# ComfyUI-wiki

**Repository Path**: bdthsjl/ComfyUI-wiki

## Basic Information

- **Project Name**: ComfyUI-wiki
- **Description**: No description available
- **Primary Language**: Python
- **License**: MIT
- **Default Branch**: main
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 1
- **Forks**: 0
- **Created**: 2024-07-29
- **Last Updated**: 2025-08-02

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# 📄项目简介

![](images/Banner_Image1.jpg)

分享最好用、最实用的ComfyUI工作流，最新、最前沿的研究成果和相应的自定义节点（custom nodes），实用的视频、文字教程和知识等。

---

# 🌍ComfyUI门户
## 😜[我的B站主页](https://space.bilibili.com/29196949)
👥QQ交流群：801334535。
## 🚌方便直达

| 画廊（借鉴）                                                     | 官方、GitHub                                                      | 优质视频                                                            | 资源                                              |
| ---------------------------------------------------------- | -------------------------------------------------------------- | --------------------------------------------------------------- | ----------------------------------------------- |
| [ideogram](https://ideogram.ai/)                           | [ComfyUI](https://github.com/comfyanonymous/ComfyUI)           | [Nerdy Rodent](https://www.youtube.com/@NerdyRodent/videos)     | [OpenArt](https://openart.ai/workflows)         |
| [midjourney-showcase](https://www.midjourney.com/showcase) | [ComfyUI-Manager](https://github.com/ltdrdata/ComfyUI-Manager) | [Latent Vision](https://www.youtube.com/@latentvision/videos)   | [civitai](https://civitai.com/)                 |
|                                                            | [ZHO-ZHO-ZHO](https://github.com/ZHO-ZHO-ZHO)                  | [Olivio Sarikas](https://www.youtube.com/@OlivioSarikas/videos) | [-Zho-博客](https://space.bilibili.com/484366804) |
|                                                            | [实时⭐制作](https://shields.io/badges/git-hub-repo-stars)          | [Scott Detweiler](https://www.youtube.com/@sedetweiler)         |                                                 |
# 📊工作流分享

我把最实用的工作流（workflow）都给毫无保留地免费分享给所有需要的人：
## [点击查看workflows文件夹](./pysssss-workflows)

# 👍custom nodes排行榜
## 📈排行榜网站[nodecafe](https://www.nodecafe.org/)
看最新的custom nodes的⭐排行榜，请看这个网站📈[nodecafe](https://www.nodecafe.org/)，由[comfyui-workspace-manager](https://github.com/11cafe/comfyui-workspace-manager)构建，根据开源`custom nodes`获得的stars⭐排名！
## 🔍 亲测！强力推荐！
我自己亲测后，觉得是必装的，且在用的`custom nodes`。排名是我认为的，⭐的多少（实时）只是参考。

