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 faces the challenge of generating "hundreds of thousands" of unique ideas for in-game assets, a process traditionally very time-consuming and resource-intensive.
As game development costs escalate, the industry is increasingly turning to AI tools, despite ongoing controversies. Recent examples include reports of AI-generated content in Call of Duty and EA's declaration of AI as central to its operations.
In a recent interview with Google Cloud Japan, Capcom's technical director Kazuki Abe (known for his work on titles like Monster Hunter: World and Exoprimal) detailed the company's AI experimentation. Abe highlighted the significant workload involved in generating diverse designs, even for seemingly simple objects like televisions, each requiring unique logos and shapes. He explained that numerous design proposals, complete with illustrations and textual descriptions, are necessary for the thousands or tens of thousands of such assets in a single game.
To address this bottleneck, Abe developed a system leveraging generative AI. This system processes game design documents and outputs design concepts, accelerating the development process and refining its output through iterative feedback. The prototype utilizes multiple AI models, including Google Gemini Pro, Gemini Flash, and Imagen, and has reportedly received positive internal reviews. The projected outcome is a substantial cost reduction and a potential improvement in design quality compared to manual creation.
Currently, Capcom's AI implementation is focused solely on this concept generation system. Other critical aspects of game development, such as gameplay mechanics, programming, character design, and overall game ideation, remain firmly under the control of human developers.
