Capcom is exploring generative AI to streamline the creation of the vast number of design concepts required for its game environments. The rising costs of video game development are driving publishers to investigate AI tools, despite controversy. Activision, for instance, faced criticism for allegedly using AI in Call of Duty: Modern Warfare 3 cosmetics and loading screens. EA even declared AI as "fundamental" 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 resources dedicated to generating the "hundreds of thousands" of unique ideas needed for game assets. He cited even seemingly simple objects like televisions, each requiring unique designs, logos, and shapes. This necessitates numerous design proposals, complete with illustrations and descriptions, for each asset.
To address this efficiency bottleneck, Abe developed a system leveraging generative AI. This system processes various game design documents, generating design concepts and refining them through iterative feedback loops. The prototype, utilizing 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 potential quality improvement compared to manual design processes.
Currently, Capcom's AI implementation is confined to this specific system. Other crucial aspects of game development, including overall game design, gameplay mechanics, programming, and character design, remain under the control of human developers.
