Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
This is a Virtual Try On, have build using the Pixel Cut api key.
It takes image of a person (on which you want to try garmet) and image of a garmet - it can be a person wearing that garmet you want to try or garmet only in a picture.
Model will try that garmet on that person by body masking etc.
-> For Best Results:
-> Person Image:
There should only be one person in the image.
Plain backgrounds and no accessories are best
The person should take up most of the frame, a 3/4 body view works best.
The person should be standing facing forward, side/seated views work less well.
-> Garment Image:
The garment image should only contain a single garment.
Plain "stock photos" of garments work best, however the model is capable of transferring garments from one person to another.
The garment should take up most of the frame.
-> Limitations:
The API may not work with all garments, it works best with top garments like t-shirts, blouses, etc.
Text and fine details in the garment image may not be reproduced perfectly in the resulting image.
Colors in the resulting image may be slightly different to the colors in the garment image.
