So the first thing you do is a git clone https://github.com/comfyanonymous/ComfyUI. Then cd ComfyUI/custom_nodes. Then issue git clone https://github.com/ltdrdata/ComfyUI-Manager. Last thing to do, navigate to ComfyUI again and issue pip install -r requirements.txt. So I’m skipping some of the PyTorch stuff and that’s important and all, but this is just a real condensed summary that you’re going to have to fill the gaps of. Sorry. I might be too stoned to do a proper doc on it, but it’ll get you pointed in the right direction.

So this is “in the works”, I haven’t succeeded yet. The ultimate goal is to be able to upscale a shitty 70kb jpeg to a megapixel jpeg using trained neural networks. Badass, rite? Well, the disclaimer here is that I’ve been chipping away at this project and haven’t yet got a functioning setup. So without further ado, here’s my fucking trainwreck.

I started off following the guide at alexjc/neural-enhance. My first attempt involved me thinking I was slick and I could just grab the docker container since it’s already installed, configured, and the neural networks trained with more than a few already very usable targets.