Seedream 5.0 Pro Multi-Reference

curl --request POST \ --url https://api.modellix.ai/api/v1/bytedance/seedream-5.0-pro-multi-reference \ --header 'Authorization: Bearer <token>' \ --header 'Content-Type: application/json' \ --data ' { "prompt": "Combine the character from image 1 with the scene from image 2", "image": [ "https://example.com/ref-1.jpg", "https://example.com/ref-2.jpg" ] } '

{ "code": 0, "message": "success", "data": { "status": "pending", "task_id": "task-abc123", "model_id": "model-123", "get_result": { "method": "GET", "url": "https://api.modellix.ai/api/v1/tasks/task-abc123" } } }

Authorizations

Authorization

string

header

required

API Key authentication. Format: Bearer YOUR_API_KEY.

Body

application/json

prompt

string

required

Image editing instruction, supports Chinese and English. Maximum 10000 characters. We recommend keeping the prompt under 600 words. Interactive precise editing is supported: edit locations can be specified via coordinates, selection boxes, or arrows described in the prompt.

Required string length: 1 - 10000

Example:

"Replace the object in the selection box (100,100)-(300,300) with a red vintage car"

image

string[]

required

Reference image array (2-10 images), each as a URL (or Base64 data URI). Each image must be <= 30 MB, width and height > 14 px, aspect ratio within [1/16, 16], total pixels <= 36,000,000. Supported formats: JPEG, PNG, WEBP, BMP, TIFF, GIF, HEIC, HEIF.

Required array length: 2 - 10 elements

Example:

[
  "https://example.com/ref-1.jpg",
  "https://example.com/ref-2.jpg"
]

size

string

default:1024x1024

Image size in format 'widthxheight'. Total pixels must be within [1280x720(921,600), 4,624,220] and aspect ratio within [1/16, 16], corresponding to the official 1K/2K resolution levels (3K/4K not supported). Recommended 2K sizes: 2048x2048 (1:1), 2816x1584 (16:9), 2368x1776 (4:3).

Example:

"2048x2048"

optimize_prompt_mode

enum<string>

default:standard

Prompt optimization mode. 'standard': higher quality with longer generation time. 'fast': faster generation with slightly lower quality.

Available options:

standard,

fast

Example:

"standard"

output_format

enum<string>

default:jpeg

Output image format. Supported values: 'jpeg' and 'png'.

Available options:

jpeg,

png

Example:

"png"

Response

200 - application/json

Task submitted successfully

code

integer

required

Response code, 0 indicates success

Example:

0

message

string

required

Response message

Example:

"success"

data

object

required

Detailed data about the submitted asynchronous task.

Show child attributes

Model API

Common API

File API

Seedream 5.0 Pro Multi-Reference

Authorizations

Body

Response