A type of generative model that learns to create data (typically images) starting from random noise and progressively refining it through successive steps until it produces an output consistent with the input prompt.
In GENAI-L and AIF-C01 (Domain 1) it is mentioned as the architecture behind image generation models (such as Google's Imagen or Stable Diffusion), in contrast to the Transformer architecture used by text LLMs.
Diffusion model is a concept that can show up on the exam. Check the full guide to see it in context.