AI Glossary
Diffusion model
What does “Diffusion model” mean?
Diffusion model: Diffusion models learn to generate data by reversing a noising process. During training, noise is gradually added to real examples; the model learns to remove it step by step, so it can later start from pure noise and refine it into a new image, video or sound.
What is an example of “Diffusion model”?
Stable Diffusion is a well-known image generator built this way. Researchers are also exploring diffusion for text generation.