Gemini Omni 1.1 Flash

Gemini Omni 1.1 Flash is the generally available release of Gemini Omni Flash, Google's model for fast video generation and editing, announced on August 27, 2026. Gemini Omni takes images, audio, video and text as input and generates video, and Google describes it as combining an intuitive understanding of physics with Gemini's knowledge of history, science and cultural context. Generated clips run 3 to 10 seconds at 24 FPS, in 16:9 or 9:16, and include audio by default, which can be steered in the prompt. The 1.1 update adds more control. Scene extension now reads up to 10 seconds of prior context instead of a single final frame and extends a clip in 10-second steps up to 40 seconds in total. First and last frames can be pinned so the model generates the motion between two keyframes, useful for camera orbits, zoom transitions and seamless loops. Prompts can combine up to six reference images and up to three reference video clips of three seconds each for character and object consistency. Videos can be refined over multiple turns in natural language, with the model changing what is asked while preserving the rest of the scene. It fits storyboard iteration, short-form social and ad video, and production workflows that need controllable, consistent shots.