bytedance/seedream-5-flash-layerize/image-to-image

Image to Image

Decompose images into editable layers with ByteDance Seedream 5.0 Flash Layerize for asset extraction, compositing and design workflows. Supply one image and optionally describe the objects or groups to separate; without instructions, the model identifies major elements automatically. The API returns a base image and up to 16 separated layers, together with stacking order, layer labels and available position coordinates. Choose automatic sizing or 1K, 1.5K and 2K output tiers. Transparent layers can be reused in an external image editor.

Try it Get API keyOpenAPI llms.txt

Prompt

Image Url *

Image size

ResultExampleSign in to try

$0.027 / image · ~37 images per $1

Images and layers

Preparing image files…

Base image

z: 0

Download image

dark green ginkgo leaf

z: 1

Extract the complete dark green ginkgo leaf including its stem, preserve all original vein details, leaf shape, color, edges, position and appearance.

Download image

coral-orange sphere

z: 2

Extract the full solid coral-orange sphere, preserve its original smooth surface, color, edges, position and lighting appearance.

Download image

ivory origami crane

z: 3

Extract the complete intact ivory origami crane as a single unified object, preserve all original folded paper edges, color, position and appearance, do not split its individual folded parts.

Download image

Pricing

Unit price $0.027 / image

Billed by the number of images actually generated.

~37 images per $1

Each request temporarily reserves $0.027; you are charged for actual usage, usually within a minute: any unused amount is released and any usage above it is charged to your balance, even if that takes it below zero; while your balance is below zero, new requests are paused until a top-up covers it.

Failed generations are not charged.

API

Submit generation requests with this model ID.

POST/v1/model-tasks

bytedance/seedream-5-flash-layerize/image-to-image

Request body

{
  "model": "bytedance/seedream-5-flash-layerize/image-to-image",
  "input": {
    "prompt": "Separate the three main foreground objects into individual transparent layers: the complete ivory origami crane, the coral-orange sphere, and the dark green ginkgo leaf. Keep the crane as one object rather than splitting its folded paper parts. Return a clean base image containing only the pale aqua studio background and tabletop, plus one layer for each of the three objects. Preserve the original positions, colors, edges and appearance. Return layer names and descriptions in English.",
    "image_url": "https://pub-a7287c8d5de944d984e22a5bd3ab9bbe.r2.dev/uploads/capability-demo-0072d694a35c704c7b203372df1fd60d.png",
    "image_size": "auto_1K"
  }
}

Input schema

Parameter	Type	Requirement	Default
image_url	string	Required	—
image_size	string	Optional	auto
prompt	string	Optional

Response

The API returns a result or a pollable asynchronous task. See the examples and Schema below for the response mode and result fields.

Asynchronous task

Submit response

HTTP 202

/v1/model-tasksapplication/json

{
  "id": "task_example",
  "model": "bytedance/seedream-5-flash-layerize/image-to-image",
  "status": "queued"
}

Status response

HTTP 200

/v1/model-tasks/{id}application/json

{
  "id": "task_example",
  "model": "bytedance/seedream-5-flash-layerize/image-to-image",
  "status": "completed",
  "output": {
    "layers": [
      {
        "image": {
          "url": "https://api.musespan.com/v1/model-tasks/task_example/artifacts/0"
        }
      }
    ],
    "images": [
      {
        "url": "https://api.musespan.com/v1/model-tasks/task_example/artifacts/1"
      }
    ]
  }
}

File download

HTTP 200

/v1/model-tasks/{id}/artifacts/{index}Generated image (e.g. image/png)

When the task completes, file URLs in output point to this endpoint, numbered from 0. Send the same API key (Authorization header) when downloading.

Error response

HTTP 400

/v1/model-tasksapplication/json

{
  "error": {
    "code": "invalid_input",
    "message": "The input does not match this model's input schema. Check the model's API documentation.",
    "type": "invalid_request_error"
  }
}

Code examples

Async submission returns a task ID. Poll until status is completed, then retrieve the generated content from the result. Get your API key in the console.

# Use a new directory for each new generation. Rerunning here continues this task.
set -eu
test -s model-task-id.txt || python3 -c "import uuid; print(uuid.uuid4())" > model-task-id.txt
REQUEST_ID=$(cat model-task-id.txt)
# Idempotent: resending the same bytes with the same ID never charges twice.
curl --fail-with-body --retry 3 --retry-connrefused --request POST 'https://api.musespan.com/v1/model-tasks' \
  --header "Authorization: Bearer $MUSESPAN_API_KEY" \
  --header "X-Request-Id: $REQUEST_ID" \
  --header "Content-Type: application/json" \
  --data '{"model":"bytedance/seedream-5-flash-layerize/image-to-image","input":{"prompt":"Separate the three main foreground objects into individual transparent layers: the complete ivory origami crane, the coral-orange sphere, and the dark green ginkgo leaf. Keep the crane as one object rather than splitting its folded paper parts. Return a clean base image containing only the pale aqua studio background and tabletop, plus one layer for each of the three objects. Preserve the original positions, colors, edges and appearance. Return layer names and descriptions in English.","image_url":"https://pub-a7287c8d5de944d984e22a5bd3ab9bbe.r2.dev/uploads/capability-demo-0072d694a35c704c7b203372df1fd60d.png","image_size":"auto_1K"}}'
# Poll every 5 seconds for up to 25 minutes until status is completed or failed.
# Still queued (with queue_position) 5 minutes after submission: failed with queue_timeout, not charged.
# No result 15 minutes after acceptance (or no confirmation 15 minutes after submission): failed with generation_timeout, not charged.
# Any failure is final: generate again in a new directory (a new X-Request-Id).
# A 404 means the POST did not arrive: rerun this script to resend it with the same ID.
curl --fail-with-body 'https://api.musespan.com/v1/model-tasks/'"$REQUEST_ID"'' --header "Authorization: Bearer $MUSESPAN_API_KEY"

Pricing

API

Input schema

Response

Code examples

Cookie preferences