Translation: A diffusion model is a type of generative artificial intelligence (AI) that can create content such as images, video, and sound. It produces its output by gradually removing noise from a noisy starting point, similar to tuning a television to remove static until a clear picture appears. The content is gradually generated through this step‑by‑step process, guided by patterns the model learned during training. Diffusion models power many modern AI image‑generation tools.