Spiral gives your agent every tool with one account. Browse the tools →

OpenClaw · ImageReleased 2026-11-11

How to Use Seedream 5.5 Layerize in OpenClaw

Seedream 5.5 Layerize turns a finished image into a base image and independently editable PNG layers. Use it to separate artwork, products, and text for recomposition, with positions, stacking order, and optional text recognition.

Prompts to try with Seedream 5.5 Layerize in OpenClaw

Copy an example into OpenClaw, or ask in your own words.

Every weekday, use Seedream 5.5 Layerize on each new promotion image in the incoming design collection, one image at a time. Separate the product and headline, then prepare an asset contact sheet for review.

Seedream 5.5 LayerizeOpenClaw
Try asking
  • Each Monday, use Seedream 5.5 Layerize on newly submitted posters with text recognition turned on. Report recognized wording for proofreading and mark text that requires manual review.

  • Each night, use Seedream 5.5 Layerize on new approved illustrations, one image per request. Extract the animals and plants as separate transparent assets and organize them by source image.

  • Every Friday, use Seedream 5.5 Layerize on new interior concept images. Separate chairs and tables, and prepare base-image previews for a reviewer to inspect the reconstructed areas.

  • Each morning, use Seedream 5.5 Layerize on newly approved campaign banners at the 2K output tier. Separate the main product and decorative elements for the design team's next layout pass.

How to set up Seedream 5.5 Layerize in OpenClaw

Pick the way that suits you. Each takes about two minutes.

Use the Spiral skill

  1. Send OpenClaw this message

    Your agent reads Spiral's skill and sets itself up.

    set up https://spiral.ai/SKILL.md
  2. Sign in or paste a key

    Approve Spiral in the browser, or give the agent a key from the console.

Use Spiral's MCP server

  1. Add the server

    On the machine that runs OpenClaw's Gateway:

    openclaw mcp add spiral \
      --url https://api.spiral.ai/mcp \
      --transport streamable-http \
      --auth oauth
  2. Sign in

    In Settings › MCP, select Sign in on the Spiral server, sign in to Spiral and click Authorize. No API key.

    openclaw mcp login spiral
  3. Reload and check

    A running Gateway may keep its old tool list: restart it, or Save & Publish in the Control UI.

    openclaw mcp reload
    openclaw mcp doctor spiral --probe

Use the Spiral CLI

  1. Install and sign in

    Installs the Spiral CLI, signs you in and adds its skill to your coding agents.

    npx -y spiral-cli@latest init

Call the Spiral API

  1. Create an API key

    In the console, under API keys.

  2. Run Seedream 5.5 Layerize

    One request; the result comes back by polling or a webhook.

    curl https://api.spiral.ai/v1/runs \
      -H "Authorization: Bearer $SPIRAL_API_KEY" \
      -H "Content-Type: application/json" \
      -H "Idempotency-Key: $(uuidgen)" \
      -d '{
        "provider": "fal",
        "model": "bytedance/seedream/v5.5/layerize",
        "input": {
          "image_url": "https://storage.googleapis.com/falserverless/example_inputs/kontext_example_input.webp"
        }
      }'

Then paste one of the prompts above: OpenClaw finds Seedream 5.5 Layerize on Spiral, shows the price and runs it.

Seedream 5.5 Layerize providers and prices

Spiral runs Seedream 5.5 Layerize through fal. Open a card for today's price, with every fee included.

falImage
Seedream 5.5 Layerize
bytedance/seedream/v5.5/layerize

Settings you can ask for

Seedream 5.5 Layerize works from your prompt and image URL. Ask OpenClaw for any of these in your prompt.

SettingAllowed valuesDefaultDescription
Image sizeauto, auto_1K, auto_1.5K, or auto_2Kauto

Resolution tier for the output base image and layers. auto adapts to the input image while preserving each element's aspect ratio.