| Custom Nodes（实时⭐）                                                                                                                                                                              | 简介（最有用的功能）                                                                                                                                                                                                                                                                       |
| ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| [ComfyUI](https://github.com/comfyanonymous/ComfyUI)<br>![GitHub Repo stars](https://img.shields.io/github/stars/comfyanonymous/ComfyUI)                                                       | ComfyUI本体，神一样的存在！<br>[ComfyUI快捷键](https://github.com/comfyanonymous/ComfyUI?tab=readme-ov-file#shortcuts)<br>                                                                                                                                                                    |
| [ComfyUI-Manager](https://github.com/ltdrdata/ComfyUI-Manager)<br>![GitHub Repo stars](https://img.shields.io/github/stars/ltdrdata/ComfyUI-Manager)                                           | 安装、删除、禁用和启用 ComfyUI 各种自定义节点等等功能。                                                                                                                                                                                                                                                 |
| [ComfyUI-Custom-Scripts](https://github.com/pythongosssss/ComfyUI-Custom-Scripts)<br>![GitHub Repo stars](https://img.shields.io/github/stars/pythongosssss/ComfyUI-Custom-Scripts)<br>        | 图像源：[Image Feed](https://github.com/pythongosssss/ComfyUI-Custom-Scripts?tab=readme-ov-file#image-feed)<br>添加一个面板，显示当前会话中生成的图像，保存自己的工作流。                                                                                                                                         |
| [comfyui_controlnet_aux](https://github.com/Fannovel16/comfyui_controlnet_aux)<br>![GitHub Repo stars](https://img.shields.io/github/stars/Fannovel16/comfyui_controlnet_aux)                  | controlnet的预处理器几乎都集成到了`AIO Aux Preprocessor`节点                                                                                                                                                                                                                                   |
| [rgthree-comfy](https://github.com/rgthree/rgthree-comfy)<br>![GitHub Repo stars](https://img.shields.io/github/stars/rgthree/rgthree-comfy)<br>                                               | 让工作流程更清晰、更简单、更快捷                                                                                                                                                                                                                                                                 |
| [ComfyUI_LayerStyle](https://github.com/chflame163/ComfyUI_LayerStyle)<br>![](https://img.shields.io/github/stars/chflame163/ComfyUI_LayerStyle)                                               | 将一些基本的Photoshop功能迁移到ComfyUI中，还有一键移除背景、AI抠图之类的神奇功能。                                                                                                                                                                                                                               |
| [comfyui-inpaint-nodes](https://github.com/Acly/comfyui-inpaint-nodes)<br>![GitHub Repo stars](https://img.shields.io/github/stars/Acly/comfyui-inpaint-nodes)<br>                             | 实现更好的(inpainting)效果，包括SDXL的Fooocus修复模型、LaMa、MAT等。                                                                                                                                                                                                                                |
| [ComfyUI-N-Sidebar](https://github.com/Nuked88/ComfyUI-N-Sidebar)<br>![](https://img.shields.io/github/stars/Nuked88/ComfyUI-N-Sidebar)<br>                                                    | 侧边栏，支持节点的拖放、收藏、搜索，以及类别的展开/收起等功能，极大增强了界面交互体验。                                                                                                                                                                                                                                     |
| [ComfyUI-KJNodes](https://github.com/kijai/ComfyUI-KJNodes)<br>![GitHub Repo stars](https://img.shields.io/github/stars/kijai/ComfyUI-KJNodes)<br>                                             | 有set/get功能，就值了。隐藏了“面条”，界面清爽多了                                                                                                                                                                                                                                                    |
| [cg-use-everywhere](https://github.com/chrisgoringe/cg-use-everywhere)<br>![GitHub Repo stars](https://img.shields.io/github/stars/chrisgoringe/cg-use-everywhere)<br>                         | 无线连接任何同类型接口，省去重复的连接，很实用、很清爽                                                                                                                                                                                                                                                      |
| [ComfyUI-AnimateDiff-Evolved](https://github.com/Kosinkadink/ComfyUI-AnimateDiff-Evolved)<br>![GitHub Repo stars](https://img.shields.io/github/stars/Kosinkadink/ComfyUI-AnimateDiff-Evolved) | 其他动画类工作流必备：<br>- [ComfyUI_FizzNodes](https://github.com/FizzleDorf/ComfyUI_FizzNodes) <br>- [ComfyUI-Advanced-ControlNet](https://github.com/Kosinkadink/ComfyUI-Advanced-ControlNet) <br>- [ComfyUI-VideoHelperSuite](https://github.com/Kosinkadink/ComfyUI-VideoHelperSuite)  |
| [ComfyUI-IF_AI_tools](https://github.com/if-ai/ComfyUI-IF_AI_tools)<br>![GitHub Repo stars](https://img.shields.io/github/stars/if-ai/ComfyUI-IF_AI_tools)<br>                                 | 通过 Ollama 使用本地大型语言模型 (LLM) 生成提示，增强图像生成工作流程。                                                                                                                                                                                                                                      |
| [ComfyUI-Easy-Use](https://github.com/yolain/ComfyUI-Easy-Use)<br>![GitHub Repo stars](https://img.shields.io/github/stars/yolain/ComfyUI-Easy-Use)<br>                                        | 化繁为简的节点整合包, 在 [tinyterraNodes](https://github.com/TinyTerra/ComfyUI_tinyterraNodes) 的基础上进行延展，并针对了诸多主流的节点包做了整合与优化。                                                                                                                                                                |
| [sdxl_prompt_styler](https://github.com/twri/sdxl_prompt_styler)<br>![GitHub Repo stars](https://img.shields.io/github/stars/twri/sdxl_prompt_styler)                                          | 根据预定义模板来设计提示词的风格。                                                                                                                                                                                                                                                                |
| [ComfyUI_Fill-Nodes](https://github.com/filliptm/ComfyUI_Fill-Nodes)<br>![GitHub Repo stars](https://img.shields.io/github/stars/filliptm/ComfyUI_Fill-Nodes)<br>                              | 按顺序（每次渲染时）或随机（也是每次渲染时）提取图像；                                                                                                                                                                                                                                                      |
## 🗺️安装指南

如果ComfyUI安装了过多组件,可能会出现环境冲突等问题。我推荐使用Anaconda创建虚拟环境来运行ComfyUI,避免潜在的冲突。就算你的虚拟环境也装的太多了，引起了冲突，你还可以再创建一个虚拟环境来专门运行起你现在很需要运行起来的工作流。具体我写了份详细的文档，请批评指正：[Windows环境下ComfyUI自定义节点安装指南](docs/Windows环境下ComfyUI自定义节点安装指南.md)，视频解释：[ComfyUI报错的终极解决方案！](https://www.bilibili.com/video/BV1Up421Q7YA/?vd_source=7351bb1ce0a307c41b60b64ca036a240)

