Presets
Extract preset from text description
POST
Provide a natural language scene description and use AI to generate style settings as a preset.
token_authheader
AuthorizationBearer <token>Token-based authentication using access tokens.
application/json- body
text*TextNatural language scene description to generate preset from.
Length
length <= 2000type?TypePreset type to generate for.
Default
"flat_2_model"Value in
"flat_2_model""model_swap""identity_creation""create_packshot""garment_recolor"Successful Response
application/json- response
instruction_data*Extracted instruction data in preset format.
suggested_name?|AI-suggested preset name.
Default
nullsuggested_description?|AI-suggested description.
Default
nullfile_id?|UUID of the source asset the preset was extracted from (image mode only).
The client persists this on the preset as instruction_data.reference_asset
so the user can optionally use the original image as an overall reference at
generation time. Null for text extraction.
Default
nullcurl -X POST "https://example.com/preset/extract-from-text" \ -H "Content-Type: application/json" \ -d '{ "text": "string" }'{ "instruction_data": {}, "suggested_name": null, "suggested_description": null, "file_id": null}