{"ID":2857065,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.10135","arxiv_id":"2510.10135","title":"CharCom: Composable Identity Control for Multi-Character Story Illustration","abstract":"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.","short_abstract":"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-char...","url_abs":"https://arxiv.org/abs/2510.10135","url_pdf":"https://arxiv.org/pdf/2510.10135v2","authors":"[\"Zhongsheng Wang\",\"Ming Lin\",\"Zhedong Lin\",\"Yaser Shakib\",\"Qian Liu\",\"Jiamou Liu\"]","published":"2025-10-11T09:36:20Z","proceeding":"cs.AI","tasks":"[\"cs.AI\"]","methods":"[\"Diffusion Model\",\"LoRA\"]","has_code":false}