Google's Gemini Omni 1.1 Flash makes AI video generation cheaper and more flexible
decoder ·
Google has updated its Gemini Omni Flash video model to version 1.1, introducing improvements to scene extension. The new version analyzes up to ten seconds of existing video instead of just the last second, enabling more visually consistent results, and allows scenes to be extended in 10-second increments up to 40 seconds total. Developers can upload up to three seconds of external footage as a style reference to carry over characters or motion patterns, and can set start and end frames to create camera movements between keyframes. A new 360p draft mode runs up to 60 percent faster at one-third the cost of 720p, with videos capable of being upscaled to 1080p or 4K. Per-second pricing is set at $0.03 for 360p, $0.10 for 720p, $0.15 for 1080p, and $0.30 for 4K. The model is available through Google AI Studio and the developer documentation.
decoder