Sign in

Nodes Browser

ComfyDeploy: How ComfyLab Pack works in ComfyUI?

What is ComfyLab Pack?

Nodes: XY Plot with many options, Output Config (JSON / JSON5 / YAML), Queue, Format String, List utilities, Input nodes, ....

How to install it in ComfyDeploy?

Head over to the machine page

  1. Click on the "Create a new machine" button
  2. Select the Edit build steps
  3. Add a new step -> Custom Node
  4. Search for ComfyLab Pack and select it
  5. Close the build step dialig and then click on the "Save" button to rebuild the machine
<p align="center"> <img src="static/repo_banner.png" title="welcome to ComfyLab Pack!"> <br/> <span>A collection of carefully experimented nodes, to improve your Comfy UX.</span> </p> <h2 align="center"><a href="#️news">News</a> &nbsp; | &nbsp; <a href="#️node-overview">Node overview</a> &nbsp; | &nbsp; <a href="#documentation">Documentation</a> | &nbsp; <a href="#installation">Installation</a></h2>

News

Latest additions:

  • 2025-01-29 - v0.0.5:
    • new List utility nodes: Random Seeds / Checkpoints / LoRAs / Samplers/ Schedulers
    • reorganize / improve wiki

Full changelog in the dedicated file.

Node overview

The complete list of nodes can be found in the wiki / node list

XY Plot - build beautiful and unique grids

Auto-queue, make virtually anything vary (checkpoints, LoRAs, ...), not restricted to KSampler, ...
Many configuration options: pagination, page header / footer, custom fonts (even your own), background,...
Make it RGBA and add a custom background image for a very unique look.

<details> <summary><strong>Detailed features</strong> <i>(click to show)</i></summary>
  • simple to use by default: only 2 nodes
    • optional configuration nodes to customize the grid, or the page header / footer
    • with possible pagination, row / column switch
  • auto-queuing (very simple to use, automatic error / interruption detection)
  • you can virtually make anything vary: CFG, seed, checkpoint / sampler / LoRA / ...
  • not restricted to KSampler: can be adapted to any process generating images
  • many configuration options:
    • custom row/col headers, with string templating
    • font (type / size / color)
      • in row / column headers, and/or page header / footer (each configurable differently)
      • either one of the 4 fonts shipped with the extension, or any other TTF font on your disk
    • background color:
      • make your grid transparent (RGBA) to add a custom background image
    • padding, wrap, ...
  • mix any image resolution / aspect ratio
  • ...
</details>

[!NOTE] For a quick start, it is advised to read the core concepts.
More information in the XY Plot node reference and the dedicated tutorials, from simple to advanced.
You can also check the examples, they will be frequently extended.

Output Config - dynamic outputs from a config file

Use the Output Config nodes to load custom config files, and dynamically create any number of custom outputs, that you can later connect to other nodes before executing the workflow.
Very useful to standardize your workflows, and keep a collection of configurations / test cases separately, share them with others... and many other applications.

<details> <summary><strong>Detailed features</strong> <i>(click to show)</i></summary>
  • any number of outputs, you decide what you need for your speific cases
  • very simple config file, by default, only output: value is needed
  • optionally configure the shape, color, and even the type of each output
  • available in JSON / JSON5 / YAML (with comments if you wish)
  • strictly validated with a JSON Schema, with detailed visual report in case of errors
</details>

[!NOTE] More information in the Output Config node reference and the dedicated tutorials.
You can also check the examples, they will be frequently extended.

Format String - one node to rule them all

Take advantage of the powerful Python string format() method, to build strings using placeholders.
Very useful for many operations: insert / prefix / append, concatenate, pad, truncate, ...
Any number of inputs (credits to @melMass and his comfy_mtb extension for the trick!).
Compatible with integers, floats, booleans.
Exist in 2 flavors: simple string and multiline.

[!NOTE] More information in the Format String node reference and the dedicated tutorials.
You can also check the examples, they will be frequently extended.

Queue - efficient and simple to use

Exist in 3 flavors: Generic, File, Image.
Very simple to use: auto-queuing (with error / interruption detection), no counter to reset or queue size to set.

List utilities - make lists as you want

A set of nodes to create lists (from string, file, individual elements).
Parse and convert strings to integers, floats, ...
Merge / limit lists.

More utilities

Please check the node list.

Documentation

[!TIP] All nodes in this extension has been adjusted with custom tooltips.
By simply moving the mouse pointer over a node or its inputs / widgets / outputs, you can get useful contextual information.

In addition, more detailed information in the wiki:

Installation

Preferred installation method via the ComfyUI Manager: search and install ComfyLab Pack

Manual installation (from the ComfyUI directory):

source venv/bin/activate # adjust to your env
cd custom_nodes
git clone https://github.com/bugltd/ComfyLab-Pack.git
cd ComfyLab-Pack
pip install -r requirements.txt
cd ../..
deactivate
# run ComfyUI as usual