MCCD: Multi-Agent Collaboration-based Compositional Diffusion for Complex Text-to-Image Generation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866918010849067008 |
|---|---|
| author | Li, Mingcheng Hou, Xiaolu Liu, Ziyang Yang, Dingkang Qian, Ziyun Chen, Jiawei Wei, Jinjie Jiang, Yue Xu, Qingyao Zhang, Lihua |
| author_facet | Li, Mingcheng Hou, Xiaolu Liu, Ziyang Yang, Dingkang Qian, Ziyun Chen, Jiawei Wei, Jinjie Jiang, Yue Xu, Qingyao Zhang, Lihua |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_02648 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MCCD: Multi-Agent Collaboration-based Compositional Diffusion for Complex Text-to-Image Generation Li, Mingcheng Hou, Xiaolu Liu, Ziyang Yang, Dingkang Qian, Ziyun Chen, Jiawei Wei, Jinjie Jiang, Yue Xu, Qingyao Zhang, Lihua Computer Vision and Pattern Recognition 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. |
| title | MCCD: Multi-Agent Collaboration-based Compositional Diffusion for Complex Text-to-Image Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2505.02648 |