Image-to-image (img2img)
Image-to-image (img2img) is generating a new picture from an existing photo plus instructions, instead of starting from text alone. The input photo anchors composition, pose or identity while the model changes the rest.
Instead of starting from pure noise, img2img starts from your photo and adds a controlled amount of noise to it — then denoises toward your instructions. How much noise is added decides how much survives: a little and only textures change; a lot and only the rough composition remains.
A concrete example: upload a photo of your living room and say "same room, Scandinavian style, oak floors". The walls, windows and perspective hold still while the furniture, materials and light transform.
How Hermosso uses it: Recreate rebuilds any reference photo — one you found on Pinterest, say — with you in it, and the AI Image Editor applies written edits to your own photos. Structure-preserving restyle in The Studio is the same idea taken to its extreme.
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 →