[Integrations](https://spiral.ai/integrations) › [Claude Code](https://spiral.ai/integrations/claude-code) › [Muse Image Text to Image](https://spiral.ai/integrations/claude-code/muse-image-text-to-image)

# How to Use Muse Image Text to Image in Claude Code

Muse Image Text to Image turns written briefs into illustrations, campaign concepts, and images with short lettering. Unlike Muse Image Edit, it starts from a description rather than an existing image.

|  |  |
| --- | --- |
| Model | Muse Image Text to Image |
| Available through | fal |
| Category | Image |
| Price | $0.013 per image. Billed on `num_images`, default 1. |
| Returns | image |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Muse Image Text to Image in Claude Code

- Read the homepage brief in this project and use Muse Image Text to Image to create a wide editorial illustration of a bicycle repair bench. Put the tools on the right and leave the left third empty for the page headline; include no lettering.
- Read the project's event brief and use Muse Image Text to Image to create a portrait poster concept. Render only the headline 'Night ride' in large lettering above a cyclist under streetlights, then inspect the spelling.
- Use Muse Image Text to Image to create a square watercolor illustration for the project's empty search state: a fox looking into an empty wooden box, pale background, centered composition, and no text.
- Generate a product photo with Muse Image Text to Image: a matte black water bottle on wet slate, soft morning light, 1:1. Tell me the price first. Save the result in ./assets.
- Make four logo concepts for a coffee brand called "Northline" with Muse Image Text to Image.

## How to set up Muse Image Text to Image in Claude Code

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

### Use Spiral's MCP server

1. **Add the hosted server**: This adds Spiral to the current project. Add `--scope user` to use it in every project.

```bash
claude mcp add --transport http spiral https://api.spiral.ai/mcp
```

2. **Sign in**: Start `claude`, type `/mcp`, choose spiral and Authenticate. Sign in to Spiral in the browser and click Authorize. No API key.

### Use the Spiral skill

1. **Send Claude Code 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 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 Muse Image Text to Image**: 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": "meta/muse-image/text-to-image",
    "input": {
      "prompt": "A cinematic editorial portrait in soft window light with crisp typography"
    }
  }'
```

Then paste one of the prompts above: Claude Code finds Muse Image Text to Image on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/claude-code

## Muse Image Text to Image tools and prices

- [Meta Muse Image Text to Image](https://spiral.ai/tools/fal/meta/muse-image/text-to-image) (fal): $0.013 per image. Billed on `num_images`, default 1.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| aspect_ratio |  | — | Any custom output aspect ratio as "width:height", for example "16:9", "5:4", or "1920:1200". Common presets are "21:9", "16:9", "4:3", "3:2", "1:1", "2:3", "3:4", "9:16", "9:21". The ratio must be between 1:16 and 16:1, the range Muse supports. Only the ratio is used: Muse renders it at its own fixed resolution of roughly 2.5 megapixels, so "1920:1200" and "960:600" both return the same 1920x1200 image. If omitted, Muse chooses the output dimensions automatically. |
| num_images | 1 to 10 | 1 | The number of images to generate. |
| output_format | jpeg, png, webp | webp | The format of the generated image. |

## What can you do with Muse Image Text to Image in Claude Code?

Create image assets from project briefs and turn visual feedback into concrete revisions. Muse Image can support website artwork, illustrated documentation, and campaign mockups with specific composition and short lettering.

### Campaign concept boards

Explore a written campaign idea with Muse Image Text to Image, or develop supplied campaign artwork with Muse Image Edit. Specify the composition, palette, and short headline.

### Editorial illustrations

Create an illustration from an article brief or rework an existing illustration. Describe the central metaphor and the visual style instead of asking for a generic image about the topic.

### Event poster concepts

Build a poster from a written brief or revise supplied poster artwork. Keep the title short and check the rendered wording before approving it.

### Comic artwork

Use Muse Image Text to Image for initial character sheets and scene concepts. Use Muse Image Edit with approved references for continuing panels and short speech bubbles.

### Website illustration concepts

Generate artwork from a website brief or adapt supplied artwork for a new composition. Specify where the subject belongs and where the design needs empty space.

### Product scene concepts

Visualize a described product in a studio scene with Muse Image Text to Image. Use Muse Image Edit when an existing product image must guide the result.

## Overview

- [fal](https://spiral.ai/providers/fal)
- [All Claude Code guides](https://spiral.ai/integrations/claude-code)

## Muse Image Text to Image in other agents

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

## More Claude Code guides

- [Muse Image Edit](https://spiral.ai/integrations/claude-code/muse-image-edit)
- [NAFNet Deblur](https://spiral.ai/integrations/claude-code/nafnet-deblur)
- [MiniMax Image-01 Subject Reference](https://spiral.ai/integrations/claude-code/minimax-image-01-subject-reference)
- [NAFNet Denoise](https://spiral.ai/integrations/claude-code/nafnet-denoise)
- [MiniMax Image-01](https://spiral.ai/integrations/claude-code/minimax-image-01)
- [Nano Banana](https://spiral.ai/integrations/claude-code/nano-banana)

## Questions about Muse Image Text to Image in Claude Code

**Can Claude Code use Muse Image Text to Image?**

Yes. Add Spiral to Claude Code as an MCP server, and Claude Code can find and run Muse Image Text to Image like any built-in tool.

**How much does Muse Image Text to Image cost in Claude Code?**

$0.013 per image. Billed on `num_images`, default 1. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Claude Code plan is separate.

**Do I need a fal account to use Muse Image Text to Image in Claude Code?**

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

**How long does it take to set up Muse Image Text to Image in Claude Code?**

About two minutes: add the hosted server, then sign in.

**Does Claude Code wait while Muse Image Text to Image runs?**

Muse Image Text to Image runs in the background. Claude Code starts the run, checks on it and gives you the image when it's ready.

**What is Muse Image good at?**

Muse Image suits briefs that combine a clear subject, deliberate composition, and short lettering. Useful starting points include campaign artwork, editorial illustrations, and comic panels.

**Can Muse Image put readable text in an image?**

Yes, but exact lettering can vary between attempts. Keep the wording short, spell it out exactly, and check every word before using the image.

**What resolution does Muse Image produce?**

The documented output is roughly 2.5 megapixels. Requested dimensions control the image's proportions rather than guaranteeing that exact pixel size.

**How should I write a Muse Image prompt?**

Describe the subject, arrangement, visual style, and lighting in concrete terms. For lettering, provide the exact words and explain which text should be most prominent.

**Will repeating a Muse Image prompt reproduce the same image?**

Treat a repeated request as another attempt rather than an exact copy. For a continuing series, keep an approved reference and use Muse Image Edit to guide subsequent images.

