A web-based creative engine for generating and editing images with Stable Diffusion and other AI models, featuring a unified canvas and node-based workflows.
28.8K3.1KTypeScriptApache-2.0Updated 8 hours ago
rgthree/rgthree-comfy
A collection of custom nodes and quality-of-life improvements for ComfyUI, the node-based Stable Diffusion interface.
- Stars
- 3,603
- Forks
- 278
- Open issues
- 313
- Last commit
- 16 days ago
What is it?
rgthree-comfy is a set of custom nodes and interface improvements for ComfyUI, the node-based interface for Stable Diffusion image generation. It installs as a ComfyUI custom node extension by cloning the repository into the custom_nodes directory.
The nodes target workflow tidiness and speed. They include a seed control that works like Automatic1111's, a Power Lora Loader that loads multiple LoRAs in one compact node, prompt nodes with dropdowns for embeddings and LoRAs, and switches that pass along the first non-empty input so disabled branches skip execution. Mute and bypass helpers let users toggle many nodes or groups from one control panel.
The project also adds a progress bar, a right-click option to queue selected output nodes, and a link fixer at a local /rgthree/link_fixer page for repairing broken connections in saved workflows. Most features are configurable from the rgthree-comfy settings panel.
Key features
- 01Seed control node that accepts -1 for random seeds and stores the seed in image metadata.
- 02Power Lora Loader loads multiple LoRAs in a single condensed node with per-LoRA toggles.
- 03Context and Context Switch nodes pass grouped data through a workflow and pick the first non-empty input.
- 04Fast Muter, Fast Bypasser and Mute/Bypass Repeater nodes toggle many nodes from one control.
- 05Power Prompt nodes offer dropdowns for embeddings and LoRAs plus saved prompt snippets.
- 06Link Fixer page repairs broken connections in saved workflow JSON or images.
Use cases
- Running ComfyUI workflows that branch into previews and full upscales without wasting GPU time.
- Stacking several LoRAs in one compact node while adjusting each one's strength.
- Organizing a large SDXL workflow with groups that can be muted or bypassed in one click.
- Repairing workflows that load with missing or broken links.
Quick start
- 1
Install ComfyUI from its GitHub repository
- 2
Go to the ComfyUI custom_nodes folder
cd ComfyUI/custom_nodes - 3
Clone the rgthree-comfy repository into custom_nodes
git clone https://github.com/rgthree/rgthree-comfy.git - 4
Start up ComfyUI
Things to know
- Built by the author for their own workflow, so behavior may not match general expectations.
- Some nodes are deprecated, such as Lora Loader Stack.
In collections
Topics
FAQ
- What is rgthree-comfy?
- A collection of custom nodes and quality-of-life improvements for ComfyUI, the node-based Stable Diffusion interface. rgthree-comfy is a set of custom nodes and interface improvements for ComfyUI, the node-based interface for Stable Diffusion image generation. It installs as a ComfyUI custom node extension by cloning the repository into the custom_nodes directory.
- Is rgthree-comfy free to use? What license does it have?
- rgthree-comfy is open source under the MIT license. Check the license terms before using it in commercial products.
- Is rgthree-comfy still maintained?
- Actively maintained. The last commit to rgthree-comfy was on Oct 6, 2026.
- What can I use rgthree-comfy for?
- Running ComfyUI workflows that branch into previews and full upscales without wasting GPU time. Stacking several LoRAs in one compact node while adjusting each one's strength. Organizing a large SDXL workflow with groups that can be muted or bypassed in one click. Repairing workflows that load with missing or broken links.
- How do I install rgthree-comfy?
- Install ComfyUI from its GitHub repository Go to the ComfyUI custom_nodes folder: cd ComfyUI/custom_nodes Clone the rgthree-comfy repository into custom_nodes: git clone https://github.com/rgthree/rgthree-comfy.git Start up ComfyUI
- Where can I get rgthree-comfy?
- The source code and installation instructions are on GitHub: https://github.com/rgthree/rgthree-comfy
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
Open-source studio and portable .char file format for keeping AI characters consistent across image and video models, locally or via hosted APIs.
56275PythonGPL-3.0Updated 6 days ago
Desktop AI art engine that combines a node graph, specialized editors and a 3D director stage for generating short-video, game and advertising assets, with local-first model access.
24133TypeScriptOtherUpdated 9 hours ago
A Blender add-on that generates textures, concept art and images from text prompts using Stable Diffusion, running locally on your machine.
8.2K437PythonGPL-3.0Updated last month
A Krita plugin that brings generative AI image creation, inpainting and outpainting into your painting workflow, backed by a local or cloud ComfyUI server.
10.8K645PythonGPL-3.0Updated 19 days ago
Desktop package manager and inference UI that installs, updates and launches many Stable Diffusion web UIs such as ComfyUI, Forge and Fooocus.
8.9K613C#AGPL-3.0Updated 2 days ago