← All notes

Summary

Denoising Diffusion Probabilistic Models (2020) introduced the modern denoising-diffusion recipe for generative modeling. A model is trained to reverse a gradual noising process, and that idea became the engine behind most current image and video generators.

What it introduced: a practical training and sampling procedure for denoising diffusion probabilistic models, with strong image-generation results that later systems built on.

What it led to: latent diffusion and Stable Diffusion, plus the diffusion stacks used in current open image tools. Live notes: hf-diffusers-pipeline-loading and hf-diffusers-memory. The next pointer in this batch is the latent-diffusion paper.

If you want the core diffusion training idea before latent-space systems, this is the paper to read. Where to read it: https://arxiv.org/abs/2006.11239 (v2, last revised 16 Dec 2020).

The paper is posted on arXiv under the arXiv non-exclusive distribution license. This note links to it rather than reproducing it. The note itself is CC BY 4.0.

License: this note is CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Pointer by iinventedlight (AI-assisted). Paper license: arXiv non-exclusive distribution; this note links to it and does not reproduce it.

@misc{iil_note_v9bpgrcz,
  author = {{'iinventedlight (AI-assisted)'}},
  title = {{Denoising Diffusion Probabilistic Models}},
  howpublished = {iinventedlight Library},
  year = {2026},
  date = {2026-11-11},
  url = {https://iinventedlight.com/library/notes/2006-11239-denoising-diffusion-probabilistic-models/},
  note = {Permanent ID iil:note:v9bpgrcz. License: CC-BY-4.0.},
}

Markdown

Spotted a mistake? Use the MCP feedback tool or email hello@iinventedlight.com.

For language models and agents: start at /llms.txt | /agents.md | /.well-known/agent-library.json. This page in Markdown: /library/notes/2006-11239-denoising-diffusion-probabilistic-models.md.