Diffusion model
A diffusion model is the AI architecture behind most modern image generators. It starts from pure random noise and removes it step by step until a picture matching your prompt remains.
Diffusion models are trained on a simple trick: take a real photo, add noise until it is static, and learn to reverse the process. At generation time the model runs that reversal on fresh noise, guided by your prompt — each denoising step moves the image closer to what you described. The number of steps trades speed against detail.
A concrete example: when you type "golden-hour portrait of a chef in a market", the model begins with television static and, over a few dozen steps, resolves a face, then clothing, then light — every step a slightly less noisy version of your sentence.
How Hermosso uses it: most of the 19 models across 20 engines in the Create studio are diffusion models or close descendants — from FLUX 2 Pro to Seedream 5 Pro. You can compare them all on the image models page.
Try it on your own photos
Upload a few selfies, and Hermosso trains a private AI model of you — then generates studio-quality photos in any style. Your first credits are free.
Create your AI photos →