用可组合的LoRA实现多角色故事插画的身份一致
CharCom: Composable Identity Control for Multi-Character Story Illustration
- 通过动态组合LoRA适配器实现角色身份控制
- 在多场景叙事中显著提升角色一致性与时序连贯性
- 无需重训练模型，适合故事创作与动画制作
在基于扩散模型的文生图生成中，保持角色身份一致性仍是核心挑战。我们提出CharCom，一种模块化且参数高效的框架，通过可组合的LoRA适配器，在不重新训练基础模型的前提下实现角色一致的故事插图生成。该框架基于冻结的扩散主干网络，在推理阶段利用提示感知控制动态组合适配器。在多场景叙事任务上的实验表明，CharCom显著提升了角色保真度、语义对齐度和时序连贯性。即使在复杂拥挤场景下仍具鲁棒性，支持低成本的多角色扩展生成，适用于故事插画与动画等真实应用场景。
原文摘要 · Abstract (English)
Ensuring character identity consistency across varying prompts remains a fundamental limitation in diffusion-based text-to-image generation. We propose CharCom, a modular and parameter-efficient framework that achieves character-consistent story illustration through composable LoRA adapters, enabling efficient per-character customization without retraining the base model. Built on a frozen diffusion backbone, CharCom dynamically composes adapters at inference using prompt-aware control. Experiments on multi-scene narratives demonstrate that CharCom significantly enhances character fidelity, semantic alignment, and temporal coherence. It remains robust in crowded scenes and enables scalable multi-character generation with minimal overhead, making it well-suited for real-world applications such as story illustration and animation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。