Gemini Omni Flash 1.1 lands on fal
By Steven Van ·
The model processes text, image and video together and can hold a character or scene consistent across editing turns.
Google's Gemini Omni Flash 1.1 is now available on fal, processing text, image and video together rather than in separate passes. The model carries over Gemini's real-world and physics knowledge into generation, and supports conversational editing that holds a character or scene consistent across multiple turns.
fal
A generative media platform and inference API for running fast image, video, and audio AI models at scale.
View fal →