Nodes Browser
ComfyDeploy: How ComfyUI Model Downloader works in ComfyUI?
What is ComfyUI Model Downloader?
This node allows downloading models directly within ComfyUI for easier use and integration.
How to install it in ComfyDeploy?
Head over to the machine page
- Click on the "Create a new machine" button
- Select the
Edit
build steps - Add a new step -> Custom Node
- Search for
ComfyUI Model Downloader
and select it - Close the build step dialig and then click on the "Save" button to rebuild the machine
Model Downloader for ComfyUI
Introduction
This project provides an experimental model downloader node for ComfyUI, designed to simplify the process of downloading and managing models in environments with restricted access or complex setup requirements. It aims to enhance the flexibility and usability of ComfyUI by enabling seamless integration and management of machine learning models.
Screenshot
Features
- Easy Model Downloading: Simplify the process of downloading models directly within the ComfyUI environment.
- Repositories: Currently only supports hugging face and CivitAI.
- User-friendly: Designed with a focus on ease of use, making model management accessible to users of all skill levels.
Installation
If you have ComfyUI Manager, you can just search for it as we're part of their repository.
Alternatively, you can clone the repository or download the extension directly into your ComfyUI project's custom_nodes
folder:
git clone https://github.com/ciri/model-downloader-comfyui.git
Alternatively use ComfyUI Manager and install via "Install via Git URL".
Usage
To use the model downloader within your ComfyUI environment:
- Open your ComfyUI project.
- Find the
HF Downloader
orCivitAI Downloader
node. - Configure the node properties with the URL or identifier of the model you wish to download and specify the destination path.
- Execute the node to start the download process.
- To avoid repeated downloading, make sure to bypass the node after you've downloaded a model.
Support
For support, questions, or contributions, please open an issue on the GitHub repository page. Contributions are welcome!