Ghost Mannequin AI
Ghost mannequin is the shot every apparel catalog needs and nobody enjoys producing: the garment holding a human shape with no human and no mannequin visible in it. Photographing it properly means a mannequin, two exposures and a retoucher joining them. Here it starts from the product photo you already have, and the same upload can go one step further onto a real model when you want the on-body version too.
How it works
Start from what you shot
A flat lay, a hanger shot or a mannequin frame are all usable inputs. Shoot it square on with even light and the collar, cuffs and hem clearly visible, because those are the edges the shape is rebuilt around.
Give it a body to hold
The garment is rendered with the volume a worn item has: the shoulders squared, the sleeves filled, the hem falling. Nothing is pasted; the item is recomposed with the shape it would take on a person.
Or take it all the way onto a model
The same upload can be shot on a roster model instead, which gives you the on-body image beside the invisible-mannequin one from a single product photo and a single session.
Models you can use right now
Every model below is live on Arteza with its current credit cost, pulled from the same pricing engine the studio uses at generation time.
Nano Banana Pro
Premium Google Gemini 3 Pro image generation
from 3 credits
Seedance 2.0
Cinema-grade AI video with native audio synthesis
from 19 credits
Seedream 5.0 Pro
Flagship deep-thinking image model with on-image text and precise editing
3 credits
Frequently asked questions
What input gives the best ghost mannequin result?
A clean, evenly lit photo of the whole garment with no strong shadows across it, shot straight on. Heavy creases, a garment folded so a seam is hidden, and colour casts from mixed lighting are the three things that most often produce a shape that reads wrong.
Does it handle the inside of a collar or an open jacket?
Those are the hard cases in ghost mannequin work generally, and they are the hard cases here too. Give it a photo where the neckline and any opening are visible rather than flattened shut, and check the result at Final quality before it goes on a product page.
Do I need a mannequin at all?
No. A flat lay is enough. If you already shoot on a mannequin, those frames work as input too and usually give a slightly more accurate shape, because the garment is already holding volume.
Can I do a whole catalog this way?
Yes, and the batch is the reason to. The studio can run one setup across many garments in a single pass, and running that pass in Draft first is how you find a staging problem before it is repeated across the entire catalog.