@GoogleDeepMind: We’re dropping Gemini Omni: our first step towards a model that can create anything from anything - starting with video. It combines Gemini...

@GoogleDeepMind 3 信息等级 3 发布：2026-05-19T17:17 抓取：2026-05-19 23:19

🔗 原文链接

AI 行业动态

摘要

Google DeepMind 发布 Gemini Omni 模型，这是首个能从任何输入生成任何输出的模型，首先从视频开始。该模型结合了 Gemini 的智能与生成媒体系统，代表了世界理解、多模态和编辑能力的飞跃。

客观事实

Google DeepMind 发布 Gemini Omni 模型。
该模型可从任何输入生成任何输出，首先支持视频。
Gemini Omni 结合了 Gemini 智能与生成媒体系统。

Google DeepMind Gemini Omni

原文

We’re dropping Gemini Omni: our first step towards a model that can create anything from anything - starting with video.

It combines Gemini’s intelligence with our generative media systems - representing a leap forward in world understanding, multimodality, and editing 🧵

likes: 6053 | retweets: 851 | replies: 197 | views: 536535