Skip to content

ComfyNodePRs/PR-ComfyUI-MLX-deb3e95c

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

ComfyUI MLX Nodes

Faster workflows for ComfyUI users on Mac with Apple silicon

Installation

  1. First, install the DiffusionKit library:
conda create -n comfy_mlx python=3.11 -y
conda activate comfy_mlx
cd /path/to/your_folder
git clone https://github.com/argmaxinc/DiffusionKit
cd DiffusionKit
pip install -e .
  1. Install the MLX nodes:

Getting Started

A basic workflow is provided to help you start experimenting with the nodes.

Why ComfyUI MLX Nodes?

I started building these nodes because image generation from Flux models was taking too much time on my MacBook. After discovering DiffusionKit on X (Twitter), which showcased great performance for image generation on Apple Silicon, I decided to create a quick port of the library.

The goal is to collaborate with other contributors to build a full suite of ComfyUI custom nodes optimized for Apple Silicon. Additionally, we aim to minimize the reliance on torch to take full advantage of future MLX improvements and further enhance performance.

This will allow ComfyUI users on Mac with Apple Silicon to experience faster workflows.

Contributing

Contributions are welcome! I'm open to best practices and suggestions and you’re encouraged to submit a Pull Request to improve the project. 🙏

Future Plans

  • SDXL models support
  • Loading models from local file
  • Build more MLX based nodes for common workflows
  • Add support for more sampler and scheduler
  • Add sampler and scheduler method

License

ComfyUI MLX Nodes is released under the MIT License. See LICENSE for more details.

Acknowledgements

Support

If you encounter any problems or have any questions, please open an issue in this repository.

About

No description, website, or topics provided.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages