Getting Started With Stable Diffusion

Youssef Hosni
Towards AI
Published in
12 min readNov 11, 2022

--

Stable Diffusion is a text-to-image latent diffusion model created by researchers and engineers from CompVis, Stability AI, and LAION. It’s trained on 512x512 images from a subset of the LAION-5B database. With stable diffusion, you generate human faces, and you can also run it on your own machine, as shown in the figure below.

Generated images by stable diffusion / Stability.ai

--

--