Max images2 to 10030

Maximum number of output images, including the base image. Higher values usually produce a finer decomposition. Above 30, images are always returned as URLs and sync_mode is ignored.

Enable text recognitionon or offoff

If True, formatted text layers include a rich-text OCR result in text_recognition.

Output formatjpeg or pngpng

Format of the base image. Separated layers always use PNG.

Watermarkon or offoff

Whether to add the provider's visible watermark.

Every API field of Seedream 5.5 Layerize is on its tool page: open its card above.

What can you do with Seedream 5.5 Layerize in OpenClaw?

Prepare incoming artwork for recurring design and review work. A scheduled agent can run Seedream 5.5 Layerize on each new image separately, organize the extracted assets, and flag results that need human review.

Rework a product promotion

Separate the product, headline, and decorative artwork from an existing promotion, then rearrange those assets in a design tool.

Prepare a poster for localization

Separate regular text from poster artwork and request text recognition. Use the results to rebuild translated text in an editor, checking font matches and line breaks.

Build an interactive illustration

Extract objects from a finished illustration and use their positions and stacking order to create selectable elements on a web canvas.

Prepare artwork for animation

Separate foreground objects and decorative elements from a static composition, then animate their movement in a separate animation tool.

Reuse illustrated assets

Extract individual animals, plants, or props from an illustration as transparent PNGs for placement in other layouts.

Remove an object from a composition

Separate the unwanted object and inspect the reconstructed base image. Recompose the remaining layers without the object in an editor.

Rearrange an interior concept

Separate selected furniture from a room image, then test different placements in a canvas editor using the returned layer bounds.

Questions about Seedream 5.5 Layerize in OpenClaw

Can OpenClaw use Seedream 5.5 Layerize?

Yes. Add Spiral to OpenClaw as an MCP server, and OpenClaw can find and run Seedream 5.5 Layerize like any built-in tool.

How much does Seedream 5.5 Layerize cost in OpenClaw?

$0.0156 per image. `image_size`: auto_1K $0.039, auto_1.5K $0.039, auto_1K $0.039, auto_1.5K $0.039, otherwise $0.05265, otherwise $0.05265 per image. Billed on `max_images`, default 30. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your OpenClaw plan is separate.

Do I need a fal account to use Seedream 5.5 Layerize in OpenClaw?

No. Spiral runs Seedream 5.5 Layerize on its own fal account. You sign in to Spiral once and never paste a key.

How long does it take to set up Seedream 5.5 Layerize in OpenClaw?

About two minutes: add the server, then sign in, then reload and check.

Does OpenClaw wait while Seedream 5.5 Layerize runs?

Seedream 5.5 Layerize runs in the background. OpenClaw starts the run, checks on it and gives you the image, json when it's ready.

What is Seedream 5.5 Layerize useful for?

Use it when a finished image needs separate, editable elements: product artwork, poster text, illustration objects, or decorative details. It returns a base image and PNG layers with positions and stacking order for recomposition.

Does Seedream 5.5 Layerize return exactly the number of layers requested?

The output count is a maximum. A request can return one base image and up to 99 layers, but the actual decomposition depends on the image and instructions.

What happens behind an object that gets separated?

The base image fills in the area behind the separated object. Inspect that reconstructed area before using the base image on its own.

Can Seedream 5.5 Layerize recover editable text?

It can return recognized text, positions, and approximate styling for regular text layers so an application can rebuild editable text. Artistic text and handwriting do not receive OCR results, and font matches need review.

Will every output layer have the same dimensions?

Each layer keeps its own aspect ratio and is sized according to the selected resolution tier. Use the returned placement information when rebuilding the composition rather than assuming every PNG covers the full canvas.

Get started

Start using Seedream 5.5 Layerize in OpenClaw

One Spiral account for every tool your agent needs. No subscription; you pay per run.

Paste this into OpenClaw:

Set up OpenClaw

set up https://spiral.ai/SKILL.md
Are you an AI agent? See setup options