Microsoft’s Latest Muse Ai Model Can Generate Game Environments

Microsoft Researchers introduced a new artificial intelligence (ai) model on wedding that can generate 3D gameplay environments. Dubbed the World and Human Action Model (Wham) or Muse, The New AI MODEL was developed by the tech Giant’s research game intelligence and teacher Studios’ Ninja Theory. The company said that Large Language Model (LLM) Can Help Game Designers in the ideation process, as well as help generate game visuals and controller action to help creatives in game.

Microsoft Unveils Muse Ai Model

In a blog postThe Redmond-Based Tech Giant Detailed The Muse Ai Model. This is a research product currently, although the company said that it is open-sourcing the weight and sample data of the model for the whole for the whom demonstrator (a concept protypes of a visual infeace to infection With the ai model). Developers can try out the model on azure ai foundry. A paper Detailing the technical aspects of the model is published in the nature journey.

To train a model on such a complex area is a differential proposation. Microsoft Researchers Collected A Large Amount of Human gameplay data from the 2020 game bleeding edge, a game published by ninja theory. The llm was trained on a billion image action pairs, which is equivalent to Seven Years of Human Gameplay. The data is said to be collected ethically and is used only for research purposes.

The researchers said that scaling up the model training was a major challenge. Initially, muse was trained on a cluster of nvidia v100 gpus, but then it was scled to multiple Nvidia H100 Gpus.

Coming to the functionality, the muse ai model accepts text prompts as well as visual inputs. Additional, Once a game environment is generated, it can be further enhanced using controller actions. The AI ​​Responds to the movements made by the user to render new environments aligned with the initial prompt, and consistent with the rest of the gameplay.

Due to being a unique ai model, typical benchmark tests cannot proper evaluate its capabilites. The researchers highlighted that they have internal tested the llm on metrics such as consistency, diversity, and personality. Since it is a research-focused model, the outputs have been limited to just 300x180p resolution.