Start a new job
Takes 1-10 garment-bearing images and produces packshot outputs based on the instructions list (one output per instruction × num_variations). No model identity is involved — outputs are product-only.
token_authAuthorizationBearer <token>Token-based authentication using access tokens.
application/json- body
ai_retouch?Ai Retouchauto: 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.
"off""off""auto"project_id*Project IdThe project identifier where input images are stored.
images*array<string|>List of garment-bearing 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": "front view"}, {"file_id": "uuid-2"}]
1 <= items <= 10instructions?array<>List of instructions — each produces ONE output image (× num_variations).
Each instruction MUST have a style (no default — packshot apps requires explicit style).
Required unless template_id is sent; mutually exclusive with it.
1 <= items <= 10template_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.
nullpost_process?Post ProcessEnables or disables post processing for all images in the batch.
falseoptions?Global options applied to all instructions (can be overridden per-instruction). Notable fields:
- model: "auto" | "nano_banana_2" | "nano_banana_pro" | "seedream"
- use_anchor: bool (default False) — generate instruction 0 first synchronously, then fan out the rest with the anchor as a reference image. Use for cross-style visual consistency (e.g., front + back of the same garment).
- anchor_index: int (default 0) — which instruction is the anchor reference.
{}review_config?|Optional review configuration. If provided, creates a review pipeline.
nullSuccessful Response
application/json- response
job_id*Job IdThe ID of the created create-packshot job.
status*StatusThe initial status of the job.
message*MessageA message indicating the job creation status.
total_outputs*Total OutputsNumber of output images that will be generated.
curl -X POST "https://example.com/create-packshot" \ -H "Content-Type: application/json" \ -d '{ "project_id": "string", "images": [ "string" ] }'{ "job_id": "string", "status": "string", "message": "string", "total_outputs": 0}