Gemini Omni Is Here! Google’s Edge Is Still in Multimodal Models, Right?!
meng shao(@shao__meng)713 字 (约 3 分钟)
78
Google's Gemini Omni is the first natively multimodal model for video understanding and generation, enabling arbitrary combinations of image, text, video, and audio inputs with conversational editing and physics-aware reasoning, significantly outperforming prior models like Veo.
入选理由：Gemini Omni 支持图、文、视频、音频任意组合输入，实现多轮对话式视频编辑，无需重述完整提示词。
FeaturedTweet#Gemini Omni#Multimodal Model#Video Generation#Google DeepMind#AI Editing中文