wan-2.2/image-to-image

POST

/openapi/v2/rhart-video/wan-2.2/image-to-image

The image-to-image transformation model in the Wan-2.2 series, leveraging 14-billion parameter MoE architecture for high-quality image redrawing and style transfer. Supports precise generation control through text prompts, achieving various creative effects including quality enhancement, style conversion, and element replacement while maintaining input image structural information. Employs dual-expert collaborative mechanism to ensure optimal balance between detail richness and semantic consistency, providing designers with an efficient visual iteration tool.

Request

Authorization

Header Params

Body Params application/jsonRequired

Example

{
    "272##image": "example.png",
    "79##text": "Change to an Asian female face",
    "267##select": "1",
    "270##value": 1024,
    "271##value": 1024,
    "242##file_type": "PNG"
}

Request Code Samples

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

curl --location --request POST 'https://www.runninghub.ai/openapi/v2/rhart-video/wan-2.2/image-to-image' \
--header 'Authorization: Bearer [Your API KEY]' \
--header 'Authorization: Bearer [Your API KEY]' \
--header 'Content-Type: application/json' \
--data-raw '{
    "272##image": "example.png",
    "79##text": "Change to an Asian female face",
    "267##select": "1",
    "270##value": 1024,
    "271##value": 1024,
    "242##file_type": "PNG"
}'

Responses

🟢200成功

application/json

Task result query endpoint: /openapi/v2/query

Body

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 2026-04-04 04:00:08

z-image-turbo/image-to-image

f-kontext-dev-lora