# 💡AIGC前沿技术


## 🤡主体特征(ID)

| 项目名称及网址                                                                                                                                                 | 介绍                      | huggingface demo（在线生成）                                                   | ComfyUI实现/视频介绍                                                                                                                                     |
| ------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------- | ------------------------------------------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------- |
| [InstantID](https://github.com/InstantID/InstantID)<br>![GitHub Repo stars](https://img.shields.io/github/stars/InstantID/InstantID)<br>                | 【主体特征】可实现使用单张图片进行ID保持生成 | [InstantID demo](https://huggingface.co/spaces/InstantX/InstantID)       | [ComfyUI InstantID](https://github.com/ZHO-ZHO-ZHO/ComfyUI-InstantID):<br>[ComfyUI_InstantID-（原生支持版）](https://github.com/cubiq/ComfyUI_InstantID)  |
| [PuLID](https://github.com/ToTheBeginning/PuLID)<br>![GitHub Repo stars](https://img.shields.io/github/stars/ToTheBeginning/PuLID)<br>                  | 【主体特征】优势：高速+高保真+风格迁移强   | [PuLID demo](https://huggingface.co/spaces/yanze/PuLID)                  | [ComfyUI-PuLID-ZHO](https://github.com/ZHO-ZHO-ZHO/ComfyUI-PuLID-ZHO)<br>[PuLID_ComfyUI](https://github.com/cubiq/PuLID_ComfyUI)cubiq大神版           |
| [IP-Adapter](https://github.com/tencent-ailab/IP-Adapter)<br>![GitHub Repo stars](https://img.shields.io/github/stars/tencent-ailab/IP-Adapter)<br>     | 【主体特征】                  | [IP-Adapter demo](https://huggingface.co/h94/IP-Adapter)                 | [ComfyUI_IPAdapter_plus](https://github.com/cubiq/ComfyUI_IPAdapter_plus)<br>![](https://img.shields.io/github/stars/cubiq/ComfyUI_IPAdapter_plus) |
| [InstantStyle](https://github.com/InstantStyle/InstantStyle)<br>![GitHub Repo stars](https://img.shields.io/github/stars/InstantStyle/InstantStyle)<br> | 【主体特征】长处是风格参考           | [InstantStyle demo](https://huggingface.co/spaces/InstantX/InstantStyle) |                                                                                                                                                    |
| [PhotoMaker](https://github.com/TencentARC/PhotoMaker)<br>![GitHub Repo stars](https://img.shields.io/github/stars/TencentARC/PhotoMaker)<br>           | 定制逼真的人物照片               |                                                                          |                                                                                                                                                    |
## 🕸️控制（controlnet）

| ControlNet<br>收集中…… | 1. [xinsir-sdxl](https://huggingface.co/xinsir)2. [lllyasviel大合集](https://huggingface.co/lllyasviel/sd_control_collection/tree/main)3. [MistoLine](https://github.com/TheMistoAI/MistoLine)4. [InstantX-SD3-Controlnet](https://huggingface.co/InstantX) |
| ------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
## 📺动画、数字人

| 项目名称及网址                                                                                                                                                  | 介绍                                                                                              | ComfyUI实现/视频介绍                                                                                                                                                                  |
| -------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| [LivePortrait](https://github.com/KwaiVGI/LivePortrait)<br>![GitHub Repo stars](https://img.shields.io/github/stars/KwaiVGI/LivePortrait)<br>            | 【动画】高效的肖像动画 - 结合缝合和重定向控制                                                                        | ![GitHub Repo stars](https://img.shields.io/github/stars/kijai/ComfyUI-LivePortraitKJ)<br>[ComfyUI-LivePortraitKJ](https://github.com/kijai/ComfyUI-LivePortraitKJ)             |
| [ToonCrafter](https://github.com/ToonCrafter/ToonCrafter)<br>![GitHub Repo stars](https://img.shields.io/github/stars/ToonCrafter/ToonCrafter)<br><br>   | 【动画】生成卡通动画差值，看上去很丝滑，[ToonCrafter-for-windows](https://github.com/sdbds/ToonCrafter-for-windows) | [ComfyUI-ToonCrafter](https://github.com/AIGODLIKE/ComfyUI-ToonCrafter)<br>![GitHub Repo stars](https://img.shields.io/github/stars/AIGODLIKE/ComfyUI-ToonCrafter)<br><br>      |
| [hallo](https://github.com/fudan-generative-vision/hallo)<br>![GitHub Repo stars](https://img.shields.io/github/stars/fudan-generative-vision/hallo)<br> | 【数字人】音频驱动肖像，复旦大学、百度、南京大学                                                                        | 系统需求：Ubuntu 20.04/Ubuntu 22.04, Cuda 12.1？！                                                                                                                                     |
| [MimicMotion](https://github.com/Tencent/MimicMotion)<br>![GitHub Repo stars](https://img.shields.io/github/stars/Tencent/MimicMotion)<br>               | 【动画】基于置信度感知姿态引导的高质量人体运动视频生成                                                                     | [ComfyUI-MimicMotionWrapper](https://github.com/kijai/ComfyUI-MimicMotionWrapper)![GitHub Repo stars](https://img.shields.io/github/stars/kijai/ComfyUI-MimicMotionWrapper)<br> |
| [champ](https://github.com/fudan-generative-vision/champ)<br>![GitHub Repo stars](https://img.shields.io/github/stars/fudan-generative-vision/champ)<br> | 【动画、视频】通过3D参数引导的可控且一致的人像动画，这项目用到了Blender！                                                       | [ComfyUI-champWrapper](https://github.com/kijai/ComfyUI-champWrapper)<br>![GitHub Repo stars](https://img.shields.io/github/stars/kijai/ComfyUI-champWrapper)<br>               |
| [EchoMimic](https://github.com/BadToBest/EchoMimic)<br>![GitHub Repo stars](https://img.shields.io/github/stars/BadToBest/EchoMimic)<br>                 | 【声音驱动肖像】阿里开源                                                                                    | [ComfyUI_EchoMimic](https://github.com/smthemex/ComfyUI_EchoMimic)                                                                                                              |
## 🧠LLM赋能、语义理解、检测、分割、描述（caption）

