 for 360p, $0.10 for 720p, $0.15 for 1080p and $0.30 for 4K. Those rates make resolution choices significant for projects that require many variations or longer sequences.
Google is making Omni 1.1 Flash available through the Gemini API in Google AI Studio and through its Enterprise Agent Platform API. The company also says the model is available in Google Flow for Google AI Plus, Pro and Ultra subscribers, while scene extension is rolling out in the Gemini app for those subscriber tiers.
Google cites Adobe Firefly, Figma Weave, GMI Cloud and Runway among companies using Gemini Omni Flash in their products or workflows.
Sources
- Gemini Omni 1.1 Flash lets you build with more control – Google
- Google launches Gemini Omni 1.1 Flash, which it says delivers studio-quality video production, including the ability to extend a scene, 4K upscaling, and more – Google DeepMind
- Google’s Gemini Omni 1.1 Flash makes AI video generation cheaper and more flexible – The Decoder
Stay up to date
AI for content creation: the latest tools, tips and trends. Every two weeks in your inbox:
