v18

latestOpenAPI 3.1.1raw.githubusercontent.com2026-05-2522769.4 KB
Predictions

Create a new prediction

Submit a prediction request for AI-powered fashion processing. Supports multiple model types including:

  • Try-on max (tryon-max)
  • Virtual try-on v1.6 (tryon-v1.6)
  • Model creation (model-create)
  • Model swap (model-swap)
  • Product to model (product-to-model)
  • Face to model (face-to-model)
  • Background operations (background-remove, background-change)
  • Image reframing (reframe)
  • Image to video (image-to-video)
  • Image editing (edit)
  • Product packshot (packshot)

All requests use the versioned format with model_name and inputs structure.

post/v1/run

Query parameters

webhook_urlstring uri
Example:https://example.com/webhook

Optional webhook URL to receive completion notifications

Request body

OR
OR
OR
OR
OR
OR
OR
OR
OR
OR
OR

Example request

{
  "inputs": {
    "product_image": "https://example.com/garment.jpg",
    "model_image": "https://example.com/model.jpg"
  }
}

Response

Prediction created successfully

idstring required

Unique prediction identifier

errorstring nullable required

Error message if prediction failed to start

Example response

{
  "id": "12345678-1234-5678-9012-123456789012"
}
All 2 operations