curl --request POST \
  --url https://api.evolink.ai/v1/images/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "doubao-seedream-5.5-layerize",
  "image_urls": [
    "https://example.com/poster.png"
  ],
  "quality": "auto",
  "output_format": "png",
  "n": 30,
  "model_params": {
    "text_recognition": true
  }
}
'

{
  "created": 1757165031,
  "id": "task-unified-1793612934-seedream55layerize",
  "model": "doubao-seedream-5.5-layerize",
  "object": "image.generation.task",
  "progress": 0,
  "status": "pending",
  "task_info": {
    "can_cancel": true,
    "estimated_time": 150
  },
  "type": "image",
  "usage": {
    "billing_rule": "per_image",
    "credits_reserved": 55.624,
    "user_group": "default"
  }
}

{
  "error": {
    "code": "invalid_request",
    "message": "Invalid request parameters",
    "type": "invalid_request_error"
  }
}

{
  "error": {
    "code": "unauthorized",
    "message": "Invalid or expired token",
    "type": "authentication_error"
  }
}

{
  "error": {
    "code": "insufficient_quota",
    "message": "Insufficient quota. Please top up your account.",
    "type": "insufficient_quota"
  }
}

{
  "error": {
    "code": "model_access_denied",
    "message": "Token does not have access to model: doubao-seedream-5.5-layerize",
    "type": "invalid_request_error"
  }
}

{
  "error": {
    "code": "rate_limit_exceeded",
    "message": "Too many requests, please try again later",
    "type": "rate_limit_error"
  }
}

{
  "error": {
    "code": "internal_error",
    "message": "Internal server error",
    "type": "api_error"
  }
}

Seedream 5.5

Seedream 5.5 Layer Decomposition

Seedream 5.5 Layer Decomposition (doubao-seedream-5.5-layerize) separates an image into a base image and independent layers
Provide 1 input image. prompt is optional; when omitted, the model automatically identifies and separates the main elements
Use n to set the maximum output count and model_params.text_recognition to enable text recognition
Processing is asynchronous. Use the returned task ID to query task status
Generated image links are valid for 24 hours, please save them promptly

Output details

output_format sets the base image format. Independent layers are always PNG images with an alpha channel
Each image in result_data includes z_index (stacking order: 0 for the base image, increasing from 1 for layers) and background (opaque for the base image, transparent for layers). Layers also include bounding_box (absolute uses pixel coordinates in the base-image coordinate system; normalized ranges from 0 to 1000), name and description
If any layer fails, the entire task fails with a full refund. Partial results are not returned

Billing

The base image and each layer are billed individually. The input image is charged separately
Task creation reserves credits for 1 input image and up to n output images. On completion, billing is settled against the actual output count and unused credits are returned automatically

POST

images

generations

curl --request POST \
  --url https://api.evolink.ai/v1/images/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "doubao-seedream-5.5-layerize",
  "image_urls": [
    "https://example.com/poster.png"
  ],
  "quality": "auto",
  "output_format": "png",
  "n": 30,
  "model_params": {
    "text_recognition": true
  }
}
'

{
  "created": 1757165031,
  "id": "task-unified-1793612934-seedream55layerize",
  "model": "doubao-seedream-5.5-layerize",
  "object": "image.generation.task",
  "progress": 0,
  "status": "pending",
  "task_info": {
    "can_cancel": true,
    "estimated_time": 150
  },
  "type": "image",
  "usage": {
    "billing_rule": "per_image",
    "credits_reserved": 55.624,
    "user_group": "default"
  }
}

{
  "error": {
    "code": "invalid_request",
    "message": "Invalid request parameters",
    "type": "invalid_request_error"
  }
}

{
  "error": {
    "code": "unauthorized",
    "message": "Invalid or expired token",
    "type": "authentication_error"
  }
}

{
  "error": {
    "code": "insufficient_quota",
    "message": "Insufficient quota. Please top up your account.",
    "type": "insufficient_quota"
  }
}

{
  "error": {
    "code": "model_access_denied",
    "message": "Token does not have access to model: doubao-seedream-5.5-layerize",
    "type": "invalid_request_error"
  }
}

{
  "error": {
    "code": "rate_limit_exceeded",
    "message": "Too many requests, please try again later",
    "type": "rate_limit_error"
  }
}

{
  "error": {
    "code": "internal_error",
    "message": "Internal server error",
    "type": "api_error"
  }
}

Authorizations

Authorization

string

header

required

##All APIs require Bearer Token authentication##

Get API Key:

Visit API Key Management Page to get your API Key

Add to request header:

Authorization: Bearer YOUR_API_KEY

Body

application/json

model

enum<string>

default:doubao-seedream-5.5-layerize

required

Image generation model name

Available options:

doubao-seedream-5.5-layerize

Example:

"doubao-seedream-5.5-layerize"

image_urls

string<uri>[]

required

URL of the image to decompose (required)

Note:

Exactly 1 image is required; omitting it or passing 2 or more returns an error
Supported formats: .png, .jpeg, .jpg (stricter than plain generation — webp and others are rejected)
Image size: no more than 30MB
Total pixels: [262144, 6000×6000], i.e. at least 512×512 (a higher lower bound than plain generation)
Aspect ratio (width/height) range: [1/16, 16]
The image URL must be directly viewable by the server, or the URL must trigger a direct download when accessed (usually such URLs end with an image file extension, such as .png, .jpg)
The input image is charged separately

Required array length: 1 element

Example:

["https://example.com/poster.png"]

prompt

string

Which elements to split out (optional)

Three ways to use it:

Omit it: the model detects every major element in the image and splits them one by one
Natural language: e.g. Split out the parrot and the title text — elements are identified semantically and turned into layers
Exact coordinates: use <bbox> tags to pin down a position, e.g. title text<bbox>179 58 809 197</bbox>; normalized coordinates (0~1000) are recommended

Example:

"Split out the parrot and the title text"

integer

default:30

Maximum number of output images, including the base image. Defaults to 30.

Details:

Allowed range: 2 to 100. Values outside this range return 400 with no charge
Decomposition stops at this limit; remaining elements may be merged or omitted. A larger value allows finer separation
A larger n reserves more credits. On completion, billing is settled against the actual output count and unused credits are returned automatically

Required range: 2 <= x <= 100

Example:

30

quality

enum<string>

default:auto

Output resolution. Defaults to auto.

Options: auto, 1K, 1.5K, 2K

Notes:

Only the resolution options above are supported. Passing an aspect ratio (such as 16:9) or pixel dimensions (such as 2048x2048) returns an error
auto makes the output follow the input image: if the original size falls within [921600, 4624220] pixels it is kept as is, below 1K it is output at 1K, above 2K it is output at 2K
Each layer keeps its own aspect ratio from the original image, and the base image keeps the aspect ratio of the input

Available options:

auto,

1K,

1.5K,

2K

Example:

"auto"

prompt_priority

enum<string>

default:standard

Prompt optimization mode. Only standard is supported and is the default.

Passing fast returns 400 with no charge.

Available options:

standard

Example:

"standard"

output_format

enum<string>

default:png

Output image format

Options:

png: PNG format (default)
jpeg: JPEG format

Note: This parameter only controls the base image. The layers are always PNG with an alpha channel and are not affected by it.

Available options:

png,

jpeg

Example:

"png"

model_params

object

Additional options for layer decomposition. Only text_recognition is accepted; other keys return 400.

Show child attributes

callback_url

string<uri>

HTTPS callback address after task completion

Callback Timing:

Triggered when task is completed, failed, or cancelled
Sent after billing confirmation is completed

Security Restrictions:

Only HTTPS protocol is supported
Callback to internal IP addresses is prohibited (127.0.0.1, 10.x.x.x, 172.16-31.x.x, 192.168.x.x, etc.)
URL length must not exceed 2048 characters

Callback Mechanism:

Timeout: 10 seconds
Maximum 3 retries on failure (retries after 1 second/2 seconds/4 seconds)
Callback response body format is consistent with the task query API response format
Callback address returning 2xx status code is considered successful, other status codes will trigger retry

Example:

"https://your-domain.com/webhooks/image-task-completed"

Response

Image generation task created successfully

created

integer

Task creation timestamp

Example:

1757165031

string

Task ID

Example:

"task-unified-1793612934-seedream55layerize"

model

string

Actual model name used

Example:

"doubao-seedream-5.5-layerize"

object

enum<string>

Specific task type

Available options:

image.generation.task

progress

integer

Task progress percentage (0-100)

Required range: 0 <= x <= 100

Example:

0

status

enum<string>

Task status

Available options:

pending,

processing,

completed,

failed

Example:

"pending"

task_info

object

Async task information

Show child attributes

type

enum<string>

Task output type

Available options:

text,

image,

audio,

video

Example:

"image"

usage

object

Usage and billing information

Show child attributes

Image Series

Video Series

Audio Series

Text Series

Account Management

Task Management

File Management

Seedream 5.5 Layer Decomposition

Output details

Billing

Authorizations

Body

Response