YanWenKun/ComfyUI-Windows-Portable

🎨ComfyUI standalone pack with 40+ custom nodes. | ComfyUI 大号整合包，预装大量自定义节点（不含SD模型）

What it is

ComfyUI‑Windows‑Portable is a ready‑to‑run Windows package that bundles the open‑source ComfyUI visual node‑based interface for Stable Diffusion (and other generative‑AI models) together with a large collection of useful custom nodes and the required Python libraries. All the heavy‑lifting—Python interpreter, compiled extensions, and dozens of extra nodes—is pre‑installed, so you can unzip the archive and start generating images or videos without any manual dependency setup.

Who it’s for

  • Artists, hobbyists, or researchers who want to experiment with ComfyUI on a Windows PC but don’t want to spend time installing Python, compiling native wheels, or hunting down compatible custom nodes.
  • Anyone with an NVIDIA GPU (2018‑series or newer) who needs a plug‑and‑play environment for diffusion‑based image/video generation.

Core features (as described in the README)

Feature What you get
Pre‑installed custom nodes 40+ popular nodes covering performance (e.g., GGUF, RadialAttention), workspace utilities (ComfyUI‑Manager, Image Saver), control‑net extensions, video tools, and more.
Pre‑installed Python packages 300+ packages, including performance‑boosting libraries like SageAttention and xFormers, plus compiled wheels for packages that normally require a build step (e.g., insightface, dlib).
Portable, self‑contained All dependencies are bundled; the package can be placed anywhere (short paths recommended) and run directly via RUN_Launcher.bat.
Model handling Only a few functional models are shipped; you add your own model files under ComfyUI\models\. The launch script also redirects HuggingFace and PyTorch cache folders to the package root for easier management.
Easy updates The built‑in ComfyUI‑Manager button lets you install, update, disable, or uninstall custom nodes without breaking the core environment.
Build your own The repo includes a GitHub Actions workflow that can rebuild the whole package. Fork the repo, run the workflow, and you’ll get a custom “all‑in‑one” zip you can publish yourself.
Advanced options Support for external model directories via extra_model_paths.yaml, optional sandboxing with Sandboxie, and command‑line launch scripts in ExtraScripts.

How to get started (quick‑start steps)

  1. Download the split archive (.7z.001/.002/.003) and the optional models.zip from the releases page.
  2. Extract the first part (.001) with 7‑Zip into a short path like C:\AI\ComfyUI_Windows_portable.
  3. Unzip models.zip into the same folder (skip if you already have the models).
  4. Place your own model checkpoints in ComfyUI\models\.
  5. Run RUN_Launcher.bat. A browser window opens at http://localhost:8188/ showing the ComfyUI UI.
  6. Use the Manager button in the UI to enable/disable the pre‑installed custom nodes as needed.

Why it matters

  • Zero‑setup: Avoid the typical “Python‑version / wheel‑compilation” headaches that often block newcomers from using ComfyUI.
  • Curated ecosystem: The author has already vetted compatibility among 40+ nodes and 300+ packages, reducing the risk of version conflicts.
  • Reproducible environment: Because everything is bundled, the same package works on any Windows machine with a supported NVIDIA GPU, making it ideal for workshops or sharing pipelines.

TL;DR: This repo provides a fully‑packaged, Windows‑only distribution of ComfyUI with a large set of ready‑to‑use custom nodes and pre‑compiled Python dependencies. Download, unzip, drop in your model files, and you’re ready to build AI‑generated images or videos without any manual installation.

Related

  • Project
    Comfy-Org/comfy-cli

    comfy‑cli is a Python CLI that automates installing, launching, and extending ComfyUI – an open‑source generative‑media engine. It lets you install custom node packs, download models, run local or cloud workflows, and call partner image/video models directly from the terminal, with optional JSON output for AI agents.

  • Project
    Tavris1/ComfyUI-Easy-Install

    A portable, one-click installer for ComfyUI on Windows that includes the EZi Desktop management tool to simplify the installation of complex AI packages and environment configuration.

  • Project
    yolain/ComfyUI-Easy-Use

    ComfyUI‑Easy‑Use is a genuine open‑source extension for the ComfyUI node‑based UI, providing dozens of convenience nodes (loaders, prompt tools, LoRA/ControlNet helpers, noise injection, image utilities, logic/loop nodes, etc.) that streamline building Stable Diffusion and other diffusion model workflows. It supports many models (SD‑1/2, SDXL, SD‑3, Flux, Kolors, Stable Cascade, etc.), offers UI theme tweaks, and includes documentation, video tutorials, and a workflow collection. Installation is a simple git clone into ComfyUI’s `custom_nodes` folder followed by running `install.bat`.

  • Project
    Acly/comfyui-tooling-nodes

    A set of ComfyUI custom nodes and API extensions that enable the use of ComfyUI as a backend for external tools, featuring optimized image transfer, regional prompting, and model inspection.

  • Project
    Comfy-Org/ComfyUI-Manager

    ComfyUI‑Manager is a feature‑rich extension for the visual AI workflow tool ComfyUI. It adds a UI button that lets users browse, install, update, enable/disable, and remove custom nodes and model files from the official registry or community channels. The manager also provides snapshot/restore of installation states, one‑click sharing to workflow‑hosting sites, a CLI (`cm‑cli`) for automation, and security‑focused storage of its data. Configuration is handled via a simple `config.ini` and optional pip‑override files. Installation works via manual git clone, portable‑Windows script, `comfy-cli`, or a Linux venv script.