Google has launched Gemini Omni 1.1 Flash, a major update to its AI video generation and editing model with longer scene extensions, more precise camera controls, and output resolutions of up to 4K.
The model is now generally available to developers through the Gemini API in Google AI Studio, moving beyond its previous preview stage.
Longer Videos and More Creative Control
One of the biggest upgrades is Scene Extension, which allows creators to continue an existing video while maintaining its characters, environment, and story.
Omni 1.1 can analyze up to 10 seconds of previous video context, compared with only the final second in earlier versions.
Videos can then be extended in 10-second increments for a total cumulative length of up to 40 seconds. Creators can also provide new prompts during each extension to change dialogue, camera movement, or where the story goes next.
Google has also introduced first and last frame controls. Users can provide two keyframes and ask Gemini Omni to generate a continuous video connecting them.
This can be used for complex camera movements, transitions, zooms, and looping videos without manually creating the frames in between.
The model can also use up to three seconds of reference video as multimodal input. This allows creators to transfer movement or other visual information from an existing clip while maintaining characters and environments from other supplied assets.
Faster Drafts and 4K Output
Google is introducing a 360p draft mode aimed at creators who generate several versions before selecting the final result.
The company says 360p generations can be up to 60% faster than standard 720p generations and cost around one-third as much, making them more practical for storyboards and rapid experimentation.
Once creators settle on a result, Gemini Omni 1.1 Flash can produce or upscale the final video to 1080p or 4K.
The API supports 360p, 720p, 1080p, and 4K output, with 720p remaining the default resolution.
Google is charging developers approximately $0.10 per second for standard 720p video output through the paid Gemini API.
Available in Gemini, Flow and AI Studio
Gemini Omni 1.1 Flash is available to developers through Google AI Studio and the Gemini API. Enterprise customers can also access it through the Gemini Enterprise Agent Platform.
Google has already integrated Gemini Omni Flash into products and creative platforms from companies including Adobe, Figma, GMI Cloud, and Runway.
The new Omni 1.1 capabilities are also rolling out globally in Google Flow for Google AI Plus, Pro and Ultra subscribers.
Additionally, Scene Extension is becoming available to Google AI Plus, Pro, and Ultra subscribers worldwide directly through the Gemini app.
Google’s previous gemini-omni-flash-preview API endpoint will be retired on September 30 as the production-ready Gemini Omni 1.1 Flash takes its place.
The post Google Upgrades Gemini Omni With 4K Video and Longer Scenes appeared first on ProPakistani.