AI engineering glossary · Generative media multimodal
What is DDPM (denoising diffusion probabilistic model)?
Denoising diffusion probabilistic model (also called DDPM): The 2020 formulation of diffusion models (DDPM) that trains a network to predict the noise added at a random step and samples by running a long chain of small denoising steps. It made diffusion competitive with GANs for image quality, though sampling needs hundreds or thousands of steps.
Denoising diffusion probabilistic model: an example
A DDPM trained with 1000 steps produces sharp faces but takes 1000 network evaluations per image, which motivated faster samplers.
Related terms
More Generative media multimodal terms
- Denoising strength
- Diffusion model
- Diffusion sampler
- Diffusion transformer
- Discriminator
- Document understanding
- DreamBooth
- Early fusion
Where you learn it
Denoising diffusion probabilistic model is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.