Hardware and basic software

The example is run on:

• CPU i7-4770K
• 32GB RAM (8GB should be enough)
• Ubuntu 24.04 LTS Server
• Python 3.12 (After a default installation of Ubuntu)

Environment and required libraries

Install virtual environments venv:

sudo apt update
sudo apt install python3-venv -y

Create and run virtual environment:

python3 -m  venv venv-sd
source venv-sd/bin/activate

Installation of required libraries

pip install diffusers torch transformers accelerate

Script

Writing a script to run stable-diffusion sd.py with code:

from diffusers import StableDiffusionPipeline
import torch

# Load model Stable Diffusion
pipe = StableDiffusionPipeline.from_pretrained("CompVis/stable-diffusion-v1-4")  
pipe.to("cpu")  # Forced CPU

# # Description and generate image
prompt = "A skyscraper on a starry night with the moon in the background"
image = pipe(prompt).images[0]  

# Save image on disk
output_path = "generated_image.png"
image.save(output_path)
print(f"Image saved to file {output_path}")

Run:

python3 sd.py

Let's wait a few minutes and see the end result: