CharCom: Composable Identity Control for Multi-Character Story Illustration

• URL: http://arxiv.org/abs/2510.10135v1
• Date: Sat, 11 Oct 2025 09:36:20 GMT
• Title: CharCom: Composable Identity Control for Multi-Character Story Illustration
• Abstract summary: CharCom is a framework that achieves character-consistent story illustration through composable LoRA adapters.<n> Experiments on multi-scene narratives demonstrate that CharCom significantly enhances character fidelity, semantic alignment, and temporal coherence.<n>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.
• Score: 13.582635774872463
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• 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.

Related papers

• MultiAnimate: A Unified Framework for Controllable Multi-Character Animation [76.56813950148235]
  MultiAnimate is a framework that enables concurrent animation of multiple characters within a shared environment.<n>We introduce an identity-specific reference net that enables appearance extraction from multiple reference images.<n>Second, we implement an identity-aware pose encoder to address the character-pose binding challenge.<n>Third, we introduce an interaction guider module that enhances the framework's capability to handle complex inter-character interactions.
  arXiv  Detail & Related papers  (2026-07-15T03:33:52Z)
• MultiAct: Text-to-Motion Generation from Composite Text via Tailored Attention Guidance [54.131431576597514]
  MultiAct is an unpaired, inference-time framework for compositional text-to-motion synthesis.<n>Our method counteracts semantic collapse by adaptively amplifying cross-attention scores associated with underrepresented prompt components.
  arXiv  Detail & Related papers  (2026-05-29T07:14:48Z)
• Towards Customized Multimodal Role-Play [50.72454102691162]
  multimodal understanding and generation models enable richer human-AI interaction.<n>Yet jointly customizing a character's persona, dialogue style, and visual identity while maintaining output consistency across modalities remains largely unexplored.<n>We construct the RoleScape-20 dataset comprising 20 characters, including training and evaluation data that cover persona, stylistic descriptions, visual/expressive cues, and text-image interactions.<n>We devise UniCharacter, a two-stage training framework containing Unified Supervised Finetuning (Unified-SFT) and character-specific group relative policy optimization (Character-GRPO). Given only 10 images plus corresponding interaction examples, the model acquires the
  arXiv  Detail & Related papers  (2026-05-01T03:22:04Z)
• ReCap: Lightweight Referential Grounding for Coherent Story Visualization [11.022891519635834]
  ReCap is a lightweight consistency framework that improves character stability and visual fidelity without modifying the base diffusion backbone.<n>ReCap's CORE (COnditional frame REferencing) module treats anaphors, in our case pronouns, as visual anchors, activating only when characters are referred to by a pronoun and conditioning on the preceding frame to propagate visual identity.<n>We extend story visualization to human-centric narratives derived from real films, demonstrating the capability of ReCap beyond stylized cartoon domains.
  arXiv  Detail & Related papers  (2026-04-20T17:57:50Z)
• Customized Visual Storytelling with Unified Multimodal LLMs [19.106229466343787]
  VstoryGen is a framework that integrates descriptions with character and background references to enable customizable story generation.<n>We introduce shot-type control via parameter-efficient prompt tuning on movie data, enabling the model to generate sequences that more faithfully reflect cinematic grammar.
  arXiv  Detail & Related papers  (2026-03-29T13:24:51Z)
• Persistent Story World Simulation with Continuous Character Customization [85.65195925369268]
  We present EverTale, a story world simulator for continuous story character customization.<n>Our EverTale achieves superior performance against a wider range of compared methods on both single- and multi-character story visualization.
  arXiv  Detail & Related papers  (2026-03-17T09:17:10Z)
• StoryTailor:A Zero-Shot Pipeline for Action-Rich Multi-Subject Visual Narratives [7.243114047801061]
  We propose a zero-shot pipeline that produces temporally coherent, identity-preserving image sequences.<n>Story delivers expressive interactions and evolving yet stable scenes.
  arXiv  Detail & Related papers  (2026-02-24T16:07:02Z)
• TaleDiffusion: Multi-Character Story Generation with Dialogue Rendering [13.076013597876623]
  We introduce TaleDiffusion, a novel framework for generating multi-character stories with an iterative process.<n>Given a story, we use a pre-trained LLM to generate per-frame descriptions, character details, and dialogues.<n>We then apply an identity-consistent self-attention mechanism to ensure character consistency across frames and region-aware cross-attention for precise object placement.
