Generative AI models learn patterns from a set of input data during a process called training. During training, the model is shown many examples of the type of content it's supposed to generate. It learns to recognize patterns in this data and uses these patterns to generate new content.
For example, if a generative AI model is trained on a dataset of images of dogs, it will learn what dogs look like and how they vary. Then, when asked to generate a new image of a dog, it will create an image that fits the patterns it learned during training.