Panel-by-Panel Souls: A Performative Workflow for Expressive Faces in AI-Assisted Manga Creation

TL;DR

This paper presents an interactive, artist-centric workflow that combines manual face framing and performative video input to enhance expressive face rendering in AI-assisted manga creation, addressing limitations of current text-to-image models.

Contribution

It introduces a novel, dual-hybrid pipeline that integrates manual and performative inputs for more nuanced facial expressions in manga, bridging artistic intent and AI output.

Findings

Streamlines manga creation process

Enables fine-grained control of facial expressions

Improves translation of narrative intent into visuals

Abstract

Current text-to-image models struggle to render the nuanced facial expressions required for compelling manga narratives, largely due to the ambiguity of language itself. To bridge this gap, we introduce an interactive system built on a novel, dual-hybrid pipeline. The first stage combines landmark-based auto-detection with a manual framing tool for robust, artist-centric face preparation. The second stage maps expressions using the LivePortrait engine, blending intuitive performative input from video for fine-grained control. Our case study analysis suggests that this integrated workflow can streamline the creative process and effectively translate narrative intent into visual expression. This work presents a practical model for human-AI co-creation, offering artists a more direct and intuitive means of ``infusing souls'' into their characters. Our primary contribution is not a new generative model, but a novel, interactive workflow that bridges the gap between artistic intent and AI execution.