2024/12/10 by Jianzong Wu, Jianhua Wu, Chao Tang +10 · 1 voice · 8 citations
Arts and Humanities · Computer Science · #Digital Humanities and Scholarship #Handwritten Text Recognition Techniques #cs.CV
paper · pdf · doi:10.48550/arxiv.2412.07589
openalex publication_date 2024/12/10 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Story visualization, the task of creating visual narratives from textual descriptions, has seen progress with text-to-image generation models. However, these models often lack effective control over character appearances and interactions, particularly in multi-character scenes. To address these limitations, we propose a new task: customized manga generation and introduce DiffSensei, an innovative framework specifically designed for generating manga with dynamic multi-character control. DiffSensei integrates a diffusion-based image generator with a multimodal large language model (MLLM) that acts as a text-compatible identity adapter. Our approach employs masked cross-attention to seamlessly incorporate character features, enabling precise layout control without direct pixel transfer. Additionally, the MLLM-based adapter adjusts character features to align with panel-specific text cues, allowing flexible adjustments in character expressions, poses, and actions. We also introduce MangaZero, a large-scale dataset tailored to this task, containing 43,264 manga pages and 427,147 annotated panels, supporting the visualization of varied character interactions and movements across sequential frames. Extensive experiments demonstrate that DiffSensei outperforms existing models, marking a significant advancement in manga generation by enabling text-adaptable character customization. The project page is https://jianzongwu.github.io/projects/diffsensei/.