[Integrations](https://spiral.ai/integrations) › [OpenClaw](https://spiral.ai/integrations/openclaw) › [Qwen Image Layered](https://spiral.ai/integrations/openclaw/qwen-image-layered)

# How to Use Qwen Image Layered in OpenClaw

Qwen Image Layered splits an existing image into transparent layers for separate layout and color edits. Choose it for standard decomposition; Qwen Image Layered LoRA adds custom adapter support.

|  |  |
| --- | --- |
| Model | Qwen Image Layered |
| Available through | fal |
| Category | Image |
| Price | $0.065 per image. |
| Returns | image |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Qwen Image Layered in OpenClaw

- Each Monday, use Qwen Image Layered to decompose each new image in the approved campaign feed into four layers. Include the source image and separate layer previews in the review.
- Every morning, use Qwen Image Layered on new product ads in the approved image feed. Request four layers and flag ads where the product remains combined with other content.
- Each Friday, use Qwen Image Layered to compare four-layer and eight-layer decompositions of the week's approved illustrations. Show both results for the designer to review.
- Every Tuesday, use Qwen Image Layered on new posters in the approved image feed with four output layers. Review whether text and objects separate and list the posters ready for layout edits.
- Every Monday at 9am: generate a product photo with Qwen Image Layered: a matte black water bottle on wet slate, soft morning light, 1:1. Tell me the price first.

## How to set up Qwen Image Layered 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:

```bash
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.

```bash
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.

```bash
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.

```bash
npx -y spiral-cli@latest init
```

### Call the Spiral API

1. **Create an API key**: In the console, under API keys.

2. **Run Qwen Image Layered**: One request; the result comes back by polling or a webhook.

