How to Use the Seedream 5.0 Flash Layer Decomposition API: image to image integration guide (2026)

Seedream 5.0 Flash Layer Decomposition is an image to image model by Doubao: Decompose one image into a base image and up to 16 layers. $0.018 per output image; maximum precharge $0.306 per request, settled by actual output count. On NamiFusion you can try it in the playground (exact quote shown before you submit), then call it through one unified REST API — about $0.018 per output image.

TL;DR

· Task type: image to image, provided by Doubao

· Pricing: about $0.018 per output image ($1 = 100 credits), pay-as-you-go

· Getting started: playground (exact quote before submit) → create an API key → one POST request

· Tunable parameters: 4 (see the table below)

· No platform watermark; commercial use allowed (per the Terms of Service)

What can you build with Seedream 5.0 Flash Layer Decomposition?

Social media visuals and covers: batch-generate on-theme images and schedule them straight away.

E-commerce and ad creatives: product scenes, banner backgrounds, and multi-variant visuals for A/B tests.

Concept art and ideation: characters, environments and style boards, iterated cheaply and fast.

Pipeline chaining: outputs feed directly into image-to-video or face swap as source material.

How do you call this API?

1. Sign up on NamiFusion and create a key on the API Keys page (signup bonus credits can only be used on selected models).
2. Submit a task with the cURL example below, passing your key as a Bearer token.
3. Poll the task status with the returned task_uuid and read the output URLs when completed.

# 1) Submit — returns { "task_uuid": "..." }
curl -X POST "https://www.namifusion.com/api/v1/marketplace/run/doubao/seedream-v5.0-flash/layer-decomposition" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "input": {
    "image": [
      "https://d1s3annbwribom.cloudfront.net/marketplace/examples/2026/09/24/89b481bb63b1.jpeg"
    ],
    "prompt": "Decompose the scene into clean transparent layers with accurate separation of the desk objects, preserving fine edges, shadows, and background details for easy compositing and editing.",
    "output_format": "png",
    "size": "auto"
  }
}'

# 2) Poll until status is "completed", then read the output URLs
curl "https://www.namifusion.com/api/v1/marketplace/run/tasks/TASK_UUID" \
  -H "Authorization: Bearer YOUR_API_KEY"

What parameters does it take?

image (Image): required

prompt (Prompt): optional

output_format (Output Format): optional, default "png"

size (Size): optional, default "auto"

How do you write prompts for Seedream 5.0 Flash Layer Decomposition?

1. Subject first: lead with the actor and action, then add environment, lighting and style ("an astronaut sprinting through a neon street in the rain, cinematic, shallow depth of field").
2. Concrete nouns beat stacked adjectives: "85mm portrait lens, golden-hour backlight" works far better than "very beautiful, ultra high quality".
3. Change one variable per iteration: pin the seed to reproduce a result, tweak a single phrase at a time so you know what actually moved the output.
4. State negatives positively: instead of "no blur", ask for "sharp focus, crisp details".

How much does it cost?

Pay per output image in credits: about $0.018 per output image ($1 = 100 credits). The total depends on the actual output count; the playground shows the precharge quote before submission.