ComfyGPT: A Self-Optimizing Multi-Agent System for Comprehensive ComfyUI Workflow Generation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908544077398016 |
|---|---|
| author | Huang, Oucheng Ma, Yuhang Zhao, Zeng Wu, Mingrui Ji, Jiayi Zhang, Rongsheng Hu, Zhipeng Sun, Xiaoshuai Ji, Rongrong |
| author_facet | Huang, Oucheng Ma, Yuhang Zhao, Zeng Wu, Mingrui Ji, Jiayi Zhang, Rongsheng Hu, Zhipeng Sun, Xiaoshuai Ji, Rongrong |
| contents | ComfyUI is a popular workflow-based interface that allows users to customize image generation tasks through an intuitive node-based system. However, the complexity of managing node connections and diverse modules can be challenging for users. In this paper, we introduce ComfyGPT, a self-optimizing multi-agent system designed to generate ComfyUI workflows based on task descriptions automatically. The key innovations of ComfyGPT include: (1) consisting of four specialized agents to build a multi-agent workflow generation system: ReformatAgent, FlowAgent, RefineAgent, and ExecuteAgent; (2) focusing on generating precise node connections instead of entire workflows, improving generation accuracy; and (3) enhancing workflow generation through reinforcement learning. Moreover, we introduce FlowDataset, a large-scale dataset containing 13,571 workflow-description pairs, and FlowBench, a comprehensive benchmark for evaluating workflow generation systems. Additionally, we propose four novel evaluation metrics: Format Validation (FV), Pass Accuracy (PA), Pass Instruct Alignment (PIA), and Pass Node Diversity (PND). Experimental results demonstrate that ComfyGPT significantly outperforms existing LLM-based methods in workflow generation, making it a significant step forward in this field. Code is avaliable at https://github.com/comfygpt/comfygpt. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_17671 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ComfyGPT: A Self-Optimizing Multi-Agent System for Comprehensive ComfyUI Workflow Generation Huang, Oucheng Ma, Yuhang Zhao, Zeng Wu, Mingrui Ji, Jiayi Zhang, Rongsheng Hu, Zhipeng Sun, Xiaoshuai Ji, Rongrong Multiagent Systems Artificial Intelligence ComfyUI is a popular workflow-based interface that allows users to customize image generation tasks through an intuitive node-based system. However, the complexity of managing node connections and diverse modules can be challenging for users. In this paper, we introduce ComfyGPT, a self-optimizing multi-agent system designed to generate ComfyUI workflows based on task descriptions automatically. The key innovations of ComfyGPT include: (1) consisting of four specialized agents to build a multi-agent workflow generation system: ReformatAgent, FlowAgent, RefineAgent, and ExecuteAgent; (2) focusing on generating precise node connections instead of entire workflows, improving generation accuracy; and (3) enhancing workflow generation through reinforcement learning. Moreover, we introduce FlowDataset, a large-scale dataset containing 13,571 workflow-description pairs, and FlowBench, a comprehensive benchmark for evaluating workflow generation systems. Additionally, we propose four novel evaluation metrics: Format Validation (FV), Pass Accuracy (PA), Pass Instruct Alignment (PIA), and Pass Node Diversity (PND). Experimental results demonstrate that ComfyGPT significantly outperforms existing LLM-based methods in workflow generation, making it a significant step forward in this field. Code is avaliable at https://github.com/comfygpt/comfygpt. |
| title | ComfyGPT: A Self-Optimizing Multi-Agent System for Comprehensive ComfyUI Workflow Generation |
| topic | Multiagent Systems Artificial Intelligence |
| url | https://arxiv.org/abs/2503.17671 |