latestOpenAPI 3.0.22026-08-21134292561.4 KB
898026c78d68
edit-workflow
Dress a person in one or more garments
Generates a photorealistic image of the person in the supplied photo wearing the supplied garments, preserving their face, body, and background.
The request is processed asynchronously. Poll GET /v1/generations/{generation_id} with the returned generation_id until the generation is completed or failed.
Supply the person as either an AssetIdentifier reference (person_asset_identifier) or the raw image bytes directly (person_image, multipart requests only), and likewise the garments as either garment_asset_identifiers or garment_images. For each of the two sources, provide exactly one of the two forms; supplying both, or neither, is rejected with a 400.
post/v2/workflow/virtual-try-on
Request body
Example request
{
"person_asset_identifier": {
"asset_type": "RESPONSE",
"asset_id": "7uS_VESkRI6O3-sVgHQp_A"
},
"garment_asset_identifiers": [
{
"asset_type": "RESPONSE",
"asset_id": "7uS_VESkRI6O3-sVgHQp_A"
}
],
"webhook_url": "https://api.example.com/webhooks/ideogram"
}Response
Try-on accepted for asynchronous processing.
Example response
{
"generation_id": "generation_id"
}