This is a very broken down version of spacenuko's original ComfyBox concept. "https://github.com/space-nuko/ComfyBox.git"
All credit for the coding goes to them. I have only removed any files that were not integral for running the program on my Windows computer (I cannot say if this will work on other systems such as Linux, Google Colab, etc). If you find out it does, let me know and I'll update the README.md. It is my hope that this will help others to have at least SOMETHING to use. I am not a coder, I only know beginner/intermediate Python, so any features, requests, updates are going to be on the community to figure out. Thank you.
Originial README
A preconfigured workflow is included for the most common txt2img and img2img use cases, so all it takes to start generating is clicking Load Default to load the default workflow and then Queue Prompt.
You can import your existing workflows from ComfyUI into ComfyBox by clicking Load and choosing the .json or .png with embedded metadata, or dropping either file onto the graph viewer.
- No-Code UI Builder - A novel system for creating your own Stable Diffusion user interfaces from the basic components.
- Prompt Queue - Queue up multiple prompts without waiting for them to finish first. Inspect currently queued and executed prompts.
- Prompt History - Browse through previously generated prompts and their output images/parameters.
- Clone/Install ComfyUI for the backend and follow all of their instructions.
- Add the argument "--enable-cors-header" to the "run_nvidia_gpu.bat" file.
- Clone this repo and place it into the "ComfyUI_windows_portable" folder.
- Run start_servers.bet.
- All set!