Home › Research Papers › Denoising Diffusion Probabilistic Models (2020)
Denoising Diffusion Probabilistic Models (2020)
Research Paper
Architecture
The DDPM paper behind every image and video generator.
You're looking at a research-paper record: a landmark paper and what it introduced to the field.
Ho, Jain and Abbeel made diffusion practical for image synthesis, and latent diffusion (Rombach 2022) made it cheap enough for consumer GPUs — the two steps from which Stable Diffusion, Midjourney-class systems, Sora and Veo all follow.
How this connects to the rest of the stack
This record's links at a glance — click a group to jump to it.
Introduced in
Basis for
Sources
Record reviewed as of 2026-01-15 — see Methodology.