Publication date: 28 August 2026
Google has released Gemini Omni 1.1 Flash as the generally available version of its conversational video generation and editing model. The model adds scene extension, first-and-last-frame interpolation and output controls from 360p through 4K.
The important change is control rather than a new video demo. Creative software teams can now use a stable API model for iterative editing workflows, including longer scene continuation and low-resolution drafts before higher-resolution output.
What can Gemini Omni 1.1 Flash do?
Gemini Omni 1.1 Flash accepts text, images and video as input and produces video. Google lists a 1,048,576-token context window and output clips from three to ten seconds, depending on the task.
The new scene-extension workflow can analyze up to ten seconds of prior video context. Google says users can extend a clip in ten-second increments to a cumulative length of 40 seconds. The model can also interpolate between a specified first and last frame, which gives developers a more direct way to control transitions and camera movement.
- Resolution choices: 360p, 720p, 1080p and 4K.
- 720p is the default output resolution.
- 1080p and 4K outputs use upscaling.
- Video references can provide up to three seconds of visual context.
- The model ID is gemini-omni-1.1-flash.
Gemini Omni 1.1 Flash access and production changes
Google made the model generally available through the Gemini API in Google AI Studio. Enterprise developers can also use it through Gemini Enterprise Agent Platform. The earlier gemini-omni-flash-preview endpoint is scheduled for deprecation on 30 September 2026.
For teams building creative tools, the low-resolution draft mode may be the most practical addition. Google says 360p generation can be up to 60 percent faster and cost one third as much as its standard 720p generation. Those are vendor-reported throughput and cost claims, so production teams should measure them against their own prompts and concurrency.
How does Gemini Omni 1.1 Flash change video workflows?
The release moves Gemini Omni from an experimental creative model toward a production API with explicit editing controls. A small product team building ad-creation, social-video or media-editing software can now test one model for generation, extension and iterative conversational changes instead of stitching together separate tools.
Google does not publish a broad independent quality comparison against competing video models in the release materials. It also does not provide a simple benchmark that tells buyers how reliably character identity or scene geometry survives repeated extensions. Those are likely to matter more than maximum resolution in real production.
What this means
Gemini Omni 1.1 Flash is worth testing for teams that are already building generative video products. The stable API, scene extension and first-and-last-frame control address practical workflow problems rather than adding another isolated generation mode.
Test continuity across several chained extensions, not only the first clip. Measure draft-to-final cost, generation time and the percentage of outputs that survive editing without a full regeneration. Those numbers will show whether Omni 1.1 improves production economics for your specific content pipeline.
For more information, visit the official announcement of Gemini Omni 1.1 Flash on the Google website.
