Seedream 5.0 Flash Layer Decomposition: AI画像編集

Split any image into a base plus clean separate layers with the Seedream 5.0 Flash Layer Decomposition API. Prompt or bbox targeting. Pay per generation.

インタラクティブなモデルコントロール

Decompose a composite image into a base image plus clean, separate layer assets with Seedream 5.0 Flash Layer Decomposition. Optionally target elements with prompts or <bbox> regions.

📝

概要

このモデルについて

Seedream 5.0 Flash Layer Decomposition separates a composite image into a base image and independent transparent PNG layers for text, subjects, and graphic elements. Leave the prompt empty to auto-detect the main elements, or describe them and pin exact regions with <bbox>x1 y1 x2 y2</bbox> tags on a 0-1000 normalized grid. It is the fast, low-cost tier alongside Seedream 5.0 Pro Layer Decomposition.

1Design: Turn flat posters into editable layers.
2Marketing: Extract text and subjects for re-layout across formats.
3Video: Prepare layers for parallax and motion graphics.
4Production: Isolate elements for compositing.
💰

料金と価値

コスト分析

muapiapp$0.459/生成

Pay-per-generation pricing, サブスクリプション不要.

Fal.ai利用不可

No dedicated Seedream 5.0 Flash endpoint at this time.

Replicate利用不可

No dedicated Seedream 5.0 Flash endpoint at this time.

** 競合サービスの料金は類似のモデル構成および利用ティアに基づいて算出された推定値です。

⚙️

技術詳細

設定スキーマ

プロンプトstring

Optional. Describe which elements to separate; supports <bbox>x1 y1 x2 y2</bbox> (0-1000 normalized). Leave empty to auto-detect main elements.

デフォルト値Separate the title text <bbox>179 58 809 197</bbox> and the parrot <bbox>330 274 641 991</bbox> into independent layers
画像 URLstring

Source image to decompose (exactly 1; PNG, JPEG, WebP, BMP, TIFF, GIF; max 30MB).

デフォルト値https://static.aiquickdraw.com/tools/example/1786019968051_cKRYLHHu.png
解像度Enum(4個の選択肢)

出力メディアの解像度(720p、1080p、4Kなど)。

デフォルト値auto
出力形式Enum(2個の選択肢)

Format of the base image only; separated layers are always PNG.

デフォルト値jpeg
📖

実装ガイド

開発者ドキュメント

How to Use Seedream 5.0 Flash Layer Decomposition

  1. Provide the source image as image_url (one image, max 30MB).

  2. Optionally add a prompt, e.g. with <bbox> regions, or leave empty to auto-detect.

  3. Choose size auto, 1K, 1.5K, or 2K.

  4. Submit and poll request_id; the output contains the base image and each layer.

curl -X POST https://api.muapi.ai/api/v1/seedream-5.0-flash-layerize \
  -H "Authorization: Bearer $MUAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"image_url":"https://static.aiquickdraw.com/tools/example/1786019968051_cKRYLHHu.png","prompt":"Separate the title text <bbox>179 58 809 197</bbox> and the parrot <bbox>330 274 641 991</bbox> into independent layers","resolution":"2K"}'
❓

よくある質問

FAQ

What is Seedream 5.0 Flash Layer Decomposition?

It splits one image into a base image plus separate PNG layers, either auto-detected or targeted by prompt and bbox coordinates.

How much does it cost?

Pay per generation with no subscription. Pricing is a flat rate per run at every resolution and size.

What resolutions are supported?

1K and 2K output through the `resolution` parameter (layer decomposition uses `auto`, `1K`, `1.5K` or `2K`).

How do I get the result?

Requests are asynchronous: submit a job, then poll `request_id` or pass a `webhook` URL to be notified on completion.

Which output formats are available?

`png` or `jpeg` via `output_format`.

Is there a sandbox for testing?

Yes — sandbox API keys return mock results instantly with no credits deducted.