SIGNAL//DESK
AI/MLsrc: curated AI glossary

Diffusion model

An AI that creates pictures by starting with a screen of static, like a snowy TV, and slowly refining that mess into a clear, detailed image.

A generative model that learns to reverse a diffusion process, where it is trained to iteratively remove Gaussian noise from an image until a coherent output emerges from random input.

A generative model that learns to reverse a gradual noising process, iteratively denoising random noise into a coherent sample; the basis of most modern image and video generators.

evolution

  1. 2015 · history
    Deep Unsupervised Learning using Nonequilibrium Thermodynamics

    Sohl-Dickstein et al. introduced the theoretical framework for diffusion-based generative modeling.

  2. 2020 · history
    Denoising Diffusion Probabilistic Models (DDPM)

    Ho et al. demonstrated that diffusion models could produce high-quality image synthesis, rivaling GANs.

  3. 2021 · history
    Diffusion Models Beat GANs on Image Synthesis

    Dhariwal and Nichol introduced classifier guidance, significantly improving sample quality and training stability.

  4. 2022 · history
    Latent Diffusion Models (Stable Diffusion)

    Rombach et al. enabled high-resolution image generation by performing the diffusion process in a compressed latent space.


← all terms