AI Vocabulary · 01 The Model
What is Diffusion Model?
A generative model that creates images and other media by starting from noise and removing it step by step.
A diffusion model learns in reverse. During training, real images are covered with more and more random noise until nothing is left but static, and the model learns to undo each of those small steps.
To create something new, it starts from pure noise and removes it step by step, guided by your prompt, until an image appears. The same principle is used for video, audio and other media, which makes diffusion models a core technique of generative AI.
Why it matters for you
Because every image starts from different random noise, the same prompt gives a different result each time (non-determinism). The same technique that makes product visuals in seconds also makes convincing deepfakes.
Own it
Check the licence and training data of the image models you use, especially for commercial work, and label AI-generated images where it matters or is required (AI labelling).
Where it comes from
The idea comes from Deep Unsupervised Learning using Nonequilibrium Thermodynamics by Jascha Sohl-Dickstein and colleagues (March 2015), inspired by physics: slowly destroy the structure of data, then learn to restore it. The breakthrough in image quality came with Denoising Diffusion Probabilistic Models by Jonathan Ho, Ajay Jain and Pieter Abbeel (June 2020), which reached state-of-the-art results on a standard image benchmark at the time.
Related
Your AI Learning Hub
Learn the whole AI Vocabulary, step by step, and build with it. Build it. Own it.