📦 Pack workflow environments as an artifact: Saves the workflow environment in a .cpack.zip artifact with Python package versions, ComfyUI and custom node revisions, and model hashes.
✨ Unpack artifact to recreate workflow environments Unpacks the .cpack.zip artifact to recreate the same environment with the exact Python package versions, ComfyUI and custom node revisions, and model weights.
🚀 Deploy workflow as an API: Deploys the workflow as a RESTful API with customizable input and output parameters.

Motivations

We learned from our community that packaging and sharing a ComfyUI workflow is currently difficult due to challenges in reliably replicating the workflow environment. To reliably replicate a workflow elsewhere, one must recreate the environment with the exact python packages, custom nodes revisions, and the identical models. This process can be tedious, error-prone, and time-consuming.

To address this, we built comfy-pack – a tool designed to simplify this process. As a ComfyUI Manager plugin, comfy-pack lets you package an entire workflow with just one click in the UI. Behind the scenes, it automatically locks and records everything you need: Python package versions, custom node revisions, model hashes, and any static assets required for the workflow. All of this is saved into a single .cpack.zip artifact.

The same environment can be recreated by unpacking the .cpack.zip artifact with a simple command:

comfy-pack unpack workflow.cpack.zip

Once this command completes, the environment is fully set up to reliably reproduce the original workflow.

Quick Start

Installation

Search comfy-pack in ComfyUI Manager (Recommended)

or install from Git:

git clone https://github.com/bentoml/comfy-pack.git

Pack a ComfyUI workflow

Click "Package" button to create .cpack.zip
(Optional) select the models that you want to include (only model hash will be recorded)

Unpack a ComfyUI workflow

# Restore a ComfyUI project from cpack files.
comfy-pack unpack workflow.cpack.zip --dir ./

Deploy a workflow as an API

1. annotate input & output

2. serve and test locally

3. (Optional) pack & run anywhere

# Get the workflow input spec
comfy-pack run workflow.cpack.zip --help

# Run
comfy-pack run workflow.cpack.zip --src-image image.png --video video.mp4

4. (Optional) deploy to cloud *

Parameter Nodes

ComfyPack provides custom nodes for standardizing inputs:

ImageInput: provides image type input, similar to official LoadImage node
StringInput: provides string type input, nice for prompts
IntInput: provides int type input, suitable for size or seeds
AnyInput: provides combo type and more input, suitable for custom nodes
ImageOutput: takes image type inputs, similar to official SaveImage node, take an image of a bunch of images
FileOutput: takes file path as string type, save and output the file under that path
...

These nodes help define clear interfaces for your workflow.

Docker Support

Under development

Examples

Check our examples folder for:

Basic workflow packaging
Parameter configuration
API integration
Docker deployment

License

MIT License

Community

Issues & Feature Requests: GitHub Issues
Questions & Discussion: Discord Server

Detailed documentation: under development

README.md Unescape Escape

Comfy-Pack: Package and Deploy ComfyUI Workflow