
- 谁
- Google DeepMind
- 引文
So today, we are rolling out a new Project Genie experience to eligible Google AI Ultra subscribers, making these worlds far more responsive, creative, and social.
发生了什么
Google DeepMind 正在向符合条件的 Google AI Ultra 订阅者推出全新的 Project Genie 体验,其中包括首次开放 Genie 4 使用权限、升级 Genie 3、提供创作代理以及社区画廊。Genie 4 支持根据提示词和原生音频进行实时世界变更;Genie 3 的单次生成会话时长可达 3 分钟,相较之前的 60 秒有所提升。Google AI Pro 会员可以加入候补名单。
推荐理由
符合条件的 Google AI Ultra 订阅者现在可以在会话期间重塑生成的世界,而 Genie 3 支持单次生成长达三分钟的探索。该体验还允许用户在社区画廊中发布和重混世界。
3 家信源报道
这件事到目前为止
Google DeepMind has made its Genie 4 world model available to eligible Google AI Ultra subscribers within the Project Genie platform. The model, which initially launched as a research preview in October 2026, enables real-time generation of interactive environments that support native audio, interactive dialogue, and environment steering via natural language prompts. Powered by Gemini 3.8 Flash, Genie 4 allows users to alter scenes dynamically—such as adding characters or changing the weather—during active simulation. The broader Project Genie update also introduced a community gallery for sharing creations and extended session durations for the Genie 3 model to three minutes. While Google DeepMind states that Genie 4 improves upon its predecessors in physics and realism, the company notes that maintaining object permanence and physical consistency during extended simulations remains an ongoing research challenge.
这件事的进展 · 2
查看完整事件- 11月19日 02:53
Google DeepMind 推出全新 Project Genie 体验 本条
- 10月28日 00:56Google DeepMind 发布 Genie 4:支持原生音频的实时世界模拟Google DeepMind