| [Omost](https://github.com/lllyasviel/Omost)<br>![GitHub Repo stars](https://img.shields.io/github/stars/lllyasviel/Omost)                                                        | 【LLM赋能SD】将LLM的编码能力转换为图像生成（或更准确地说，图像组合）能力，[Omost demo](https://huggingface.co/spaces/lllyasviel/Omost) | [ComfyUI_omost](https://github.com/huchenlei/ComfyUI_omost)<br>![GitHub Repo stars](https://img.shields.io/github/stars/huchenlei/ComfyUI_omost)<br>                                |
| --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| [ELLA](https://github.com/TencentQQGYLab/ELLA)<br>![GitHub Repo stars](https://img.shields.io/github/stars/TencentQQGYLab/ELLA)<br>                                               | 【语义理解】让大语言模型LLM赋能AI绘画                                                                                 | [ComfyUI_ELLA](https://github.com/ExponentialML/ComfyUI_ELLA)<br>![GitHub Repo stars](https://img.shields.io/github/stars/ExponentialML/ComfyUI_ELLA)<br>                           |
| [DenseDiffusion](https://github.com/naver-ai/DenseDiffusion)<br>![GitHub Repo stars](https://img.shields.io/github/stars/naver-ai/DenseDiffusion)<br>                             | 【语义理解、解构画面】处理密集提示词，即插即用                                                                               | [ComfyUI_densediffusion](https://github.com/huchenlei/ComfyUI_densediffusion)<br>![GitHub Repo stars](https://img.shields.io/github/stars/huchenlei/ComfyUI_densediffusion)<br>     |
| [florence-2](https://clarifai.com/microsoft/florence/models/florence-2-large)                                                                                                     | 【检测、分割、描述】微软免费                                                                                        | [ComfyUI-Florence2](https://github.com/kijai/ComfyUI-Florence2)<br>![GitHub Repo stars](https://img.shields.io/github/stars/kijai/ComfyUI-Florence2)                                |
| [segment-anything-2](https://github.com/facebookresearch/segment-anything-2)<br>![GitHub Repo stars](https://img.shields.io/github/stars/facebookresearch/segment-anything-2)<br> | 【检测、分割】Meta出品                                                                                         | [ComfyUI-segment-anything-2](https://github.com/kijai/ComfyUI-segment-anything-2)<br>![GitHub Repo stars](https://img.shields.io/github/stars/kijai/ComfyUI-segment-anything-2)<br> |

## ✏️扩图、擦除、重绘
| [BrushNet](https://github.com/TencentARC/BrushNet)<br>![GitHub Repo stars](https://img.shields.io/github/stars/TencentARC/BrushNet)<br>       | 【局部重绘】局部重绘效果不错                | [ComfyUI-BrushNet](https://github.com/nullquant/ComfyUI-BrushNet)<br>            |
| --------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------- | -------------------------------------------------------------------------------- |
| [PowerPaint](https://github.com/open-mmlab/PowerPaint)<br>![GitHub Repo stars](https://img.shields.io/github/stars/open-mmlab/PowerPaint)<br> | 【扩图、擦除、重绘】                    | [ComfyUI-BrushNet](https://github.com/nullquant/ComfyUI-BrushNet)含PowerPaint v2  |
| [IOPaint](https://github.com/Sanster/IOPaint)<br>![GitHub Repo stars](https://img.shields.io/github/stars/Sanster/IOPaint)<br>                | 【擦除、重绘、去除背景、生成文字】集大成，完成度很高的项目 | [iopaint官网](https://www.iopaint.com/)                                            |
| [InSPyReNet](https://github.com/plemeri/InSPyReNet)<br>![GitHub Repo stars](https://img.shields.io/github/stars/plemeri/InSPyReNet)<br>       | 背景移除效果一流                      | [ComfyUI-Inspyrenet-Rembg](https://github.com/john-mnz/ComfyUI-Inspyrenet-Rembg) |

