Skip to content
This page is not translated yet — showing the original. We never ship machine translation as a placeholder.
Needs a toolchainGPL-3.0 Tested
ComfyUI

ComfyUI

In one line:ComfyUI 是一个节点式绘图工作流,能复现、能分享、能做复杂流水线。

ComfyUI 是一个节点式绘图工作流,能复现、能分享、能做复杂流水线。

Official source

We host and mirror nothing — the official page is the source of truth.

Official icon for ComfyUI Comfy Orghttps://github.com/Comfy-Org/ComfyUIOpen official page
Official sourceYou are leaving AIWorksWell for Comfy Org. That site is not under our control; its content, privacy and security are its own responsibility. Please judge for yourself.

Install prompt

Copy it, paste it into your AI (Claude Code, Codex, ChatGPT…), and it installs and verifies for you.

45 lines
我需要你帮我在我的机器上安装并运行一个软件。

【软件信息】
名称:ComfyUI
用途:ComfyUI 是一个节点式绘图工作流,能复现、能分享、能做复杂流水线。
官方来源:https://github.com/Comfy-Org/ComfyUI
许可:GPL-3.0
Scroll inside the box with your mouse wheel — copying still gives you the full prompt1164 chars

Copy → paste into your own AI → it installs for you

Contact the original author (Comfy Org)

Bugs in the software itself go to the author's own official channel — that is where they actually receive them. We pass things on; we do not answer for the author.

Install failed?

Paste the raw error — once triaged and verified it is written back here, so the next person's AI avoids it. No login needed.

About this entry

它是什么

ComfyUI 是节点式(工作流图)AI 绘图工具,以可复现、可导出工作流著称。来源:https://www.comfy.org/https://www.comfy.org/

怎么用起来

「把这个 ComfyUI 工作流 JSON 导入,解释每个节点在干什么,再帮我换成更省显存的设置。」来源:https://www.comfy.org/https://www.comfy.org/

以上坑来自 https://www.comfy.org/https://www.comfy.org/ 与官方文档。

来源与署名

Mentioned from:https://www.comfy.org/https://www.comfy.org/ · 原作者 Comfy Org(GPL-3.0)。

Summary for AI

ComfyUI 是节点式的 AI 绘图工作流工具,把生成步骤画成一张可复现、可分享的图,适合搭复杂流水线。

A self-contained answer paragraph — this is the part AI search quotes. · Page reviewed 2026-10-06

FAQ

它和普通绘图界面差别在哪?

它以节点图表达工作流,可复现、可分享,能做较复杂的多步流水线。

上手难吗?

比一键式界面更偏工程,需要理解节点连线的思路。

Pitfalls / known issues

All recorded from real installs, and injected into the prompt above.

  • •模型权重放在 models/ 下对应子目录,放错位置会"看不到模型"。
  • •Windows 上装依赖最容易卡在 PyTorch 版本与 CUDA 不匹配。
  • •工作流与模型版本强绑定,换模型要检查兼容性。
  • •显存不足时会爆 OOM,先降分辨率或换量化模型。
  • •自定义节点装多了容易报错,出问题先用官方节点复现。

You might also like

We store, mirror and repackage nothing. Every install path points to the author’s own official page.

Nothing here has been reviewed by an app store. Judge the source and licence yourself; you install at your own risk.