Google releases Gemini Omni 1.1 Flash, 40-sec video with 4K output
Google released Gemini Omni 1.1 Flash in August: 10-sec extension per generation, cumulative length up to 40 sec, first/last frame control, and 4K output.
On August 28, Google DeepMind released the Gemini Omni 1.1 Flash video generation model. The model can read up to 10 seconds of preceding video for extension, with each generation adding 10 seconds and cumulative length up to 40 seconds, supporting first/last frame control for transition shots.
Gemini Omni 1.1 Flash adds a 360p draft mode that delivers approximately 60% higher throughput than 720p at about one-third the cost, with final output supporting 4K resolution. The model is available to developers via the Gemini API and Google AI Studio, with consumer access across AI Plus, Pro, and Ultra tiers.
In concurrent developer testing, Omni 1.1 Flash reduced token consumption by approximately 30% versus Sora 2 on a 4-second video generation task while maintaining nearly 1.5x speed advantage on 8-second video, seen as Google's key update to put competitive pressure on Sora and Seedance in the video generation space.