This paper explores using Large Language Models and Diffusion Models to procedurally generate trading card game content, specifically for Pokémon cards. The research proposes a pipeline that combines player co-creation with AI models to create personalized and dynamic card designs. A user study with 49 participants demonstrated high satisfaction with the generated cards, indicating the potential for AI to enhance creative range and offer alternatives to traditional game evolution. AI
IMPACT Demonstrates a novel application of generative AI for personalized content creation in established industries like TCGs.
RANK_REASON Academic paper detailing a novel application of LLMs and diffusion models for procedural content generation.
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →
