About us
Stay in touch
Generative models that learn to reverse a process of gradually adding noise: they start from random noise and remove it step by step, guided by a prompt. They power Stable Diffusion, DALL-E 2 and Midjourney.
And now, with latent diffusion models, any style of any object you want is now available to you for just a few pennies and within increasingly slimming seconds.
John Maeda, John Maeda on Computational Evolution