MagicTailor: Component-Controllable Personalization in Text-to-Image Diffusion Models
Abstract
Text-to-image diffusion models can generate high-quality images but lack fine-grained control of visual concepts, limiting their creativity. Thus, we introduce component-controllable personalization, a new task that enables users to customize and reconfigure individual components within concepts. This task faces two challenges: semantic pollution, where undesired elements disrupt the target concept, and semantic imbalance, which causes disproportionate learning of the target concept and component. To address these, we design MagicTailor, a framework that uses Dynamic Masked Degradation to adaptively perturb unwanted visual semantics and Dual-Stream Balancing for more balanced learning of desired visual semantics. The experimental results show that MagicTailor achieves superior performance in this task and enables more personalized and creative image generation.
Cite
Text
Zhou et al. "MagicTailor: Component-Controllable Personalization in Text-to-Image Diffusion Models." International Joint Conference on Artificial Intelligence, 2025. doi:10.24963/IJCAI.2025/1136Markdown
[Zhou et al. "MagicTailor: Component-Controllable Personalization in Text-to-Image Diffusion Models." International Joint Conference on Artificial Intelligence, 2025.](https://mlanthology.org/ijcai/2025/zhou2025ijcai-magictailor/) doi:10.24963/IJCAI.2025/1136BibTeX
@inproceedings{zhou2025ijcai-magictailor,
title = {{MagicTailor: Component-Controllable Personalization in Text-to-Image Diffusion Models}},
author = {Zhou, Donghao and Huang, Jiancheng and Bai, Jinbin and Wang, Jiaze and Chen, Hao and Chen, Guangyong and Hu, Xiaowei and Heng, Pheng-Ann},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2025},
pages = {10225-10233},
doi = {10.24963/IJCAI.2025/1136},
url = {https://mlanthology.org/ijcai/2025/zhou2025ijcai-magictailor/}
}