## 🏬全新架构（大厂出品）

| [flux](https://github.com/black-forest-labs/flux)<br>![GitHub Repo stars](https://img.shields.io/github/stars/black-forest-labs/flux)                   | [23.8GB完整版FLUX.1-dev模型下载](https://huggingface.co/black-forest-labs/FLUX.1-dev)<br>[17.2GBfp8版FLUX.1-DEV](https://huggingface.co/Comfy-Org/flux1-dev/tree/main)<br>[Flux.1介绍](https://blackforestlabs.ai/announcing-black-forest-labs/) | ComfyUI原生支持                                                                                                                                                                                                                                                 |
| ------------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| [Kolors](https://github.com/Kwai-Kolors/Kolors)<br>![GitHub Repo stars](https://img.shields.io/github/stars/Kwai-Kolors/Kolors)<br>                     | 【全新模型架构】快手开源                                                                                                                                                                                                                           | [ComfyUI-KwaiKolorsWrapper](https://github.com/kijai/ComfyUI-KwaiKolorsWrapper)<br>![GitHub Repo stars](https://img.shields.io/github/stars/kijai/ComfyUI-KwaiKolorsWrapper)                                                                                |
| [PixArt-sigma](https://github.com/PixArt-alpha/PixArt-sigma)<br>![GitHub Repo stars](https://img.shields.io/github/stars/PixArt-alpha/PixArt-sigma)<br> | 【全新模型架构】华为诺亚方舟实验室、大连理工大学、香港大学合作开发的项目。<br>[亲测可用的简化安装教程](docs/PIXART-Σ基于扩散Transformer的弱到强训练方法,用于4K文本到图像生成.md)                                                                                                                            | [ComfyUI_ExtraModels](https://github.com/city96/ComfyUI_ExtraModels)<br>[官方-如何在ComfyUI中使用PixArt](https://github.com/PixArt-alpha/PixArt-alpha/blob/master/asset/docs/pixart_comfyui.md)<br>工作流[12-PixArt-sigma](pysssss-workflows/12-PixArt-sigma.json)<br> |
| [HunyuanDiT](https://github.com/Tencent/HunyuanDiT)<br>![GitHub Repo stars](https://img.shields.io/github/stars/Tencent/HunyuanDiT)<br>                 | 【全新模型架构】腾讯开源                                                                                                                                                                                                                           | [comfyui-hydit](https://github.com/Tencent/HunyuanDiT/tree/main/comfyui-hydit)官方<br>ComfyUI原生支持                                                                                                                                                             |
| [AuraFlow](https://huggingface.co/fal/AuraFlow)<br>                                                                                                     | [AuraFlow-v0.2](https://huggingface.co/fal/AuraFlow-v0.2)                                                                                                                                                                              | ComfyUI原生支持                                                                                                                                                                                                                                                 |
| [Stable Diffusion 3](https://stability.ai/news/stable-diffusion-3-api?utm_source=twitter&utm_medium=website&utm_campaign=blog)                          | 申请 API ：[Stability API key](https://platform.stability.ai/account/keys)                                                                                                                                                                | 官方版本：[ComfyUI-SAI_API](https://github.com/Stability-AI/ComfyUI-SAI_API)                                                                                                                                                                                     |

## 🔍放大、超分辨率（upscale、Super-Resolution）

| [SUPIR](https://github.com/Fanghua-Yu/SUPIR)<br>![GitHub Repo stars](https://img.shields.io/github/stars/Fanghua-Yu/SUPIR)<br>                             | 【图片放大】极致卓越的放大方案，模糊照片还原出照片级别质感                                                                                                           | [ComfyUI-SUPIR](https://github.com/kijai/ComfyUI-SUPIR)                                                                                                                              |
| ---------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| <br>[APISR](https://github.com/Kiteretsu77/APISR)<br>![GitHub Repo stars](https://img.shields.io/github/stars/Kiteretsu77/APISR)<br>                       | 【图片放大】- 对 [APISR](https://github.com/Kiteretsu77/APISR) 的非官方实现。专门用于动漫的超分模型，[APISR demo](https://huggingface.co/spaces/HikariDawn/APISR) | [ComfyUI-APISR](https://github.com/ZHO-ZHO-ZHO/ComfyUI-APISR)                                                                                                                        |
| [aura-sr](https://github.com/fal-ai/aura-sr)<br>![GitHub Repo stars](https://img.shields.io/github/stars/fal-ai/aura-sr)<br>                               | 【图片放大】这是GigaGAN论文在图像条件下放大方面的一个变种,用于实现真实世界图像的超分辨率。                                                                                       | [ComfyUI-AuraSR-ZHO](https://github.com/ZHO-ZHO-ZHO/ComfyUI-AuraSR-ZHO)<br>[AuraSR-ComfyUI](https://github.com/GreenLandisaLie/AuraSR-ComfyUI)                                       |
| [res-adapter](https://github.com/bytedance/res-adapter)<br>![GitHub Repo stars](https://img.shields.io/github/stars/bytedance/res-adapter)<br>             | 【分辨率自适应】即插即用的，可以使任何扩散模型生成无分辨率限制的图像                                                                                                      | [ComfyUI-ResAdapter](https://github.com/jiaxiangc/ComfyUI-ResAdapter)<br>![GitHub Repo stars](https://img.shields.io/github/stars/jiaxiangc/ComfyUI-ResAdapter)<br>                  |
| [HiDiffusion](https://github.com/megvii-research/HiDiffusion)<br>![GitHub Repo stars](https://img.shields.io/github/stars/megvii-research/HiDiffusion)<br> | 【高分辨率】解锁预训练扩散模型中的高分辨率创造力和效率                                                                                                             | [ComfyUI-HiDiffusion](https://github.com/florestefano1975/ComfyUI-HiDiffusion)<br>![GitHub Repo stars](https://img.shields.io/github/stars/florestefano1975/ComfyUI-HiDiffusion)<br> |
## 🎖️隐形冠军（文字、换装、加速、透明图、上色）


