# CharCom: Composable Identity Control for Multi-Character Story Illustration

arXiv: https://arxiv.org/abs/2510.10135 · HTML: https://mlsanity.com/paper/2510.10135/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models.
- Builds on 12 of its 28 references that are in the map.
- First posted on arXiv 11 Oct 2025.

## Placed in

- Diffusion models / [Image generation, text-to-image and editing](https://mlsanity.com/diffusion/image-generation-text-to-image-and-editing/)

## Builds on (most cited first, 12 of 12)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022)
- [Multi-Concept Customization of Text-to-Image Diffusion](https://mlsanity.com/paper/2212.04488/) (2022)
- [Less-to-More Generalization: Unlocking More Controllability by In-Context Generation](https://mlsanity.com/paper/2504.02160/) (2025)
- [StoryDALL-E: Adapting Pretrained Text-to-Image Transformers for Story Continuation](https://mlsanity.com/paper/2209.06192/) (2022)
- [The Chosen One: Consistent Characters in Text-to-Image Diffusion Models](https://mlsanity.com/paper/2311.10093/) (2023)
- [CharacterFactory: Sampling Consistent Characters with GANs for Diffusion Models](https://mlsanity.com/paper/2404.15677/) (2024)
- [AutoStudio: Crafting Consistent Subjects in Multi-turn Interactive Image Generation](https://mlsanity.com/paper/2406.01388/) (2024)
- [Personalized Image Generation with Deep Generative Models: A Decade Survey](https://mlsanity.com/paper/2502.13081/) (2025)
- [Conceptrol: Concept Control of Zero-shot Personalized Image Generation](https://mlsanity.com/paper/2503.06568/) (2025)
- [ORACLE: Leveraging Mutual Information for Consistent Character Generation with LoRAs in Diffusion Models](https://mlsanity.com/paper/2406.02820/) (2024)

## Built on by (most cited first, 2 of 2)

- [Squeezing Capacity from Multimodal Large Language Models for Subject-driven Generation](https://mlsanity.com/paper/2605.26111/) (2026)
- [SDO: Subspace Deconflicting Operator for Multi-Adapter Composition](https://mlsanity.com/paper/2608.13820/) (2026)

## Abstract (arXiv)

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.