Capcom Enlists AI for Immersive In-Game Content Generation

Capcom is exploring generative AI to streamline the creation of the vast number of design concepts required for its game environments. With escalating video game development costs, publishers are increasingly turning to AI, despite controversy. Activision, for example, reportedly utilized AI for a Call of Duty cosmetic and a loading screen, sparking criticism from fans. EA has even declared 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 Monster Hunter: World and Exoprimal), detailed the company's AI experimentation. Abe highlighted the significant time and effort invested in generating the "hundreds of thousands" of unique ideas needed for game assets. Even seemingly simple objects like televisions require individual designs, logos, and shapes, leading to a massive volume of concept proposals. Each proposal, Abe explained, necessitates illustrations and textual descriptions for communication with art directors and artists.

To improve efficiency, Abe developed a system leveraging generative AI. This system processes game design documents and generates design concepts, accelerating the development process. The AI iteratively refines its output based on self-generated feedback. This prototype, utilizing models like Google Gemini Pro, Gemini Flash, and Imagen, has reportedly received positive internal reviews. The anticipated outcome is a substantial cost reduction and potential quality enhancement compared to manual creation.

Currently, Capcom's AI implementation is confined to this specific system. Other crucial aspects of game development, such as core gameplay mechanics, programming, character design, and overarching narrative ideation, remain firmly under human control.