```bash
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": "fal-ai/qwen-image-layered",
    "input": {
      "image_url": "https://v3b.fal.media/files/b/0a86d421/6xSMYtyW-fm2ciM6dHEgB.png"
    }
  }'
```

Then paste one of the prompts above: OpenClaw finds Qwen Image Layered on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/openclaw

## Qwen Image Layered tools and prices

- [Qwen Image Layered](https://spiral.ai/tools/fal/fal-ai/qwen-image-layered) (fal): $0.065 per image.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| prompt |  | — | A caption for the input image. |
| negative_prompt |  |  | The negative prompt to generate an image from. |
| num_inference_steps | 1 to 50 | 28 | The number of inference steps to perform. |
| guidance_scale | 1 to 20 | 5 | The guidance scale to use for the image generation. |
| seed |  | — | The same seed and the same prompt given to the same version of the model will output the same image every time. |
| num_layers | 1 to 10 | 4 | The number of layers to generate. |

## What can you do with Qwen Image Layered in OpenClaw?

Prepare new campaign images for later design revisions on a schedule. An always-on agent can decompose incoming images, collect layer previews, and flag results that need closer inspection.

### Reposition products in an ad

Decompose an existing product ad, inspect the product layer, then move it in an editor to make room for new copy.

### Prepare assets for motion design

Split a finished illustration into transparent layers, then animate selected layers with separate position and scale changes.

### Recolor isolated artwork

Separate a flattened illustration into layers, then recolor a selected layer in an editor while retaining the others.

### Rework a poster layout

Decompose a poster containing text and objects. Review their separation, then rearrange suitable layers for a revised composition.

### Resize an object within a scene

Extract layers from an existing scene, then adjust an isolated object's size without scaling the entire composition.

### Build a web layout from flattened artwork

Decompose an existing hero illustration and use suitable transparent layers as separately positioned image elements in the page.

### Prepare design handoffs

Turn a flattened campaign image into layers that a designer can inspect, reposition, and recolor during revisions.

## Overview

- [fal](https://spiral.ai/providers/fal)
- [All OpenClaw guides](https://spiral.ai/integrations/openclaw)

## Qwen Image Layered in other agents

- [Amp](https://spiral.ai/integrations/amp/qwen-image-layered)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/qwen-image-layered)
- [Claude](https://spiral.ai/integrations/claude-desktop/qwen-image-layered)
- [Claude Code](https://spiral.ai/integrations/claude-code/qwen-image-layered)
- [Cline](https://spiral.ai/integrations/cline/qwen-image-layered)
- [Codex](https://spiral.ai/integrations/codex/qwen-image-layered)
- [Cursor](https://spiral.ai/integrations/cursor/qwen-image-layered)
- [Devin](https://spiral.ai/integrations/devin/qwen-image-layered)
- [dots](https://spiral.ai/integrations/dots/qwen-image-layered)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/qwen-image-layered)
- [Gemini](https://spiral.ai/integrations/gemini/qwen-image-layered)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/qwen-image-layered)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/qwen-image-layered)
- [goose](https://spiral.ai/integrations/goose/qwen-image-layered)
- [Grok](https://spiral.ai/integrations/grok/qwen-image-layered)
- [Grok Build](https://spiral.ai/integrations/grok-build/qwen-image-layered)
- [Hermes](https://spiral.ai/integrations/hermes/qwen-image-layered)
- [Instinct](https://spiral.ai/integrations/instinct/qwen-image-layered)
- [Manus](https://spiral.ai/integrations/manus/qwen-image-layered)
- [Muse](https://spiral.ai/integrations/muse/qwen-image-layered)
- [Muse Code](https://spiral.ai/integrations/muse-code/qwen-image-layered)
- [n8n](https://spiral.ai/integrations/n8n/qwen-image-layered)
- [Notion](https://spiral.ai/integrations/notion/qwen-image-layered)
- [opencode](https://spiral.ai/integrations/opencode/qwen-image-layered)
- [Perplexity](https://spiral.ai/integrations/perplexity/qwen-image-layered)
- [Raycast](https://spiral.ai/integrations/raycast/qwen-image-layered)
- [VS Code](https://spiral.ai/integrations/vscode/qwen-image-layered)
- [Windsurf](https://spiral.ai/integrations/windsurf/qwen-image-layered)
- [Zapier](https://spiral.ai/integrations/zapier/qwen-image-layered)

## More OpenClaw guides

- [Qwen Image Image to Image](https://spiral.ai/integrations/openclaw/qwen-image-image-to-image)
- [Qwen Image Layered LoRA](https://spiral.ai/integrations/openclaw/qwen-image-layered-lora)
- [Qwen Image Edit Shirt Design](https://spiral.ai/integrations/openclaw/qwen-image-edit-shirt-design)
- [Recraft 20B](https://spiral.ai/integrations/openclaw/recraft-20b)
- [Qwen Image Edit Remove Lighting](https://spiral.ai/integrations/openclaw/qwen-image-edit-remove-lighting)
- [Recraft Creative Upscale](https://spiral.ai/integrations/openclaw/recraft-creative-upscale)

## Questions about Qwen Image Layered in OpenClaw

**Can OpenClaw use Qwen Image Layered?**

Yes. Add Spiral to OpenClaw as an MCP server, and OpenClaw can find and run Qwen Image Layered like any built-in tool.

**How much does Qwen Image Layered cost in OpenClaw?**

$0.065 per image. 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 Qwen Image Layered in OpenClaw?**

No. Spiral runs Qwen Image Layered on its own fal account. You sign in to Spiral once and never paste a key.

**How long does it take to set up Qwen Image Layered in OpenClaw?**

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

**Does OpenClaw wait while Qwen Image Layered runs?**

Qwen Image Layered runs in the background. OpenClaw starts the run, checks on it and gives you the image when it's ready.

**What does Qwen Image Layered produce?**

It splits an existing image into RGBA image layers with transparency. You can then manipulate individual layers in an editor.

**How should I write the prompt?**

Describe the image's overall content, including its objects, text, and arrangement. Qwen's instructions say the prompt does not explicitly assign content to individual layers.

**Can Qwen Image Layered create layered artwork from text alone?**

Qwen reports limited performance for text-only multilayer generation in the released model. Start with an existing image when preparing editable assets.

**Can I move or recolor one object after decomposition?**

Yes, when the object is separated into a suitable layer. Apply the change to that layer in an editor while leaving the other layers untouched.

**Can it separate text from a poster?**

Qwen's paper demonstrates separating text and objects into image layers. Inspect the returned layers before using them to rebuild a poster layout.