| [AnyText](https://github.com/tyxsspa/AnyText)<br>![GitHub Repo stars](https://img.shields.io/github/stars/tyxsspa/AnyText)<br>                              | 【生成文字】多语言（包括汉字！）视觉文本生成与编辑              | [AnyText安装指南](docs/AnyText安装指南.md)<br>[AnyText视频指南](https://www.bilibili.com/video/BV1Kr421G7Xi/?vd_source=7351bb1ce0a307c41b60b64ca036a240)<br>[ComfyUI-AnyText](https://github.com/zmwv823/ComfyUI-AnyText) |
| ----------------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| [Glyph-ByT5](https://github.com/AIGText/Glyph-ByT5)<br>![GitHub Repo stars](https://img.shields.io/github/stars/AIGText/Glyph-ByT5)<br>                     | 【生成文字】用于精确视觉文本渲染的定制文本编码器               |                                                                                                                                                                                                               |
| [IDM-VTON](https://github.com/yisol/IDM-VTON)<br>![GitHub Repo stars](https://img.shields.io/github/stars/yisol/IDM-VTON)<br>                               | 【换装】目前换装效果最好？                          | [ComfyUI-IDM-VTON](https://github.com/TemryL/ComfyUI-IDM-VTON)<br>![GitHub Repo stars](https://img.shields.io/github/stars/TemryL/ComfyUI-IDM-VTON)                                                           |
| [Hyper-SD](https://huggingface.co/ByteDance/Hyper-SD)                                                                                                       | 【生成加速】最新的 State-of-the-Art 扩散模型加速技术之一。 | [Hyper-SD安装方法及工作流](resources/Hyper-SD-in-ComfyUI)<br>[Hyper-SD视频实测](https://www.bilibili.com/video/BV19H4y1N7ha/?vd_source=7351bb1ce0a307c41b60b64ca036a240#reply1053550184)                                  |
| [LayerDiffuse](https://github.com/layerdiffusion/LayerDiffuse)<br>![GitHub Repo stars](https://img.shields.io/github/stars/layerdiffusion/LayerDiffuse)<br> | 【生成带透明信息图片】使用潜在透明度的透明图像层扩散             | [ComfyUI-layerdiffuse](https://github.com/huchenlei/ComfyUI-layerdiffuse)<br>![GitHub Repo stars](https://img.shields.io/github/stars/huchenlei/ComfyUI-layerdiffuse)                                         |
| [BasicPBC](https://github.com/ykdai/BasicPBC)<br>![GitHub Repo stars](https://img.shields.io/github/stars/ykdai/BasicPBC)<br>                               | 【漫画上色】                                 |                                                                                                                                                                                                               |

## 其他用户界面UI、集合怪

| [InvokeAI](https://github.com/invoke-ai/InvokeAI)<br>![GitHub Repo stars](https://img.shields.io/github/stars/invoke-ai/InvokeAI)<br> | 【AI绘画全套解决方案】有画布功能，可以边画边生成，对专业一些的人来说非常适合的。                | [invoke官方模型库](https://models.invoke.ai/)<br>[invoke官网](https://www.invoke.com/) |
| ------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------- | ------------------------------------------------------------------------------- |
| [Fooocus](https://github.com/lllyasviel/Fooocus)                                                                                      | 前瞻版[mashb1t-Fooocus](https://github.com/mashb1t/Fooocus) |                                                                                 |
| [pinokio](https://pinokio.computer/)                                                                                                  | 一键安装、运行、管控各类AI项目                                         |                                                                                 |
| [SwarmUI](https://github.com/mcmonkeyprojects/SwarmUI)                                                                                | 模块化的Stable Diffusion Web用户界面                             |                                                                                 |

## 其他（TTS、RVC、换脸）

| [facefusion](https://github.com/facefusion/facefusion)<br>![GitHub Repo stars](https://img.shields.io/github/stars/facefusion/facefusion)<br>                                                      | 作者自认为是“下一代换脸工具”                                                                                                                                                                                                                      |
| -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| [RVC变声](https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI)<br>![GitHub Repo stars](https://img.shields.io/github/stars/RVC-Project/Retrieval-based-Voice-Conversion-WebUI)<br> | RVC，我视频用的变声器，(#^.^#)。[下载地址](https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/releases)贴心的百度网盘，解压即用！                                                                                                             |
| [ChatTTS](https://github.com/2noise/ChatTTS)<br>![GitHub Repo stars](https://img.shields.io/github/stars/2noise/ChatTTS)<br>                                                                       | 文字转语言，主打一个拟人，[ChatTTS-ui](https://github.com/jianchang512/ChatTTS-ui)webUI版很好<br>[pyvideotrans](https://github.com/jianchang512/pyvideotrans)该作者的视频翻译项目（顺便）<br>[ChatTTS-Enhanced](https://github.com/CCmahua/ChatTTS-Enhanced)另一个项目。 |


