新闻

Gemini Omni 1.2 Flash: Fast and cost-effective with longer clips

Google AI · {"$":{"xmlns:author":"http://www.w3.org/2005/Atom"},"name":["Anish Nangia"],"title":["Product Manager, Google DeepMind"],"department":[""],"company":[""]} · 发布于 2026年11月5日 · 阅读约3分钟

30秒读懂

发生了什么: Google released Gemini Omni 1.2 Flash, supporting native 15-second video generation with 30% lower costs and improved consistency.
为何重要: Developers and businesses building video content at scale should evaluate this for production workflows across Gemini API and Google Cloud.
注意: Model still has known limitations with fast sports action, rapid script changes, and complex physics simulations that users should test.

阅读完整文章

gemini

还有谁报道了

Gemini Omni 1.2 Flash: Fast and cost-effective with longer clipsGoogle DeepMind

同一件事，来自我们关注的其他媒体。

这条新闻背后的模式

每个模式都讲清楚技术如何运作、何时值得投入，以及在哪里会失效。

The Agent Architect

每周一个模式、一个权衡、一个生产事故案例。为构建智能体系统的人准备的每周简报。

每周一封邮件,一键退订。您的地址仅用于发送简报。