SakugaFlow: A Stagewise Illustration Framework Emulating the Human Drawing Process and Providing Interactive Tutoring for Novice Drawing Skills

2025-06-10

AI Summary

Existing AI image generation tools produce high-quality outputs but lack modeling of human stepwise artistic creation, limiting their utility in art pedagogy. Method: We propose a four-stage progressive drawing framework that integrates a Stable Diffusion variant with an LLM-driven multi-turn instructional dialogue system. The diffusion process is decoupled into interpretable intermediate representations—such as anatomy, perspective, and composition—and supports nonlinear editing and branching creative exploration. Contribution/Results: We introduce the “generation-as-instruction” paradigm, transforming AI from a content generator into an educational creative scaffold. User studies with novice artists show that 87% successfully transitioned to autonomous composition, structural error rates decreased by 32%, and both conceptual understanding and practical drawing proficiency improved significantly.

Technology Category

• Humans and AI: Game Design — Procedural Content Generation & Storytelling
• Computer Vision: Diffusion Models for Vision
• Cognitive Modeling & Cognitive Systems: Computational Creativity

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications

Abstract

While current AI illustration tools can generate high-quality images from text prompts, they rarely reveal the step-by-step procedure that human artists follow. We present SakugaFlow, a four-stage pipeline that pairs diffusion-based image generation with a large-language-model tutor. At each stage, novices receive real-time feedback on anatomy, perspective, and composition, revise any step non-linearly, and branch alternative versions. By exposing intermediate outputs and embedding pedagogical dialogue, SakugaFlow turns a black-box generator into a scaffolded learning environment that supports both creative exploration and skills acquisition.

Problem

• Emulate human drawing process for novice artists
• Provide interactive tutoring for drawing skills
• Combine AI generation with step-by-step feedback

Innovation

• Four-stage pipeline with diffusion-based generation
• Real-time feedback via large-language-model tutor
• Non-linear revision and branching alternatives