Models & Architecture

Diffusion Model

A type of generative model, common in image tools, that creates content by starting from noise and gradually refining it.

A diffusion model learns to reverse a process of adding random noise to data. To generate an image it begins with pure static and removes noise step by step, guided by the prompt, until a coherent picture emerges. This approach powers most leading image and video generators and tends to produce sharper, more controllable results than the earlier GAN-based methods.

Reference: Wikipedia: Diffusion Model