liveBook · Manning

Denoising

As explained in Local Image Generation

The process of removing noise from a data representation to recover or produce structured content.

Denoising removes what a model believes is noise from an image representation. In Stable Diffusion, the prompt helps distinguish meaningful structure from unwanted variation. section 4.2.1

The useful trick is to start with pure noise. The model removes a little noise at a time, guided by the prompt, until recognizable content emerges. It is image-making by repeatedly finding shapes in a cloud of static. section 4.2.1

The workflow has a few moving parts:

  • A U-Net predicts what the noise in the current image representation should be. section 5.0
  • The prompt guides the prediction toward content such as a tree at night, rather than merely producing a cleaned-up image. section 4.2.1
  • Repeated sample steps gradually move the result toward the requested image. section 4.2.1
  • A sampler controls how much noise disappears at each step, while a scheduler determines the step size. section 6.0

From static to structure

Give Stable Diffusion random noise and the prompt “a tree at night.” Early passes find a rough silhouette; later passes develop features such as branches and other details. section 4.2.1

How Local Image Generation covers it

How deep it goes
Explains prompt guidance, U-Net prediction, iterations, samplers, and schedulers without detailing their internal mathematics.
Examples
Uses random noise, a tree-at-night prompt, cloud imagery, and iterative sample steps as concrete illustrations.
What you can do after
Operate Stable Diffusion by adjusting sample steps, samplers, and schedulers to influence generated images.
How it connects
Links denoising to diffusion models, prompts, U-Nets, checkpoints, samplers, schedulers, and image generation.

Also explained in

Compare how 9 books explain denoising →

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Local Image Generation. The section links point to the parts of the book it draws on.