Multimodal AI

Product Scene Variations API

Generate multiple ecommerce scene variants from a product image, optional segmentation, and prompt guidance.

post/api/skill-api/v1/skills/product-scene-variations/run

Request

  • Base URL: https://api.nexscope.ai
  • URL: https://api.nexscope.ai/api/skill-api/v1/skills/product-scene-variations/run
  • Auth: HTTP bearer

Headers

X-Nexscope-Http-Status'legacy' | 'semantic'

Use semantic for HTTP error statuses on run and task-result requests. Without this header v1 retains legacy status behavior. The JSON envelope is unchanged; code 0 means success or acceptance, not asynchronous completion.

Request body

imageUrlstring required

Public URL of the product image. The image must be up to 20 MB and between 385 and 8192 pixels in both width and height.

segImageUrlstring

Optional segmentation mask URL.

strengthnumber

Variation strength from 0.1 to 1. Defaults to 0.5.

promptstring

Scene generation prompt, up to 600 characters.

imageOutputWidthinteger

Desired output width in pixels, from 32 to 2048.

imageOutputHeightinteger

Desired output height in pixels, from 32 to 2048.

outputNuminteger

Number of images to generate, from 1 to 4.

Example request

{
  "imageUrl": "https://example.com/product.jpg",
  "segImageUrl": "https://example.com/mask.png",
  "strength": 0.5,
  "prompt": "modern kitchen countertop",
  "imageOutputWidth": 1024,
  "imageOutputHeight": 1024,
  "outputNum": 1
}

Response

Successful response.

codeinteger required

0 means accepted or successful; nonzero is a platform error.

msgstring nullable required
tsstring required

Epoch milliseconds.

timestring required

Server local time: yyyy-MM-dd HH:mm:ss.

coststring required

Elapsed milliseconds, never credits; -1 outside web requests.

traceIdstring nullable required

Changes

No recorded changes to this operation across all 1 revision of this API.