Text-to-image
Text-to-image is generating a picture from a written description alone, with no input photo. You type what you want and the model creates it from scratch.
This is the foundational mode of AI image generation: the only input is language. Everything — subject, setting, style, light — has to exist in the prompt or the model invents it. That makes text-to-image unmatched for things that do not exist yet, and weaker when you need a specific real person, product or room preserved.
A concrete example: "a cosy reading nook in a lighthouse at dusk, warm lamp light, rain on the glass" needs no reference photo — the scene never existed, so there is nothing to preserve.
How Hermosso uses it: the Image Creation studio and Create run 19 models across 20 engines from one prompt box, so you can fire the same sentence at several engines and keep the best. When you do have a photo to preserve, that is image-to-image.
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 →