Diffusion models have shown excellent performance in text-to-image generation. Nevertheless, existing methods often suffer from performance bottlenecks when handling complex prompts that involve multiple objects, characteristics, and relations. Therefore, we propose a Multi-agent Collaboration-based Compositional Diffusion (MCCD) for text-to-image generation for complex scenes. Specifically, we design a multi-agent collaboration-based scene parsing module that generates an agent system comprising multiple agents with distinct tasks, utilizing MLLMs to extract various scene elements effectively. In addition, Hierarchical Compositional diffusion utilizes a Gaussian mask and filtering to refine bounding box regions and enhance objects through region enhancement, resulting in the accurate and high-fidelity generation of complex scenes. Comprehensive experiments demonstrate that our MCCD significantly improves the performance of the baseline models in a training-free manner, providing a substantial advantage in complex scene generation.
@article{arxiv.2505.02648,
title = {MCCD: Multi-Agent Collaboration-based Compositional Diffusion for Complex Text-to-Image Generation},
author = {Mingcheng Li and Xiaolu Hou and Ziyang Liu and Dingkang Yang and Ziyun Qian and Jiawei Chen and Jinjie Wei and Yue Jiang and Qingyao Xu and Lihua Zhang},
journal= {arXiv preprint arXiv:2505.02648},
year = {2025}
}