How to Use Qwen Image Layered in Muse Code
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.
Prompts to try with Qwen Image Layered in Muse Code
Copy an example into Muse Code, or ask in your own words.
Use Qwen Image Layered on the hero illustration in this project with four output layers. Caption the existing scene, save the layers, and build a preview with visibility toggles for each one.
Use Qwen Image Layered on the campaign poster in the assets directory. Request four layers, inspect whether text and objects separate, and build a page where I can reposition suitable layers.
Use Qwen Image Layered on the onboarding illustration with four output layers. Show each transparent layer separately, then add a scale control for the layer containing the main character.
Use Qwen Image Layered on the splash illustration twice, requesting four layers and then eight. Create a comparison view so I can choose the better separation before adding animation.
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. Save the result in ./assets.
How to set up Qwen Image Layered in Muse Code
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- Install Muse Code
curl -fsSL https://dev.meta.ai/install.sh | bash
- Ask Muse to add the server
Start muse and ask:
Add the Spiral MCP server at https://api.spiral.ai/mcp
- Sign in
In your terminal, run:
muse mcp login spiral
Use the Spiral skill
- Send Muse Code this message
Your agent reads Spiral's skill and sets itself up.
set up https://spiral.ai/SKILL.md
- Sign in or paste a key
Approve Spiral in the browser, or give the agent a key from the console.
Use the Spiral CLI
- 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
- Create an API key
In the console, under API keys.
- Run Qwen Image Layered
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": "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: Muse Code finds Qwen Image Layered on Spiral, shows the price and runs it.
Qwen Image Layered providers and prices
Spiral runs Qwen Image Layered through fal. Open a card for today's price, with every fee included.
Settings you can ask for
Qwen Image Layered works from your prompt and image URL. Ask Muse Code for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Negative prompt | what to leave out, in words | The negative prompt to generate an image from. | |
| Number of 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 | a whole number | The same seed and the same prompt given to the same version of the model will output the same image every time. | |
| Number of layers | 1 to 10 | 4 | The number of layers to generate. |
| Output format | png or webp | png | The format of the generated image. |
| Acceleration | none, regular, or high | regular | The acceleration level to use. |
Every API field of Qwen Image Layered is on its tool page: open its card above.
What can you do with Qwen Image Layered in Muse Code?
Turn flattened project artwork into separately positioned visual assets. A coding agent can inspect the returned layers, build a composition preview, and add movement or layout controls around suitable layers.
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.
More on Qwen Image Layered and Muse Code
Overview
Qwen Image Layered in other agents
Questions about Qwen Image Layered in Muse Code
Can Muse Code use Qwen Image Layered?
Yes. Add Spiral to Muse Code as an MCP server, and Muse Code can find and run Qwen Image Layered like any built-in tool.
How much does Qwen Image Layered cost in Muse Code?
$0.065 per image. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Muse Code plan is separate.
Do I need a fal account to use Qwen Image Layered in Muse Code?
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 Muse Code?
About two minutes: install Muse Code, then ask Muse to add the server, then sign in.
Does Muse Code wait while Qwen Image Layered runs?
Qwen Image Layered runs in the background. Muse Code 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.
Start using Qwen Image Layered in Muse Code
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Muse Code:
set up https://spiral.ai/SKILL.md


