Skip to navigation
Tools

Ghost Mannequin

Turns photos of one garment into a ghost-mannequin product image on a clean white studio background, removing the person, mannequin, hanger, and other clothing. Upload the photos using multipart/form-data, in the directional fields (such as front_image) when the camera direction is known and in garment_images otherwise. Returns a generation_id; poll GET /v2/generations/{generation_id} or supply a webhook_url.

Authentication

Api-Keystring

API key for access control. Use in the header with the name "Api-Key"

Query parameters

dry_runbooleanOptionalDefaults to false

When true, the request is validated and priced but not run: nothing is generated, stored, or billed, and no safety review is performed. The response is a PriceQuote object instead of the usual response for this endpoint. Send exactly the request you would send to generate, so the quote reflects the same options.

Request

The garment photos and the requested output view.
garment_imagesfilesOptional
Additional photos of the same garment, up to 50 MB each. JPEG, PNG, WEBP, HEIF, AVIF, GIF, BMP, TIFF, and MPO are supported. Multipart requests only.
front_imagefileOptional

Optional front-view garment photo, up to 50 MB. Multipart requests only.

back_imagefileOptional

Optional back-view garment photo, up to 50 MB. Multipart requests only.

left_imagefileOptional

Optional left-view garment photo, up to 50 MB. Multipart requests only.

right_imagefileOptional

Optional right-view garment photo, up to 50 MB. Multipart requests only.

top_imagefileOptional

Optional top-view garment photo, up to 50 MB. Multipart requests only.

bottom_imagefileOptional

Optional bottom-view garment photo, up to 50 MB. Multipart requests only.

viewenumRequired
Camera view for the output garment.
Allowed values:
instructionstringOptional<=2000 characters

Optional reconstruction guidance or identity-critical garment details to check against the photos. The output always uses a clean white studio background.

metadatastringOptional<=8000 characters
Optional JSON object serialized as a string containing factual product context, such as title, brand, category, color, material, item code, and exact printed text. Metadata helps disambiguate the garment photos but does not add features they do not show.
aspect_ratiostringOptionalformat: "^(1:1|3:4|4:3|16:9|9:16)$"

Output aspect ratio. Defaults to 1:1 when omitted. Supported values are 1:1, 3:4, 4:3, 16:9, and 9:16.

qualityenumOptional
The quality tier for the edit. Higher tiers may improve detail and take longer to complete.
Allowed values:
seedintegerOptional0-2147483647
Optional seed for repeatable results.
webhook_urlstringOptionalformat: "uri"<=2048 characters

HTTPS URL that Ideogram delivers the generated result to. Ideogram sends a JSON POST to this URL once all images for the request have finished generating. The body mirrors the synchronous generate response: request_id, created, and a data array containing every generated image (url, prompt, resolution, seed, is_image_safe). Each delivery is signed with Ed25519 and verifiable against the public keys at https://api.ideogram.ai/v1/.well-known/jwks.json. Must be HTTPS; private and loopback hosts and the cloud metadata service are rejected.

Response

Ghost-mannequin generation accepted for asynchronous processing.

generation_idstring

URL-safe base64 ID accepted by the generation polling endpoint.

Errors

400
Bad Request Error
401
Unauthorized Error
402
Payment Required Error
403
Forbidden Error
404
Not Found Error
413
Content Too Large Error
422
Unprocessable Entity Error
429
Too Many Requests Error