LingyiChen-AI/comfyui-workflow-skill

274 stars · Last commit 2026-04-09

Natural language → ComfyUI workflow JSON. 34 built-in templates, 360+ node definitions, auto model download. Supports txt2img, img2img, txt2vid, img2vid, audio, 3D generation across SD1.5/SDXL/SD3/FLUX/Wan2.2/HunyuanVideo/LTXV/Mochi/Cosmos + LLM integration. Works as a skill for Claude Code, Cursor, and other AI coding agents.

README preview

# ComfyUI Workflow Skill

> 用自然语言生成可直接导入 ComfyUI 的工作流 JSON 文件。

**无需 API 费用，无需后端。描述你想要的 → 生成有效的工作流 JSON → 导入 ComfyUI 运行。**

[![Linux.do](https://img.shields.io/badge/Linux.do-Discussion-blue)](https://linux.do/t/topic/1896794)

## 效果展示

### 安装 Skill
![安装skills](images/安装skills.png)

### AI 生成工作流 → 导入 ComfyUI → 运行出图
![生图转视频workflow](images/生图转视频workflow.png)
![图生视频流程](images/图生视频流程.png)

### 生成的图片 & 视频
![生成的图片](images/生成的图片.jpg)
![运行结果](images/运行结果.png)

View full repository on GitHub →