Introducing Gemini Omni
Google is introducing Gemini Omni, a natively multimodal model that creates and edits high-quality videos using text, image, audio, and video inputs.Summary
Google has announced Gemini Omni, a new natively multimodal AI model designed to bridge the gap between reasoning and creative production. The model allows users to generate and edit high-quality videos by combining diverse inputs such as text, images, audio, and video. A key feature is the ability to perform complex video editing through natural language, maintaining scene consistency and applying realistic physics. The first release, Gemini Omni Flash, is currently available for Google AI subscribers via the Gemini app, Google Flow, and for users on YouTube Shorts and YouTube Create, with plans to expand access to developers soon. The platform also emphasizes responsible AI, incorporating SynthID watermarking for content transparency.
(Source：Gemini)