P-Image Try-On
Pruna's P-Image Try-On virtually fits one or more garments onto a person's photo. Provide a photo of a person plus garment reference images and the model realistically dresses the person in the provided garments.
Quick start
# Inspect the price — a plain request returns the 402 challenge:
curl -i https://api.glianalabs.com/v1/infer \
-H "content-type: application/json" \
-d '{
"model": "pruna/p-image-try-on",
"prompt": <string>
}'
# Pay + run in one step with the mppx CLI (create a wallet: npx mppx account create):
npx mppx https://api.glianalabs.com/v1/infer \
-J '{"model": "pruna/p-image-try-on", "prompt": "<string>"}'Examples
Parameters
Garment reference images to fit onto the person. Each entry is an HTTP(S) URL or a base64 data URI. Up to 6 recommended, up to 11 supported.
Format of the saved output image.
Quality for jpg/webp outputs, from 0 to 100.
Image of the person to dress. A publicly reachable HTTP(S) URL or a base64 data URI (data:image/...;base64,...). Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url.
Return the output at the original input resolution.
Experimental guidance for non-flatlay garment images, e.g. which garment from which image to use.
Optional reference pose image (HTTP(S) URL or data URI). When provided, the person is reposed to match this reference before virtual try-on. Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url.
Random seed. Leave unset for a random seed.
Run faster with additional optimizations. Not recommended for more than 4 garments.