comfy-ui 开源项目推荐（98 个）

ATH-MaaS /ComfyUI-Copilot

一个为 ComfyUI 设计的 AI 驱动自定义节点，旨在增强工作流自动化并提供智能辅助

replicate /comfyui-replicate

Run Replicate models as nodes in ComfyUI

StableCanvas /comfyui-client

all ComfyUI http/ws APIs. support NodeJS / Browser environments. and advanced programmable workflow.

chanon /comfyui-obvpm

ComfyUI nodes to save time and keep your workflows tidy. Bundle multiple wires into one wire. Create customizable presets nodes.

phineas-pta /comfyui-auto-nodes-layout

apply better nodes layout algorithm to ComfyUI workflow

anxety-solo /sdAIgen

A1111，ComfyUI，Forge，Forge-Classic/Neo，ReForge，SD-UX - 一本适用于 Google Colab 和 Kaggle 的笔记本

bradsec /ComfyUI_StringEssentials

ComfyUI 的简单字符串操作节点（去除文本字符串，搜索和替换文本字符串，字符串布尔检查，预览修改后的字符串输出）。对于修改LLM输出的提示或文本非常有用。

mobcat40 /ComfyUI-PromptChain

A visual prompt engineering toolkit for ComfyUI. Chain prompts together, see what fires, lock what works.

ComfyUI-Kelin /ComfyUI-LLMs-Toolkit

ComfyUI custom nodes for DeepSeek, Qwen, GPT, and other OpenAI-compatible LLM APIs, with tools for chat, translation, vision, and JSON workflows.

vslinx /ComfyUI-vslinx-nodes

Custom ComfyUI nodes to streamline and speed up workflows: multi-select and last-image loaders, pixel-art, model upscaling, batched VAE decode and a per-segment detailer; boolean AND/OR/NOT plus bypass/mute, pipe and bookmark nodes for clean branching; BBox-mask compositing; an rgthree-LoRA to Image-Saver bridge; and model-loader previews.

bradsec /ComfyUI_ResolutionSelectorPlus

Custom node for ComfyUI providing easy resolution and empty latent selection for image generation workflows.

Virgile-fr /ShrinkComfy

缩小你的 ComfyUI PNG 图像，同时保留其中的工作流。

StableCanvas /StableCanvas

👩‍🎨 StableCanvas is a professional AI drawing editor, aimed at providing a more suitable creative experience for AI painting. No download or installation required, start instantly in your browser, making the AI-driven image creation process more efficient and streamlined.

Lex-DRL /ComfyUI-BestResolution

ComfyUI [UX/QoL] nodes for semi-automatic calculation of the best (most optimal) resolution.

badgids /ComfyUI-H3-ExactAudioLock

ComfyUI custom nodes for deterministic multi-speaker timed audio mixing and exact MiniMax H3 target-audio latent locking.

kantan-kanto /ComfyUI-MultiModal-Prompt-Nodes

Multimodal prompt generator nodes for ComfyUI, designed to generate prompts for QwenImageEdit and Wan2.2. Supports local LLM / local GGUF models (Qwen2.5-VL, Qwen3-VL, Qwen3.5, Qwen3.6 and Qwen3.8) and Qwen API for image and video prompt generation and enhancement.

Majika007 /MaPic

MaPic is a Image Viewer with AI Metadata Reader

weisiren000 /comfyui-jimeng-api

这是一个插件用来调用即梦生图API的插件，顺便能够通过OSC协议沟通等TouchDesigner可视化程序

muerrilla /ComfyUI-Colorcraft

Node pack for ComfyUI + extension for Forge Neo providing an extensive color grading toolset for latents

vavo /LTX2.5-serverless

LTX 2.5 serverless worker template with i2v t2v workflows and bundled frontend.