🪴 rhack


Search IconIcon to open search

Stable Diffusion

Last updated Oct 23, 2022

Stable Diffusion is a deep learning, text-to-image model used to primarily generate images based on text descriptions. It’s code and model weights have been released publicly. I’m using it to generate most of the images that I’m using in my digital garden.

Go here and follow the commands.

Before you can run it, go to huggingface.co, sign-up, accept the terms and conditions and download the weights. https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt

Then finally run:


python scripts/txt2img.py --n_samples 1 --n_iter 1 --plms --precision full --H 512 --W 512 --prompt "digital garden. Hyper Detail, 8K, HD, Octane Rendering, Unreal Engine, V-Ray, full hd"

Github repo: https://github.com/magnusviri/stable-diffusion