Capcom is exploring the use of generative AI to streamline the creation of the vast number of design concepts required for its game environments. The company acknowledges the significant time and resources dedicated to generating "hundreds of thousands" of unique ideas for in-game assets.
With escalating video game development costs, the industry is increasingly turning to AI tools, a move met with both excitement and controversy. Recent examples include reports of AI-generated cosmetics in Call of Duty: Modern Warfare 3 and allegations of AI use in loading screens. EA has even declared AI as "the very core" of its operations.
In a recent interview with Google Cloud Japan, Capcom's Technical Director Kazuki Abe, a veteran of major titles like Monster Hunter: World and Exoprimal, detailed the company's AI experimentation. Abe highlighted the immense effort involved in generating unique designs, citing even seemingly simple objects like televisions requiring individual designs, logos, and shapes. He emphasized the need for multiple design proposals for tens of thousands of such assets per game, each requiring illustrations and textual descriptions.
To address this efficiency bottleneck, Abe developed a system utilizing generative AI. This system processes game design documents and generates design concepts, significantly accelerating the development process. The AI iteratively refines its output based on its own feedback mechanisms.
Abe's prototype, leveraging AI models like Google Gemini Pro, Gemini Flash, and Imagen, has reportedly received positive internal reviews. The anticipated outcome is a substantial cost reduction and a potential improvement in overall design quality.
Currently, Capcom's AI implementation is focused solely on this concept generation system. Other crucial aspects of game development, including gameplay mechanics, programming, character design, and overall creative direction, remain firmly under the control of human developers.