curl --request POST \
  --url https://api.evolink.ai/v1/images/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "doubao-seedream-5.0-flash-layerize",
  "image_urls": [
    "https://example.com/poster.png"
  ],
  "quality": "auto",
  "output_format": "jpeg"
}
'

{
  "created": 1757165031,
  "id": "task-unified-1757165031-seedream5flashlayerize",
  "model": "doubao-seedream-5.0-flash-layerize",
  "object": "image.generation.task",
  "progress": 0,
  "status": "pending",
  "task_info": {
    "can_cancel": true,
    "estimated_time": 60
  },
  "type": "image",
  "usage": {
    "billing_rule": "per_image",
    "credits_reserved": 18.7272,
    "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-5.0-flash-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

Seedream 5.0 Flash Layer Decomposition

Seedream 5.0 Flash Layer Decomposition (doubao-seedream-5.0-flash-layerize) splits one image into a base image and several independent layers; every layer is a PNG with an alpha channel, while the base image format follows output_format
Exactly one input image is required; prompt is optional — omit it and the model automatically detects every major element in the image and splits them one by one
The number of output images is decided by the decomposition result (1 ~ 17) and cannot be controlled by request parameters; if any layer fails the whole request fails — there is no partial success, and a failed request is fully refunded
Asynchronous processing mode, use the returned task ID to query. In the task detail, every item in result_data carries z_index (stacking order: 0 for the base image, incrementing from 1 for layers); layers additionally carry bounding_box (absolute in base-image pixel coordinates, normalized in the 0~1000 range), name and description
Billed per image: the base image and each layer count as one image at the same price, regardless of resolution tier; the input image is free. Credits for up to 17 images are reserved when the task is created, then settled against the actual output count on completion; any excess reserved credits are automatically returned
Estimated processing time: about 60 seconds
Generated image links are valid for 24 hours, please save them promptly

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-5.0-flash-layerize",
  "image_urls": [
    "https://example.com/poster.png"
  ],
  "quality": "auto",
  "output_format": "jpeg"
}
'

{
  "created": 1757165031,
  "id": "task-unified-1757165031-seedream5flashlayerize",
  "model": "doubao-seedream-5.0-flash-layerize",
  "object": "image.generation.task",
  "progress": 0,
  "status": "pending",
  "task_info": {
    "can_cancel": true,
    "estimated_time": 60
  },
  "type": "image",
  "usage": {
    "billing_rule": "per_image",
    "credits_reserved": 18.7272,
    "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-5.0-flash-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-5.0-flash-layerize

required

Image generation model name

Available options:

doubao-seedream-5.0-flash-layerize

Example:

"doubao-seedream-5.0-flash-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)

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:

"Separate the parrot and the title text"

quality

enum<string>

default:auto

Output resolution tier, defaults to auto

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

Notes:

Layer mode only accepts tiers; passing a ratio (such as 16:9) or explicit pixels (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

Billing: Billed per image regardless of resolution tier; 1K, 1.5K, 2K, and auto cost the same.

Available options:

auto,

1K,

1.5K,

2K

Example:

"auto"

prompt_priority

enum<string>

default:standard

Prompt optimization strategy, used to set the prompt optimization mode

Options:

standard: Standard mode

Note: Seedream 5.0 Flash only supports standard; passing fast returns 400. Flash already provides faster generation and does not offer a separate fast mode.

Available options:

standard

Example:

"standard"

output_format

enum<string>

default:jpeg

Output image format

Options:

jpeg: JPEG format (default)
png: PNG 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:

jpeg,

png

Example:

"jpeg"

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-1757165031-seedream5flashlayerize"

model

string

Actual model name used

Example:

"doubao-seedream-5.0-flash-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 5.0 Flash Layer Decomposition

Authorizations

Body

Response