2K角色-10K故事：一个具有解耦控制和序列一致性的质量门控风格化叙事数据集
2K-Characters-10K-Stories: A Quality-Gated Stylized Narrative Dataset with Disentangled Control and Sequence Consistency
AI总结：
本文提出2K-Characters-10K-Stories数据集，通过解耦控制和质量门控机制，实现高质量的风格化叙事生成。
摘要：
在可控视觉叙事中，精确的瞬时属性控制下的序列身份一致性仍是一个长期存在的挑战。现有数据集缺乏足够的保真度，并未能将稳定的身份与瞬时属性解耦，限制了对姿态、表情和场景构成的结构化控制，从而限制了可靠的序列合成。为了解决这一差距，我们引入了2K角色-10K故事数据集，这是一个包含2,000个独特风格化角色出现在10,000个插图故事中的多模态风格化叙事数据集。它是第一个将大规模唯一身份与显式、解耦的控制信号配对以实现序列身份一致性的数据集。我们引入了一种人机协同流水线（HiL），利用专家验证的角色模板和LLM引导的叙事规划来生成高度对齐的结构化数据。一种解耦控制方案将持久身份与瞬时属性（姿态和表情）分开，同时一种质量门控循环整合MMLM评估、Auto-Prompt Tuning和局部图像编辑，以强制像素级一致性。广泛的实验表明，经过我们数据集微调的模型在生成视觉叙事方面的性能与闭源模型相当。
英文摘要：
Sequential identity consistency under precise transient attribute control remains a long-standing challenge in controllable visual storytelling. Existing datasets lack sufficient fidelity and fail to disentangle stable identities from transient attributes, limiting structured control over pose, expression, and scene composition and thus constraining reliable sequential synthesis. To address this gap, we introduce \textbf{2K-Characters-10K-Stories}, a multi-modal stylized narrative dataset of \textbf{2{,}000} uniquely stylized characters appearing across \textbf{10{,}000} illustration stories. It is the first dataset that pairs large-scale unique identities with explicit, decoupled control signals for sequential identity consistency. We introduce a \textbf{Human-in-the-Loop pipeline (HiL)} that leverages expert-verified character templates and LLM-guided narrative planning to generate highly-aligned structured data. A \textbf{decoupled control} scheme separates persistent identity from transient attributes -- pose and expression -- while a \textbf{Quality-Gated loop} integrating MMLM evaluation, Auto-Prompt Tuning, and Local Image Editing enforces pixel-level consistency. Extensive experiments demonstrate that models fine-tuned on our dataset achieves performance comparable to closed-source models in generating visual narratives.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
