Portable Package

The portable package is a pre-built, self-contained version of the open-source ComfyUI release from GitHub. Download it, extract it, and run it without installing system Python.

This guide is for the Windows Portable Package from the ComfyUI GitHub releases page. It is not the same thing as the ComfyUI Desktop app, which has its own installer, app-managed folders, and update path. See How to Install ComfyUI Desktop on Windows if you are using Desktop.

Official ComfyUI releases change often. Use the release page as the source of truth for the current asset names and supported CUDA/Python combinations.

Step 1: Download

Go to the ComfyUI GitHub releases page and download the portable package that matches your hardware.

Current release assets usually follow this pattern:

• ComfyUI_windows_portable_nvidia.7z - NVIDIA GPU default package
• ComfyUI_windows_portable_nvidia_cu126.7z - NVIDIA CUDA 12.6 package, useful for older NVIDIA GPUs
• ComfyUI_windows_portable_amd.7z - AMD Windows portable package when available
• ComfyUI_windows_portable_intel.7z - experimental Intel Windows portable package when available

The file is usually around 1-2 GB.

Step 2: Extract

1. Right-click the downloaded .7z file.
2. Select 7-Zip -> Extract to "ComfyUI_windows_portable/".
3. Wait for extraction to complete.

If extraction fails: Right-click the .7z file -> Properties -> check Unblock at the bottom -> click Apply, then try again.

Path rules:

• Choose a location with enough free space for models, outputs, and custom nodes.
• Avoid spaces and special characters in the path when possible.
• Do not extract to system folders like C:\Program Files, C:\Windows, or the C:\ root.
• Do not run ComfyUI as Administrator unless you intentionally installed it in a protected system path.
• Keep the path short to avoid Windows path-length issues. See Long Paths fix.

Step 3: Download a Model

Before you can generate images, you need at least one checkpoint model. Download one and place it in the correct folder:

ComfyUI_windows_portable/
+-- ComfyUI/
    +-- models/
        +-- checkpoints/    <- Put your .safetensors file here

Popular starter models:

• SD 1.5 - fast, low VRAM, huge community
• SDXL - higher quality, needs more VRAM
• Flux Schnell - newer generation, needs more VRAM and disk space

See Download Models for download links and details.

Step 4: Run

Double-click the appropriate batch file in your extracted portable root.

If you downloaded a dedicated AMD or Intel portable asset, follow the batch files and notes included in that extracted package. Do not copy commands from another portable package without checking the files in your own folder.

A console window will open showing startup logs. Once you see:

Starting server
To see the GUI go to: http://127.0.0.1:8188

Open http://127.0.0.1:8188 in your browser.

Folder Structure

Your folder name can be different. What matters is the relationship: python_embeded, ComfyUI, update, and the run_*.bat files are siblings in the extracted portable root.

ComfyUI_windows_portable/
+-- python_embeded/          # Bundled Python for this portable package
+-- update/                  # Update scripts
|   +-- update_comfyui.bat
|   +-- update_comfyui_stable.bat
+-- ComfyUI/
|   +-- models/              # AI models
|   |   +-- checkpoints/     # Main models (.safetensors)
|   |   +-- loras/           # LoRA files
|   |   +-- vae/             # VAE files
|   |   +-- controlnet/      # ControlNet models
|   |   +-- upscale_models/  # Upscaler models
|   |   +-- clip/            # CLIP models
|   +-- custom_nodes/        # Community plugins
|   +-- input/               # Input images for img2img
|   +-- output/              # Generated images
|   +-- extra_model_paths.yaml
+-- run_nvidia_gpu.bat
+-- run_cpu.bat

If a guide says to run .\python_embeded\python.exe, it means from this portable root, not from inside the ComfyUI\ subfolder.

Updating

To update ComfyUI portable:

1. Open the update/ folder inside the portable directory.
2. Double-click update_comfyui.bat or update_comfyui_stable.bat.
3. Wait for the update to complete.
4. Restart ComfyUI.

Use dependency update scripts carefully. They can reinstall many Python packages and may break custom nodes that depend on specific versions. If an update fails, the UI looks old, or you need to roll back to a stable folder, see ComfyUI Won't Update or Need to Downgrade.

Sharing Models With A1111 / Forge

If you already have models from other AI tools, you do not need to download them again.

Method 1: extra_model_paths.yaml

Edit ComfyUI/extra_model_paths.yaml to point to your existing model folders:

a111:
  base_path: D:/stable-diffusion-webui/

  checkpoints: models/Stable-diffusion
  vae: models/VAE
  loras: models/Lora
  upscale_models: models/ESRGAN
  controlnet: models/ControlNet

Restart ComfyUI after saving.

Method 2: Symbolic Links

If you want ComfyUI to use an existing model folder directly, you can create a Windows symbolic link:

mklink /D "ComfyUI\models\checkpoints" "D:\my-models\checkpoints"

This makes ComfyUI see models in D:\my-models\checkpoints as if they were in its own folder, without duplicating files.

Troubleshooting

Adding Launch Arguments

To add flags like --lowvram, edit the .bat file with a text editor. Find the line with main.py and add your flags:

.\python_embeded\python.exe -s ComfyUI\main.py --lowvram

Common flags:

Next Steps

• Generate your first image
• Download models
• Where to Put Safetensors in ComfyUI
• Install custom nodes
• ComfyUI Won't Update
• ComfyUI Multi GPU
• Troubleshoot common issues

Source References

• ComfyUI GitHub releases
• ComfyUI GitHub README