---
title: "What Is a Diffusion Model? | ImageQuarry"
url: https://www.imagequarry.com/faq/what-is-a-diffusion-model/
last_updated: 2026-10-20
---

# What is a diffusion model?

A diffusion model is a type of generative AI model that learns to create images by reversing a process that gradually turns training images into noise. When generating, it starts from random noise and removes it step by step until an image matching the prompt appears.

A widely cited 2020 paper, "Denoising Diffusion Probabilistic Models" by Ho, Jain and Abbeel, showed that this method could produce high-quality images. In text-to-image systems, the prompt guides each denoising step toward the picture you described.

Not every current image model is a diffusion model, and model makers do not always publish their architecture. For choosing a tool, the architecture matters less than what a model does well for you: following instructions, keeping details during edits, rendering text and matching a style.

In ImageQuarry you describe the image or the change in plain words and compare the versions that come back.

_Source: Ho, Jain and Abbeel (2020), arXiv. Checked October 20, 2026._

Next step: [Why do different AI models give different results from the same prompt?](https://www.imagequarry.com/faq/why-do-different-ai-models-give-different-results/)

## Related questions

- [Why do different AI models give different results from the same prompt?](https://www.imagequarry.com/faq/why-do-different-ai-models-give-different-results/): Different training and goals produce different pictures.
- [Which AI image model is best?](https://www.imagequarry.com/faq/which-ai-image-model-is-best/): It depends on the task; compare on your own request.
- [What is generative fill?](https://www.imagequarry.com/faq/what-is-generative-fill/): Adobe's selection-based fill in Photoshop.
- [How does text-to-image AI work?](https://www.imagequarry.com/faq/how-does-text-to-image-ai-work/): A model turns a text description into a new image.

Last reviewed 2026-10-20 by ImageQuarry.

## Skip the theory and describe the image

In ImageQuarry, you describe what you want in plain words and refine it version by version.