What are Diffusion Models? | Stanford HAI
Stanford
University
  • Stanford Home
  • Maps & Directions
  • Search Stanford
  • Emergency Info
  • Terms of Use
  • Privacy
  • Copyright
  • Trademarks
  • Non-Discrimination
  • Accessibility
© Stanford University.  Stanford, California 94305.
Skip to content
  • About

    • About
    • People
    • Get Involved with HAI
    • Support HAI
    • Subscribe to Email
  • Research

    • Research
    • Fellowship Programs
    • Grants
    • Student Affinity Groups
    • Centers & Labs
    • Research Publications
    • Research Partners
  • Education

    • Education
    • Executive and Professional Education
    • Government and Policymakers
    • K-12
    • Stanford Students
  • Policy

    • Policy
    • Policy Publications
    • Policymaker Education
    • Student Opportunities
  • AI Index

    • AI Index
    • AI Index Report
    • Global Vibrancy Tool
    • People
  • News
  • Events
  • Industry
  • Centers & Labs

What are Diffusion Models?

Diffusion Models are a type of generative model that creates new content like images by adding and then subtracting “noise.” For example, an image generator would take a real image and slowly add random pixels until they become pure static and unrecognizable, then reverse this process to create a clear, realistic image. The technology is behind AI generators like DALL-E, Midjourney, and Stable Diffusion. 

Navigate
  • About
  • Events
  • Careers
  • Search
Participate
  • Get Involved
  • Support HAI
  • Contact Us

Stay Up To Date

Get the latest news, advances in research, policy work, and education program updates from HAI in your inbox weekly.

Sign Up For Latest News


Diffusion Models mentioned at Stanford HAI

Explore Similar Terms:

Generative AI | GANs (Generative Adversarial Networks) | Deep Learning

See Full List of Terms & Definitions

How to Promote Responsible Open Foundation Models
Kevin Klyman
Oct 03
news

Experts from industry, academia, and government share lessons learned and outline a path forward at a Princeton-Stanford workshop.

How to Promote Responsible Open Foundation Models

Kevin Klyman
Oct 03

Experts from industry, academia, and government share lessons learned and outline a path forward at a Princeton-Stanford workshop.

Machine Learning
news
What DALL-E Reveals About Human Creativity
Gordy Slack
Jan 17
news

The image-generating model has some impressive capabilities that parallel the brain, but is it really creative?

What DALL-E Reveals About Human Creativity

Gordy Slack
Jan 17

The image-generating model has some impressive capabilities that parallel the brain, but is it really creative?

Arts, Humanities
Communications, Media
news
Could Stable Diffusion Solve a Gap in Medical Imaging Data?
Nikki Goth Itoi
Nov 29
news

Stanford AIMI scholars found a way to generate synthetic chest X-rays by fine-tuning the open-source Stable Diffusion foundation model.

Could Stable Diffusion Solve a Gap in Medical Imaging Data?

Nikki Goth Itoi
Nov 29

Stanford AIMI scholars found a way to generate synthetic chest X-rays by fine-tuning the open-source Stable Diffusion foundation model.

news
How Foundation Models Can Advance AI in Healthcare
Jason Fries, Scott Fleming, Michael Wornow, Nigam Shah
Ethan Steinberg, Yizhe Xu, Keith Morse, Dev Dash
Dec 15
news

This new class of models may lead to more affordable, easily adaptable health AI.

How Foundation Models Can Advance AI in Healthcare

Jason Fries, Scott Fleming, Michael Wornow, Nigam Shah
Ethan Steinberg, Yizhe Xu, Keith Morse, Dev Dash
Dec 15

This new class of models may lead to more affordable, easily adaptable health AI.

Healthcare
news

Enroll in a Human-Centered AI Course

This HAI program covers technical fundamentals, business implications, and societal considerations.