installing and running Stable Diffusion on 64-bit Ubuntu 22.04 LTS

https://github.com/CompVis/stable-diffusion/

Does anyone have this working on 64-bit Ubuntu 22.04 LTS? Could you share steps on how to get it working, or just link to a known tested/working guide for same?

From your comment:

I was kinda looking for the "easy button"

A fairly large portion (probably a majority) of Stable Diffusion users currently use a local installation of the AUTOMATIC1111 web-UI. There's an installation script that also serves as the primary launch mechanism (performs Git updates on each launch):

sudo apt install wget git python3 python3-venv # system dependencies
bash <(wget -qO- https://raw.githubusercontent.com/AUTOMATIC1111/stable-diffusion-webui/master/webui.sh)
# Download model file(s) (e.g. Hugging Face account, which does require an account and login) and install into `models/Stable-Diffusion` subdirectory

Full dependencies and optional dependencies are on this page.

This particular repository seems to move at a lightning pace, and has quickly added a number of features with documentation.

Late to the party, but Stable Diffusion 2.1 (base) is just as simple:

from PIL import Image
from diffusers import StableDiffusionPipeline, EulerDiscreteScheduler
import torch

prompt = "Smurf village in summer"
iterations = 100

model_id = "stabilityai/stable-diffusion-2-1-base"

print("Loading model")
scheduler = EulerDiscreteScheduler.from_pretrained(model_id, subfolder="scheduler")
pipe = StableDiffusionPipeline.from_pretrained(model_id, scheduler=scheduler, 
torch_dtype=torch.float16)
pipe = pipe.to("cuda")

image = pipe(prompt, guidance_scale=9, num_inference_steps=iterations).images[0]
image.save("output.jpg", 'JPEG', quality=70)
print("Image saved as output.jpg")

Works like a charm for me, give this a try. Same requirements as stated above:

pip install pillow diffusers torch

I wrote a little prose around this here, but essentially this is what you need to run.

Hope this helps!