seedream-v5-lite/image-to-image

POST

/openapi/v2/seedream-v5-lite/image-to-image

focuses on ultimate visual control and deep image editing. Beyond basic repainting, it introduces powerful multi-image feature fusion and "Reference-to-Sequential Generation." Whether seamlessly reconstructing styles, materials, and elements from multiple inputs, or expanding references into perfectly consistent visual series, this API enables high-degree artistic manipulation and industrial-grade design delivery while preserving the core characteristics of the original references.

Request

Authorization

Header Params

Body Params application/jsonRequired

Example

{
    "prompt": "Please fuse the inputted Image 1 and Image 2 Generate a coherent sequence of 3 Guoman-style horizontal concept art pieces. The main subjects are the young man Fang Wen and his pet black-feathered crow. Image 1: Fang Wen, wearing the Jinyiwei-style attire from Image A, stands before the rainy ancient temple from Image B, with the crow circling in the rain. Image 2: A closer perspective as Fang Wen pushes open the mottled wooden doors of the temple, with faint light refracting onto his face through the gap. Image 3: Fang Wen enters the temple interior, the crow perched on a ruined Buddha statue, surrounded by mysterious mist. Requirement: Perfectly extract and fuse the clothing material details from Image 1 and the atmospheric environment of Image 2. Maintain flawless character traits and scene consistency across all 3 images.",
    "width": 2048,
    "height": 2048,
    "imageUrls": [
        "https://www.runninghub.cn/view?filename=8f697d8ec4f8eb8e34e43caf5af55aba492260c4253cfbcb802b0d5e298e45da.jpg&type=input&subfolder=&Rh-Comfy-Auth=eyJ1c2VySWQiOiIzZjY1MTNlNWEwNjY1N2I4OGYyNjU5NTEzYmU3ZDM0YyIsInNpZ25FeHBpcmUiOjE3NzI3MDM3MDcyOTIsInRzIjoxNzcyMDk4OTA3MjkyLCJzaWduIjoiMWZjNjY2YTQ1YzQzNjE1MDJiMDQ2MzQyMGQ5MWIyOTAifQ==&Rh-Identify=3f6513e5a06657b88f2659513be7d34c&rand=0.3137804387708145"
    ],
    "sequentialImageGeneration": "disabled",
    "maxImages": 1
}

Request Code Samples

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

curl --location 'https://www.runninghub.ai/openapi/v2/seedream-v5-lite/image-to-image' \
--header 'Authorization: Bearer [Your API KEY]' \
--header 'Authorization: Bearer [Your API KEY]' \
--header 'Content-Type: application/json' \
--data '{
    "prompt": "Please fuse the inputted Image 1 and Image 2 Generate a coherent sequence of 3 Guoman-style horizontal concept art pieces. The main subjects are the young man Fang Wen and his pet black-feathered crow. Image 1: Fang Wen, wearing the Jinyiwei-style attire from Image A, stands before the rainy ancient temple from Image B, with the crow circling in the rain. Image 2: A closer perspective as Fang Wen pushes open the mottled wooden doors of the temple, with faint light refracting onto his face through the gap. Image 3: Fang Wen enters the temple interior, the crow perched on a ruined Buddha statue, surrounded by mysterious mist. Requirement: Perfectly extract and fuse the clothing material details from Image 1 and the atmospheric environment of Image 2. Maintain flawless character traits and scene consistency across all 3 images.",
    "width": 2048,
    "height": 2048,
    "imageUrls": [
        "https://www.runninghub.cn/view?filename=8f697d8ec4f8eb8e34e43caf5af55aba492260c4253cfbcb802b0d5e298e45da.jpg&type=input&subfolder=&Rh-Comfy-Auth=eyJ1c2VySWQiOiIzZjY1MTNlNWEwNjY1N2I4OGYyNjU5NTEzYmU3ZDM0YyIsInNpZ25FeHBpcmUiOjE3NzI3MDM3MDcyOTIsInRzIjoxNzcyMDk4OTA3MjkyLCJzaWduIjoiMWZjNjY2YTQ1YzQzNjE1MDJiMDQ2MzQyMGQ5MWIyOTAifQ==&Rh-Identify=3f6513e5a06657b88f2659513be7d34c&rand=0.3137804387708145"
    ],
    "sequentialImageGeneration": "disabled",
    "maxImages": 1
}'

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 2026-05-25 12:05:38

hitem3d-v15/image-to-3d

seedream-v4/image-to-image