ComfySearch: Autonomous Exploration and Reasoning for ComfyUI Workflows

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.