Capcom Unveils Innovative Use of AI for Game Development

Capcom is exploring generative AI to streamline the creation of the vast number of design concepts required for its game environments – a process currently demanding "hundreds of thousands" of unique ideas.

The rising costs of video game development are pushing publishers towards AI tools, despite ongoing controversies. Activision, for example, faced criticism for reportedly using AI to generate cosmetic items for Call of Duty: Modern Warfare 3 and a loading screen in a previous iteration. EA, meanwhile, declared AI as "the very core" of its operations.

In a recent interview with Google Cloud Japan, Capcom's technical director, Kazuki Abe (known for his work on Monster Hunter: World and Exoprimal), detailed the company's AI experimentation. Abe highlighted the significant time and resources dedicated to generating countless unique design concepts, citing even seemingly simple objects like televisions as requiring individual designs, logos, and shapes. He emphasized the sheer volume of proposals – thousands to tens of thousands per game – each needing accompanying illustrations and textual descriptions for communication with art directors and artists.

To address this efficiency bottleneck, Abe developed a generative AI system. This system processes various game design documents, generating design concepts and providing self-iterative feedback for refinement. Leveraging AI models such as Google Gemini Pro, Gemini Flash, and Imagen, the prototype has reportedly received positive internal feedback. The anticipated outcome is a substantial cost reduction and a potential quality improvement compared to manual creation.

Currently, Capcom's AI implementation appears confined to this specific system. Other crucial aspects of game development, including core gameplay mechanics, programming, character design, and overarching creative direction, remain firmly under human control.