What are diffusion models and why did they dethrone GANs in AI image generation?

The answer

Diffusion models work by learning to reverse a gradual noising process: during training, noise is incrementally added to images until they become pure static, and the model learns to reverse each step. At generation time, the model starts from random noise and iteratively denoises it into a coherent image. First formalized by Sohl-Dickstein et al. in 2015 and made practical by Ho et al. in their 2020 paper on Denoising Diffusion Probabilistic Models (DDPM), diffusion models surpassed GANs in image quality by 2021 while offering more stable training and better mode coverage.