ComfySearch: Autonomous Exploration and Reasoning for ComfyUI Workflows
Jinwei Su, Qizhen Lan, Zeyu Wang, Yinghui Xia, Hairu Wen, Yiqun Duan, Xi Xiao, Tianyu Shi, Yang Jingsong, Lewei He

TL;DR
ComfySearch is an autonomous framework that explores and constructs ComfyUI workflows, significantly improving the success rate and quality of AI-generated creative pipelines through validation-guided exploration.
Contribution
The paper introduces ComfySearch, a novel agentic framework that enhances exploration and construction of ComfyUI workflows, addressing structural consistency and pass rate issues.
Findings
Outperforms existing methods on complex tasks
Achieves higher pass and solution rates
Demonstrates stronger generalization capabilities
Abstract
AI-generated content has progressed from monolithic models to modular workflows, especially on platforms like ComfyUI, allowing users to customize complex creative pipelines. However, the large number of components in ComfyUI and the difficulty of maintaining long-horizon structural consistency under strict graph constraints frequently lead to low pass rates and workflows of limited quality. To tackle these limitations, we present ComfySearch, an agentic framework that can effectively explore the component space and generate functional ComfyUI pipelines via validation-guided workflow construction. Experiments demonstrate that ComfySearch substantially outperforms existing methods on complex and creative tasks, achieving higher executability (pass) rates, higher solution rates, and stronger generalization.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsScientific Computing and Data Management · Machine Learning in Materials Science · Business Process Modeling and Analysis