# 🏆顶级开发者（他们贡献了最棒的custom nodes）

| 开发者                                                           | 简介（主要贡献）                                                                                                                                                                                                                                                                                                                                                                                             |
| ------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| [ZHO-ZHO-ZHO](https://github.com/ZHO-ZHO-ZHO)                 | [BRIA_RMBG 1.4 in ComfyUI](https://github.com/ZHO-ZHO-ZHO/ComfyUI-BRIA_AI-RMBG)：BRIA 开发的目前最好的背景去除模型，已支持批量处理（可去除视频背景）<br>[ComfyUI InstantID](https://github.com/ZHO-ZHO-ZHO/ComfyUI-InstantID): 仅需一张图就可实现高质量的角色保持！多种风格随心变。<br>[ComfyUI-BiRefNet-ZHO](https://github.com/ZHO-ZHO-ZHO/ComfyUI-BiRefNet-ZHO)背景扣除神器。<br>[ComfyUI-Phi-3-mini](https://github.com/ZHO-ZHO-ZHO/ComfyUI-Phi-3-mini)利用本地大语言模型。 |
| [kijai](https://github.com/kijai)                             | [ComfyUI-SUPIR](https://github.com/kijai/ComfyUI-SUPIR)<br>[ComfyUI-BrushNet-Wrapper](https://github.com/kijai/ComfyUI-BrushNet-Wrapper)<br>[ComfyUI-IC-Light](https://github.com/kijai/ComfyUI-IC-Light)<br>                                                                                                                                                                                        |
| [huchenlei](https://github.com/huchenlei)                     | [ComfyUI-layerdiffuse](https://github.com/huchenlei/ComfyUI-layerdiffuse)<br>[ComfyUI_omost](https://github.com/huchenlei/ComfyUI_omost)                                                                                                                                                                                                                                                             |
| [lllyasviel](https://github.com/lllyasviel)                   | [Fooocus](https://github.com/lllyasviel/Fooocus)<br>[stable-diffusion-webui-forge](https://github.com/lllyasviel/stable-diffusion-webui-forge)<br>[ControlNet](https://github.com/lllyasviel/ControlNet)<br>[IC-Light](https://github.com/lllyasviel/IC-Light)                                                                                                                                       |
| [ltdrdata](https://github.com/ltdrdata)<br>                   | [ComfyUI-Manager](https://github.com/ltdrdata/ComfyUI-Manager)<br> [ComfyUI-Impact-Pack](https://github.com/ltdrdata/ComfyUI-Impact-Pack)                                                                                                                                                                                                                                                            |
| [HumanAIGC](https://github.com/HumanAIGC)<br>阿里               | 阿里的开源项目<br>[EMO](https://github.com/HumanAIGC/EMO)：情感肖像活灵活现<br>[AnimateAnyone](https://github.com/HumanAIGC/AnimateAnyone)：有了这个谁都可以跳科目三<br>[OutfitAnyone](https://github.com/HumanAIGC/OutfitAnyone)：换装，在线演示：[OutfitAnyone demo](https://huggingface.co/spaces/HumanAIGC/OutfitAnyone)<br>                                                                                                           |
| [TencentARC](https://github.com/TencentARC)<br>腾讯             | [PhotoMaker](https://github.com/TencentARC/PhotoMaker)<br>[T2I-Adapter](https://github.com/TencentARC/T2I-Adapter)<br>[BrushNet](https://github.com/TencentARC/BrushNet)局部重绘很顶！                                                                                                                                                                                                                      |
| [PKU-YUAN-Lab (袁粒课题组-北大信工)](https://github.com/PKU-YuanGroup) | [Open-Sora-Plan](https://github.com/PKU-YuanGroup/Open-Sora-Plan)北大出手还是牛。<br>[MagicTime](https://github.com/PKU-YuanGroup/MagicTime)<br>comfyui：[ComfyUI-MagicTimeWrapper](https://github.com/kijai/ComfyUI-MagicTimeWrapper)                                                                                                                                                                        |

# ⬇️工作流、模型下载，社区交流、Youtube大佬

| 网址                                                              | 说明                                                                                      |     |
| --------------------------------------------------------------- | --------------------------------------------------------------------------------------- | --- |
| [OpenArt](https://openart.ai/workflows)                         | 【工作流分享】很多大佬分享了海量的高质量工作流。                                                                |     |
| [civitai](https://civitai.com/)                                 | 【模型、工作流等】搜索、下载和分享各种 AI 绘画模型，最齐全的网站，好像没有之一？                                              |     |
| [Nerdy Rodent](https://www.youtube.com/@NerdyRodent/videos)     | 【Youtube大佬】手把手教你用命令行安装最新的AI项目                                                           |     |
| [Latent Vision](https://www.youtube.com/@latentvision/videos)   | 【Youtube大佬】[ComfyUI_IPAdapter_plus](https://github.com/cubiq/ComfyUI_IPAdapter_plus)的作者 |     |
| [Olivio Sarikas](https://www.youtube.com/@OlivioSarikas/videos) | 【Youtube大佬】做个SD和ComfyUI都能有20万粉丝！                                                        |     |
| [Scott Detweiler](https://www.youtube.com/@sedetweiler)         | 【Youtube大佬】Stability.ai的首席质量保证工程师，内部员工真是排面，他的视频挺好的，但是后面视频全部要收费了。                        |     |

