seedream-v4.5/image-to-image

POST

/openapi/v2/seedream-v4.5/image-to-image

ByteDance’s premium image editing model, engineered for professional-grade, prompt-driven retouching. Unlike standard AI filters, it maintains high fidelity to the original image—preserving facial identity, poses, lighting, and color palettes with precision. Key highlights include batch processing for up to 10 images to ensure aesthetic consistency and 4K-ready output for ultra-crisp detail. With its exceptional prompt adherence, the model accurately interprets nuanced instructions for clothing, backgrounds, and moods. It is the definitive tool for creators seeking sophisticated edits with minimal artifacts and realistic textures.

Request

Authorization

Header Params

Body Params application/jsonRequired

Example

{
    "prompt": "Preserve the character’s pose, clothing, lighting, and facial features exactly as in the original. Replace the rainforest background with a snowy mountain path at night: snow-covered ground, distant glowing lanterns, gentle snowfall, and low mist rising from the earth. Retain the texture of the wet stone path and fallen leaves, but adapt them to a snowy setting. Maintain a cool, cinematic color tone and ensure the new background lighting matches the original direction and mood.",
    "width": 2048,
    "height": 2048,
    "imageUrls": [
        "https://www.runninghub.cn/view?filename=bc4c0c410ef53a600fa3ea353c4ab909fe814d6c249543af0248cfaf19f2ff32.jpeg&type=input&subfolder=&Rh-Comfy-Auth=eyJ1c2VySWQiOiIzZjY1MTNlNWEwNjY1N2I4OGYyNjU5NTEzYmU3ZDM0YyIsInNpZ25FeHBpcmUiOjE3NjkwODU4NDgzMjUsInRzIjoxNzY4NDgxMDQ4MzI1LCJzaWduIjoiOWY0ZWU2NTg1NjQ3ZTBiMWY2NTFkMmNmYjNlYzljOWEifQ==&Rh-Identify=3f6513e5a06657b88f2659513be7d34c&rand=0.6440490186137648"
    ],
    "sequentialImageGeneration": "disabled",
    "maxImages": 1
}

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/seedream-v4.5/image-to-image' \
--header 'Authorization: Bearer [Your API KEY]' \
--header 'Authorization: Bearer [Your API KEY]' \
--header 'Content-Type: application/json' \
--data-raw '{
    "prompt": "Preserve the character’s pose, clothing, lighting, and facial features exactly as in the original. Replace the rainforest background with a snowy mountain path at night: snow-covered ground, distant glowing lanterns, gentle snowfall, and low mist rising from the earth. Retain the texture of the wet stone path and fallen leaves, but adapt them to a snowy setting. Maintain a cool, cinematic color tone and ensure the new background lighting matches the original direction and mood.",
    "width": 2048,
    "height": 2048,
    "imageUrls": [
        "https://www.runninghub.cn/view?filename=bc4c0c410ef53a600fa3ea353c4ab909fe814d6c249543af0248cfaf19f2ff32.jpeg&type=input&subfolder=&Rh-Comfy-Auth=eyJ1c2VySWQiOiIzZjY1MTNlNWEwNjY1N2I4OGYyNjU5NTEzYmU3ZDM0YyIsInNpZ25FeHBpcmUiOjE3NjkwODU4NDgzMjUsInRzIjoxNzY4NDgxMDQ4MzI1LCJzaWduIjoiOWY0ZWU2NTg1NjQ3ZTBiMWY2NTFkMmNmYjNlYzljOWEifQ==&Rh-Identify=3f6513e5a06657b88f2659513be7d34c&rand=0.6440490186137648"
    ],
    "sequentialImageGeneration": "disabled",
    "maxImages": 1
}'

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 2026-03-14 12:00:01

midjourney-text-to-image-v7

seedream-v4/image-to-image