To generate images, diffusion models use a process known as denoising. AI researchers knew by that point that diffusion models take a couple of technical shortcuts when generating images. Mason Kamb (left) and Surya Ganguli found that the creativity in diffusion models is a consequence of their architecture. "As soon as you impose locality, [creativity] was automatic; it fell out of the dynamics completely naturally," he said. "Human and AI creativity may not be so different," said Benjamin Hoover, a machine learning researcher at the Georgia Institute of Technology and IBM Research who studies diffusion models.