Diffusion models are a type of generative artificial intelligence (AI) model that uses deep learning techniques to generate images that are artistic, realistic, and often surreal in nature. A famous example of such a model is DALL-E, a 12-billion parameter model created by OpenAI. Diffusion models use a combination of convolutional neural networks and generative adversarial networks to create the images, and are used in applications such as DALL-E, Stable Diffusion, Midjourney, and DiffusionBee.