Flat lay to model

Start a new job

POST
/flat-2-model

This endpoint takes flat/article images (SKUs) and generates Product Detail Page images with the specified model identity wearing the articles.

Unlike model_swap (1 input → 1 output), flat_2_model combines ALL input images and generates multiple outputs based on the instructions list:

  • N input SKU images + M instructions → M output images

Authorization

token_auth
headerAuthorizationBearer <token>

Token-based authentication using access tokens.

Request Body

application/json
  1. body
ai_retouch?Ai Retouch

auto: once the AI reviewer has checked the outputs, the AI retoucher fixes what it flagged on each image, once, without being asked. Each fixed image costs the AI retouch price, charged only when an image is fixed. Enterprise only for now, and not with review_config (images in a review round are retouched from the review screen); otherwise ignored. quality_summary.settled on GET /jobs//results, or the job_quality notification, tells when it is done.

Default"off"
Value in"off""auto"
identity_code*Identity Code

The identity code of the model to use for generating PDP images.

project_id*Project Id

The project identifier where SKU/article images are stored.

images*array<string|>

List of SKU/article image UUIDs or objects with file_id and optional note. Accepts both formats for backward compatibility:

  • Simple: ["uuid-1", "uuid-2"]
  • With annotations: [{"file_id": "uuid-1", "note": "tucked in"}, {"file_id": "uuid-2"}]
Items1 <= items <= 10
instructions?array<>

List of instructions - each instruction produces ONE output image. The number of instructions determines the number of output images (parallel workers). If empty, a single default instruction will be used. Mutually exclusive with template_id.

Items1 <= items <= 10
template_id?|

ID of a saved template to run instead of sending instructions. Each preset in the template becomes one instruction (newest preset first), and the first preset's processing options (engine, post-processing, look, ...) apply unless this request sets them explicitly. Mutually exclusive with instructions.

Defaultnull
post_process?Post Process

Enables or disables post processing for all images in the batch.

Defaultfalse
options?

Global options applied to all instructions (can be overridden per-instruction).

Default{}
review_config?|

Optional review configuration. If provided, creates a review pipeline for this job. Fields: requires_review (bool), default_reviewer_type (str), default_retouch_method (str), auto_approve_threshold (float).

Defaultnull

Response Body

Successful Response

application/json
  1. response
job_id*Job Id

The ID of the created flat-to-model job.

status*Status

The initial status of the job.

message*Message

A message indicating the job creation status.

total_outputs*Total Outputs

Number of output images that will be generated.

curl -X POST "https://example.com/flat-2-model" \  -H "Content-Type: application/json" \  -d '{    "identity_code": "string",    "project_id": "string",    "images": [      "string"    ]  }'
{  "job_id": "string",  "status": "string",  "message": "string",  "total_outputs": 0}