用智能代理自动构建高质量ComfyUI创作流程，解决组件组合难、成功率低的问题。
ComfySearch: Autonomous Exploration and Reasoning for ComfyUI Workflows
- 设计智能体通过验证引导探索组件空间，自动生成可运行的工作流。
- 在复杂任务上通过率超现有方法，解决方案生成率和泛化能力显著提升。
- 适合需要高效搭建创意工作流的AI内容创作者与开发者使用。
AI生成内容已从单一模型演变为模块化工作流，尤其在ComfyUI等平台中，用户可自定义复杂的创作流程。然而，ComfyUI组件数量庞大，在严格图结构约束下维持长时序一致性困难，常导致执行失败率高、流程质量有限。为此，我们提出ComfySearch——一种智能体框架，通过验证引导的工作流构建，有效探索组件空间并生成可运行的ComfyUI管道。实验表明，ComfySearch在复杂创意任务上显著优于现有方法，实现更高的可执行性（通过率）、更高的解决方案生成率以及更强的泛化能力。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。