Capcom is leveraging 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.
As game development costs escalate, the industry is increasingly exploring AI tools to enhance efficiency and reduce expenses. Recent examples include reports of AI-generated content in Call of Duty and EA's declaration of AI as central to its operations.
In an 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. He highlighted the substantial effort involved in designing even seemingly simple objects, such as televisions, each requiring unique designs, logos, and shapes. This necessitates numerous design proposals, complete with illustrations and textual descriptions, for thousands of assets per game.
Abe developed a system utilizing generative AI to analyze game design documents and generate design concepts. This system, incorporating models like Google Gemini Pro, Gemini Flash, and Imagen, aims to accelerate development, refine outputs through iterative feedback, and ultimately reduce costs substantially while potentially improving overall quality.
Currently, Capcom's AI implementation is focused on this specific design generation process. Other crucial aspects of game development, including core gameplay mechanics, programming, character design, and overarching narrative ideation, remain under the purview of human developers.
