Google DeepMind 发布它最新的世界模型"Genie 4"在星期二的研究预览中。 最新的模型生成了相片现实和互动性最强的世界至今，允许用户键入中模拟来改变场景。 该模型还生成了与模拟世界相匹配的实时音频，包括音乐，环境噪声，以及交互式对话。
Genie 4的发布是在AI视频启动后Runway 发布的第二个世界模式GWM Worlds 2的几个月后而来，这个可玩模式对用户输入有动态反应并包括音频生成。 同时，世界示范产业也开始得到巩固。 Fei-Fei Li的世界实验室是AMD的收购，Amazon正在谈判购买Decart,Rivian只是收购的第三维度将模拟能力带入内部进行自驾测试。
Genie 4是Google最新一步
Google 发布的前身Genie 3作为一年多前的研究预览。 Genie 4除了更具有相片现实性和以音频为特色外，还允许自由形式编辑，比如实时地改变天气或相机角度或者添加新的人或物体。 它可以维持一出一致的场景长达两分钟，将前作的极限翻一番，并提供更好的物理和更像人类的人物。
Gemini,Google的AI模型，也与Genie 4更紧密地融合了起来，担任导演负责计划步骤和检查帧，而Genie则创造视觉。 在与Gemini机器人相关的研究实验中，Gemini 4 Argon模型将任务分解为Genie 4实时所模拟的步骤。 实验显示是一种在真实世界发生之前在模拟中测试机器人情景的可能方法。
“我们将来会越来越多地看到这些混合世界模型，将Gemini的写作代码和文本组合在一起
与其他世界模式一样，投放的商业使用案例包括游戏、互动学习和机器人。 互动学习的一个推测性实例是进入一幅历史场景的画作，并与画作的主题谈论所描绘的事件。
但是，“受信任的试验者”——首先获得Google先进产品的人——指出了一种可能的新用途：原型电影。
“在创造空间保持流动状态变得非常有用的领域，实时问题变得最有价值。” “例如，在思想阶段，在故事板刻阶段——无论何时，你都需要迅速的思考。”
Google还提供Veo，其AI视频生成模型从文本，图像，或视频提示中，用内置同步音频制作高清晰度剪辑——这个工具在电影制作人中越来越受欢迎。
Rivas还补充说，用户最终可以依靠Gemini Omni(一种能够从图像，音频，和文本中生成视频的多式大型语言模型)将这些原型转化为创意资产。 虽然这些能力，他称，仍然是一条出路。
整个简报期间，里瓦斯强调，对于Genie 4来说，现在还很早，目前还不清楚什么是端到端的产品经验。 团队也承认Genie 4仍有空白：细节和物体可以漂移时间越长的模拟运行
Genie 4现在作为值得信任的测试者的研究预览提供。 未来几周，该模型将推出至Genie项目中的Google AI Ultra用户，Google的AI工具从文本或图像提示中生成互动世界，以及Gemini API和Google AI Studio的早期访问伙伴。
本文由 AI宝库自动抓取并翻译，版权归原作者所有；如需查看原文请点下方链接。
Google DeepMind released its newest world model, Genie 4, in research preview on Tuesday. The latest model generates the most photorealistic and interactive worlds yet, allowing users to type prompts mid-simulation to change the scene. The model also generates real-time audio that matches the simulated world, including music, ambient noises, and interactive dialogue.
The release of Genie 4 comes a couple of months after AI video startup Runway released its second world model, GWM Worlds 2, a playable model that responds dynamically to user inputs and includes audio generation. At the same time, the world model industry is beginning to consolidate. Fei-Fei Li’s World Labs is being acquired by AMD, Amazon is in talks to buy Decart, and Rivian just acquired Third Dimension to bring simulation capabilities in-house for self-driving testing.
Genie 4 is Google’s latest move to stay ahead in the crowded field.
Google released its predecessor, Genie 3, as a research preview a little over a year ago. Aside from being far more photorealistic and featuring audio, Genie 4 allows for freeform edits, like changing the weather or camera angle in real time or adding new people or objects. It can maintain a consistent scene for up to two minutes, double its predecessor’s limit, and offers better physics and more human-like characters.
Gemini, Google’s AI model, is also more closely integrated with Genie 4, acting as the director that plans steps and checks frames while Genie creates the visuals. In a research experiment tied to Gemini Robotics, a Gemini 4 Argon model broke down tasks into steps that Genie 4 simulated in real time. The experiment shows a possible way to test robot scenarios in simulation before they happen in the real world.
“What we’ll increasingly see in the future are these hybrid world models, where you have a combination of Gemini writing code and text, and Genie ingesting that in real time and simulating reality at different levels of abstraction,” Tejas Kulkarni, research director at Google, said during a briefing.
As with other world models, the pitched commercial use cases include gaming, interactive learning, and robotics. One speculative example of interactive learning would be entering a painting of a historical scene and chatting to the painting’s subjects about the event portrayed.
But “trusted testers” — the people who get first access to Google cutting-edge products — are pointing to a possible new use: prototyping films.
“The real time aspect becomes most valuable in the areas where keeping a state of flow in the creativity space becomes incredibly useful,” Diego Rivas, a Google DeepMind engineer, said during a press briefing. “For example, in the ideation phase, in the storyboarding phase — anytime you’re kind of in need of rapid ideation.”
Google also offers Veo, its AI video generation model that makes high-definition clips with built-in synchronized audio from text, image, or video prompts — a tool that has been growing in popularity among filmmakers.
Rivas added that users could, eventually, rely on Gemini Omni, a multimodal large language model that can generate video from images, audio, and text, to turn those prototypes into creative assets. Though those capabilities, he says, are still a ways off.
Throughout the briefing, Rivas stressed that it’s still early days for Genie 4, and that it’s not yet clear what the end-to-end product experience will be. The team also acknowledged that Genie 4 still has gaps: details and objects can drift the longer a simulation runs, and they still haven’t quite figured out how to ensure the audio will be accurate and any in-world text will be legible.
Genie 4 is available now as a research preview for trusted testers. In the coming weeks, the model will roll out to Google AI Ultra subscribers in Project Genie, Google’s AI tool for generating interactive worlds from text or image prompts, and early access partners of the Gemini API and Google AI Studio.
Auto-fetched and translated by AI Gem Box. All rights belong to the original author.