Google Introduces Gemini Omni 1.1 Flash for Generative Video

Google has announced the release of Gemini Omni 1.1 Flash, an update designed to provide developers with increased control over generative video projects. The model is now available for production use through Google AI Studio and the Gemini Enterprise Agent Platform.

Key features include the ability to extend video scenes by up to 40 seconds in 10-second increments, with improved visual consistency by referencing up to 10 seconds of prior context. Developers can also specify start and end frames to create transitions and camera movements. For prototyping, the model supports 360p resolution previews, which are reported to be up to 60% faster and less costly than standard 720p generation. Final outputs can be upscaled to 4K resolution. Additionally, the model allows for the use of up to three seconds of video as reference material to maintain character and visual consistency.