SakugaFlow: A Stagewise Illustration Framework Emulating the Human Drawing Process and Providing Interactive Tutoring for Novice Drawing Skills
This addresses the need for scaffolded learning in AI-driven art tools for novices, though it is incremental as it builds on existing diffusion and LLM methods.
The authors tackled the problem of AI illustration tools lacking step-by-step guidance by developing SakugaFlow, a four-stage pipeline that pairs diffusion-based image generation with an LLM tutor to provide real-time feedback and interactive revision for novice artists.
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.