Sketchar: Supporting Character Design and Illustration Prototyping Using Generative AI

2025-08-17

AI Summary

In game development, narrative designers and illustrators suffer from low collaboration efficiency due to disciplinary gaps, resulting in significant visual communication bottlenecks in traditional workflows. This paper proposes a generative AI–assisted framework designed for cross-disciplinary collaboration, enabling non-artistic designers to rapidly generate high-fidelity character concept images from textual descriptions or hand-drawn sketches—serving as shared visual references to align creative intent with illustrators. The framework integrates controllable image generation, user-centered interaction optimization, and seamless workflow integration. Empirical evaluation demonstrates that the tool substantially enhances designers’ visual expressiveness and engagement; the generated reference images are effectively incorporated into production pipelines, accelerating iterative cycles and improving communication fidelity. This work contributes a reusable methodology and empirical validation for generative AI–augmented human–AI co-design in creative domains.

Technology Category

• Humans and AI: Game Design — Procedural Content Generation & Storytelling
• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Cognitive Modeling & Cognitive Systems: Computational Creativity

Application Category

• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Character design in games involves interdisciplinary collaborations, typically between designers who create the narrative content, and illustrators who realize the design vision. However, traditional workflows face challenges in communication due to the differing backgrounds of illustrators and designers, the latter with limited artistic abilities. To overcome these challenges, we created Sketchar, a Generative AI (GenAI) tool that allows designers to prototype game characters and generate images based on conceptual input, providing visual outcomes that can give immediate feedback and enhance communication with illustrators' next step in the design cycle. We conducted a mixed-method study to evaluate the interaction between game designers and Sketchar. We showed that the reference images generated in co-creating with Sketchar fostered refinement of design details and can be incorporated into real-world workflows. Moreover, designers without artistic backgrounds found the Sketchar workflow to be more expressive and worthwhile. This research demonstrates the potential of GenAI in enhancing interdisciplinary collaboration in the game industry, enabling designers to interact beyond their own limited expertise.

Problem

• Bridging communication gaps between game designers and illustrators
• Enabling non-artist designers to prototype characters visually
• Improving interdisciplinary collaboration in game character design

Innovation

• Generative AI tool for character prototyping
• Enhances interdisciplinary design communication
• Supports non-artists in expressive design