# 🌐图片、视频、音乐、3D模型、数字人…生成网站

| [ideogram](https://ideogram.ai/)                                                                    | 这个网站生成的图片质量不错，可以生成文字。他们的模型也在不断迭代中。                                                                       |
| --------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------- |
| [haiper](https://app.haiper.ai/explore)                                                             | 【生成视频】个人觉得生成的效果比什么[runway](https://runwayml.com/)、[pika](https://pika.art/)要好啊！就是2秒时间太短。                 |
| [suno](https://app.suno.ai)<br>[udio](https://www.udio.com/)<br>[elevenlabs](https://elevenlabs.io) | 【生成音乐、声音】音乐生成界的chatgpt？                                                                                  |
| [heygen主页](https://app.heygen.com/home)<br>[hedra](https://www.hedra.com/)<br>                      | 【heygen】一个云端视频创作平台，提供了视频编辑（**视频翻译**）、AI生成内容（**数字人**）、个性化定制、模板场景库等功能，适合各种背景和技能水平的用户使用。<br>【hedra】音频驱动数字人。 |
| [Tripo3D](https://www.tripo3d.ai/)<br>[rodin](https://hyperhuman.deemos.com/)                       | 【生成3D模型】生成的3D模型效果挺不错的，在不断迭代中。<br>【3D生成】影眸科技，达到商用级别？                                                      |
| [marker](https://github.com/VikParuchuri/marker)                                                    | 【PDF转Markdown】安装简单，效果惊人的好！拿来翻译和分享论文用！                                                                    |

# 💡小技巧

| 技巧                                                                      | 📺视频解说                                                                                                                                                                                                  |
| ----------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **1️⃣**[ComfyUI如何共享模型文件](docs/🔗ComfyUI如何共享模型文件.md)                     | [懒人必学!ComfyUI模型共享设置,省空间又省心!](https://www.bilibili.com/video/BV1Xt42177m8/?vd_source=7351bb1ce0a307c41b60b64ca036a240)                                                                                   |
| **2️⃣**[Windows环境下ComfyUI自定义节点安装指南](docs/Windows环境下ComfyUI自定义节点安装指南.md) | [ComfyUI报错的终极解决方案！](https://www.bilibili.com/video/BV1Up421Q7YA/?vd_source=7351bb1ce0a307c41b60b64ca036a240)                                                                                            |
| **3️⃣**实现翻译自由                                                           | [实现翻译自由](https://www.bilibili.com/video/BV1bs421K7ZX/?spm_id_from=333.999.0.0&vd_source=7351bb1ce0a307c41b60b64ca036a240)                                                                               |
| **4️⃣**huggingface下载加速器-webUI                                           | [huggingface下载加速器-webUI](resources/HuggingFace-Download-Accelerator.zip)👽双击run.bat，然后按住ctrl点击网址即可。如果下载出问题，可以开关下代理，如果反复下载，需要到`C:\Users\c6023\.cache\huggingface\hub`把之前下载的缓存删除一下，然后再重新下载。😂（每个人文件夹不一样哈） |

# 👽ComfyUI快捷键

| 快捷键                       | 说明                              |
| ------------------------- | ------------------------------- |
| Ctrl + Enter              | 将当前图添加到生成队列                     |
| Ctrl + Shift + Enter      | 将当前图添加到生成队列的第一位                 |
| Ctrl + Z/Ctrl + Y         | 撤销/重做                           |
| Ctrl + S                  | 保存工作流                           |
| Ctrl + O                  | 加载工作流                           |
| Ctrl + A                  | 选择所有节点                          |
| Alt + C                   | 折叠/展开选中的节点                      |
| Ctrl + M                  | 静音/取消静音选中的节点                    |
| Ctrl + B                  | 旁路选中的节点（相当于从图中移除节点并重新连接线路）      |
| Delete/Backspace          | 删除选中的节点                         |
| Ctrl + Delete/Backspace   | 删除当前图                           |
| Space                     | 按住空格键并移动鼠标可以移动画布                |
| Ctrl/Shift + Click        | 将点击的节点添加到选择中                    |
| Ctrl + C/Ctrl + V         | 复制和粘贴选中的节点（不保持与未选中节点输出的连接）      |
| Ctrl + C/Ctrl + Shift + V | 复制和粘贴选中的节点（保持未选中节点输出与粘贴节点输入的连接） |
| Shift + Drag              | 同时移动多个选中的节点                     |
| Ctrl + D                  | 加载默认图                           |
| Q                         | 切换队列的可见性                        |
| H                         | 切换历史记录的可见性                      |
| R                         | 刷新图                             |
| Double-Click LMB          | 打开节点快速搜索面板                      |
对于 macOS 用户，Ctrl 也可以替换为 Cmd