Gemini Omni 1.1 Adds 4K AI Video Control
Google has launched Gemini Omni 1.1 with stronger AI video controls and 4K output. The update gives creators more control over generated scenes.
The model can now continue footage by analyzing up to 10 seconds of previous video. Previously, it could only use the final second for scene continuation.
More Control Over AI Video
Users can extend scenes in 10-second sections. They can stack these extensions until reaching a total limit of 40 seconds. The model also supports first and last frames as references. Therefore, creators can generate motion between two selected images.
This feature can help create camera movements, loops, and smooth transitions. Video references within prompts can also run for up to three seconds.
Google has also improved rendering speeds and costs. Draft videos can render at 360p, which Google says works up to 60% faster. The lower-resolution option also costs about one-third of standard 720p rendering. Creators can then produce final videos at 1080p or 4K.
Wider Availability
Several creative platforms already use Omni Flash in production. These include Adobe Firefly, Figma Weave, Runway, and GMI Cloud.
Google also uses Omni technology inside Google Photos. The tool can help improve videos that suffer from poor lighting. Gemini Omni 1.1 is now available through Flow for Google AI Plus, Pro, and Ultra subscribers. Scene extension is also coming to the Gemini app.
Overall, the update makes AI video generation more controllable. It combines faster drafts, flexible references, longer scenes, and high-resolution final output. These improvements could make AI video tools more useful for creators. They also bring generated video closer to traditional editing workflows.
