Google has introduced Gemini Omni 1.1 Flash, a new suite of creative controls and generative video capabilities designed to make the model production-ready for professional use via the Gemini API in Google AI Studio.
- Scene extension allows the model to analyze up to 10 seconds of prior context to continue generating footage in 10-second increments up to a total length of 40 seconds.
- Developers can specify first and last frames to generate continuous video between keyframes for smooth transitions and camera movements.
- Drafting videos in 360p resolution is up to 60% faster and costs a third compared to the standard 720p resolution.
- The model supports upscaling outputs to 1080p or 4K resolution for polished, high-resolution results.
- Multimodal input now allows referencing up to three seconds of video to maintain visual context and character consistency.
Omni 1.1 is rolling out across the Google developer ecosystem, including Google AI Studio and the Gemini Enterprise Agent Platform, and is available to Google AI Plus, Pro, and Ultra subscribers in Google Flow.