Google launches Gemini Omni 1.1 Flash video model
The model is available through the Gemini API in Google AI Studio, Gemini Enterprise Agent Platform, and Google Flow.
- Scene extension analyzes up to 10 seconds of prior context to extend clips in 10-second increments up to 40 cumulative seconds.
- Developers can specify explicit starting and ending keyframes to interpolate continuous transitions, pans, and zooms.
- Drafting at 360p resolution generates output up to 60% faster at one-third the cost of 720p, with upscaling up to 4K.
- Multimodal input accepts up to three seconds of reference video for character and style consistency.
Developers can now build generative video workflows with keyframe constraints, lower-cost draft rendering, and longer visual continuity.
