[3F1-GS-10] AI application:

[3F1-GS-10-01] Proposal and Evaluation Experiment of a Fine-Tuning Method for LLMs Using the Ideation Process of Art Directors

〇Daisuke Niino¹, Susumu Namikawa¹, Hitomi Matsushita¹, Yoshia Abe² (1. DENTSU INC., 2. AI Center, The Univ. of Tokyo)

Keywords:Large Language Models, Professional skills modeling, Art direction, Idea generation, Aesthetic modeling

In recent years, the advancement of diffusion models for text-to-image generation has enabled users to quickly produce visual content from textual prompts. However, these models may still fail to capture specialized expertise in creative domains such as advertising, where an art director’s ideation process is crucial for effective communication and brand storytelling. This study proposes a method that fine-tunes a large-scale model using data based on an art director’s conceptual thinking, including brand insight, metaphor formulation, and design rationale. We collected detailed textual representations of real advertising projects and performed supervised fine-tuning. An online evaluation with 1,000 participants was then conducted to compare our proposed approach against a baseline model, using eight key metrics related to creative quality. The results showed significant improvements (5%–12%; p<0.001) in overall appeal, visual impact, metaphorical expression, and other dimensions. Our findings suggest that embedding an art director’s thought process within the training data can help generate more compelling and conceptually rich visual outputs, thereby bridging the gap between automated image generation and professional-level art direction. Such an approach highlights the importance of domain-specific knowledge in shaping AI-based image generation workflows.