xai/rhart-imagine-image-quality/edit-official-stable

POST

/openapi/v2/rhart-imagine-image-quality/edit

Grok Imagine Image Quality Edit is an AI image editing model for commercial visuals and creative retouching. It edits a single input image with natural-language instructions, supports flexible aspect ratios, 1k/2k output tiers, multiple image variations, and common export formats for product imagery, marketing assets, and social media creatives. Official-stable: stable and highly efficient, with pricing lower than purchasing directly from the official model provider.

Request

Authorization

Header Params

Body Params application/jsonRequired

Example

{
    "prompt": "The protagonist is a young woman. Use the precise facial features from the reference image, preserving identity features and natural skin texture. The composition is arranged like a scrolling timeline of memories, captured within overlapping film frames and negatives. Each frame presents a different fleeting emotional moment: laughing while walking, looking out the window, adjusting her hair in the mirror, holding a coffee, and gently captured smiles.",
    "imageUrl": "https://www.runninghub.cn/view?filename=b6c99ef689ab9e1bf57af7ba56b4f51c73431d6230192db28de7d843ad7219c9.png&type=input&subfolder=&Rh-Comfy-Auth=eyJ1c2VySWQiOiI5N2U2NzFjNWNmZDU0NjBhMWZlOWZmYzYyNzg4OTU1ZiIsInNpZ25FeHBpcmUiOjE3Nzk2NzQ3OTY4MzIsInRzIjoxNzc5MDY5OTk2ODMyLCJzaWduIjoiNWI3ZDlkY2RiYmM4MjYxNjlhZWQ5NTI2M2Y2NmI5NzAifQ==&Rh-Identify=97e671c5cfd5460a1fe9ffc62788955f&rand=0.6937836129730577",
    "aspectRatio": "auto",
    "resolution": "1k",
    "numImages": "1",
    "outputFormat": "jpeg"
}

Request Code Samples

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

curl --location 'https://www.runninghub.ai/openapi/v2/rhart-imagine-image-quality/edit' \
--header 'Authorization: Bearer [Your API KEY]' \
--header 'Authorization: Bearer [Your API KEY]' \
--header 'Content-Type: application/json' \
--data '{
    "prompt": "The protagonist is a young woman. Use the precise facial features from the reference image, preserving identity features and natural skin texture. The composition is arranged like a scrolling timeline of memories, captured within overlapping film frames and negatives. Each frame presents a different fleeting emotional moment: laughing while walking, looking out the window, adjusting her hair in the mirror, holding a coffee, and gently captured smiles.",
    "imageUrl": "https://www.runninghub.cn/view?filename=b6c99ef689ab9e1bf57af7ba56b4f51c73431d6230192db28de7d843ad7219c9.png&type=input&subfolder=&Rh-Comfy-Auth=eyJ1c2VySWQiOiI5N2U2NzFjNWNmZDU0NjBhMWZlOWZmYzYyNzg4OTU1ZiIsInNpZ25FeHBpcmUiOjE3Nzk2NzQ3OTY4MzIsInRzIjoxNzc5MDY5OTk2ODMyLCJzaWduIjoiNWI3ZDlkY2RiYmM4MjYxNjlhZWQ5NTI2M2Y2NmI5NzAifQ==&Rh-Identify=97e671c5cfd5460a1fe9ffc62788955f&rand=0.6937836129730577",
    "aspectRatio": "auto",
    "resolution": "1k",
    "numImages": "1",
    "outputFormat": "jpeg"
}'

Responses

🟢200成功

application/json

Task result query endpoint: /openapi/v2/query

Bodyapplication/json

Examples

Submit response exampleTask success response example

{
    "taskId": "2013508786110730241",
    "status": "RUNNING",
    "errorCode": "",
    "errorMessage": "",
    "results": null,
    "clientId": "f828b9af25161bc066ef152db7b29ccc",
    "promptTips": "{\"result\": true, \"error\": null, \"outputs_to_execute\": [\"4\"], \"node_errors\": {}}"
}

Modified at 2026-05-18 12:00:16

xai/grok-imagine-image/edit-official-stable

bytedance/jimeng-4.6/image-to-image