  arXiv  Detail & Related papers  (2025-09-04T11:37:06Z)
• RMTBench: Benchmarking LLMs Through Multi-Turn User-Centric Role-Playing [111.06936588273868]
  RMTBench is a comprehensive textbfuser-centric bilingual role-playing benchmark featuring 80 diverse characters and over 8,000 dialogue rounds.<n>Our benchmark constructs dialogues based on explicit user motivations rather than character descriptions, ensuring alignment with practical user applications.<n>By shifting focus from character background to user intention fulfillment, RMTBench bridges the gap between academic evaluation and practical deployment requirements.
  arXiv  Detail & Related papers  (2025-07-27T16:49:47Z)
• CharaConsist: Fine-Grained Consistent Character Generation [93.08900337098302]
  CharaConsist is first consistent generation method tailored for text-to-image DiT model.<n>CharaConsist enables fine-grained consistency for both foreground and background.<n>Its ability to maintain fine-grained consistency, combined with the larger capacity of latest base model, enables it to produce high-quality visual outputs.
  arXiv  Detail & Related papers  (2025-07-15T17:58:08Z)
• InstantCharacter: Personalize Any Characters with a Scalable Diffusion Transformer Framework [24.29397138274732]
  InstantCharacter is a scalable framework for character customization built upon a foundation diffusion transformer.<n>It achieves open-domain personalization across diverse character appearances, poses, and styles while maintaining high-fidelity results.
  arXiv  Detail & Related papers  (2025-04-16T18:01:59Z)
• StoryWeaver: A Unified World Model for Knowledge-Enhanced Story Character Customization [36.14275850149665]
  We propose a novel knowledge graph, namely Character Graph (textbfCG), which comprehensively represents various story-related knowledge.<n>We then introduce StoryWeaver, an image generator that achieve Customization via Character Graph (textbfC-CG), capable of consistent story visualization with rich text semantics.
  arXiv  Detail & Related papers  (2024-12-10T10:16:50Z)
• CharacterBox: Evaluating the Role-Playing Capabilities of LLMs in Text-Based Virtual Worlds [74.02480671181685]
  Role-playing is a crucial capability of Large Language Models (LLMs)<n>Current evaluation methods fall short of adequately capturing the nuanced character traits and behaviors essential for authentic role-playing.<n>We propose CharacterBox, a simulation sandbox designed to generate situational fine-grained character behavior trajectories.
  arXiv  Detail & Related papers  (2024-12-07T12:09:35Z)
• Storynizor: Consistent Story Generation via Inter-Frame Synchronized and Shuffled ID Injection [27.412361280397057]
  We introduce Storynizor, a model capable of generating coherent stories with strong inter-frame character consistency. Key innovation of Storynizor lies in its key modules: ID-Synchronizer and ID-Injector. To facilitate the training of Storynizor, we have curated a novel dataset called StoryDB comprising 100, 000 images.
  arXiv  Detail & Related papers  (2024-09-29T09:15:51Z)
• Towards Multiple Character Image Animation Through Enhancing Implicit Decoupling [77.08568533331206]
  We propose a novel multi-condition guided framework for character image animation.<n>We employ several well-designed input modules to enhance the implicit decoupling capability of the model.<n>Our method excels in generating high-quality character animations, especially in scenarios of complex backgrounds and multiple characters.
  arXiv  Detail & Related papers  (2024-06-05T08:03:18Z)
• Text-Only Training for Visual Storytelling [107.19873669536523]
  We formulate visual storytelling as a visual-conditioned story generation problem. We propose a text-only training method that separates the learning of cross-modality alignment and story generation.
  arXiv  Detail & Related papers  (2023-08-17T09:32:17Z)
• Make-A-Story: Visual Memory Conditioned Consistent Story Generation [57.691064030235985]
  We propose a novel autoregressive diffusion-based framework with a visual memory module that implicitly captures the actor and background context. Our method outperforms prior state-of-the-art in generating frames with high visual quality. Our experiments for story generation on the MUGEN, the PororoSV and the FlintstonesSV dataset show that our method not only outperforms prior state-of-the-art in generating frames with high visual quality, but also models appropriate correspondences between the characters and the background.
  arXiv  Detail & Related papers  (2022-11-23T21:38:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.