[Integrations](https://spiral.ai/integrations) › [Muse Code](https://spiral.ai/integrations/muse-code) › [FLUX.1 Dev](https://spiral.ai/integrations/muse-code/flux-1-dev)

# How to Use FLUX.1 Dev in Muse Code

FLUX.1 Dev turns written descriptions into images for editorial illustrations, product concepts, and scene studies. Black Forest Labs places its image quality below FLUX.1 Pro, with adjustable guidance and generation steps for refining results.

|  |  |
| --- | --- |
| Model | FLUX.1 Dev |
| Available through | fal |
| Category | Image |
| Price | $0.0325 per megapixel. `image_size` presets count as 1 MP; custom sizes round up to whole megapixels. Billed on `num_images`, default 1. |
| Returns | image |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with FLUX.1 Dev in Muse Code

- Read the homepage copy and design tokens, then use FLUX.1 Dev to create a 1360 × 768 illustration of a paper boat crossing a calm lake at dawn. Match the project's colors, place the boat on the right, and leave open water on the left for the heading.
- Use FLUX.1 Dev to create a 1024 × 1024 illustration for the project's empty search state: a small red squirrel examining an empty wooden basket, soft pencil shading, simple white background. Add the selected image to the component and write descriptive alt text.
- Read the game's location notes and use FLUX.1 Dev to create a 1360 × 768 environment study of the harbor. Show the viewpoint from the pier, weathered wooden buildings, overcast light, and the architectural details described in the notes.
- Use FLUX.1 Dev to create a 1024 × 1024 fictional product concept for the ceramic desk lamp described in the project brief. Show matte clay, a curved shade, and soft side lighting. Start at 30 steps with guidance 3.5 and save the result for design review.
- Read the latest blog draft and use FLUX.1 Dev to create a 1360 × 768 editorial illustration of its main idea. Write a concrete scene description from the article, keep lettering out of the composition, and compare results at 30 and 50 steps.

## How to set up FLUX.1 Dev in Muse Code

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

### Use Spiral's MCP server

1. **Install Muse Code**

```bash
curl -fsSL https://dev.meta.ai/install.sh | bash
```

2. **Ask Muse to add the server**: Start `muse` and ask:

```text
Add the Spiral MCP server at https://api.spiral.ai/mcp
```

3. **Sign in**: In your terminal, run:

```bash
muse mcp login spiral
```

### Use the Spiral skill

1. **Send Muse 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 FLUX.1 Dev**: 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/flux-1/dev",
    "input": {
      "prompt": "Extreme close-up of a single tiger eye, direct frontal view. Detailed iris and pupil. Sharp focus on eye texture and color. Natural lighting to capture…"
    }
  }'
```

Then paste one of the prompts above: Muse Code finds FLUX.1 Dev on Spiral, shows the price and runs it.

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

## FLUX.1 Dev tools and prices

- [FLUX.1 \[dev\] · Text to Image](https://spiral.ai/tools/fal/fal-ai/flux-1/dev) (fal): $0.0325 per megapixel. `image_size` presets count as 1 MP; custom sizes round up to whole megapixels. Billed on `num_images`, default 1.
- [FLUX.1 \[dev\] · Text to Image](https://spiral.ai/tools/fal/fal-ai/flux/dev) (fal): $0.0325 per megapixel. `image_size` presets count as 1 MP; custom sizes round up to whole megapixels. Billed on `num_images`, default 1.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| image_size |  | landscape_4_3 | The size of the generated image. |
| num_inference_steps | 1 to 50 | 28 | The number of inference steps to perform. |
| seed |  | — | The same seed and the same prompt given to the same version of the model will output the same image every time. |
| guidance_scale | 1 to 20 | 3.5 | The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you. |
| num_images | 1 to 4 | 1 | The number of images to generate. |
| output_format | jpeg, png | jpeg | The format of the generated image. |

## What can you do with FLUX.1 Dev in Muse Code?

Create original artwork that matches a project's written design brief. A coding agent can use project files to describe the scene, generate images with FLUX.1 Dev, and place the selected artwork in the interface.

### Article illustrations

Turn an article's central idea into a visual metaphor, such as a tangled garden hose representing a complicated workflow.

### Website artwork

Create an original scene from a written brief, specifying the subject's placement and leaving room for a heading.

### Fictional product concepts

Explore a proposed object's shape, materials, and lighting before commissioning a prototype or arranging a photo shoot.

### Game environment studies

Develop visual directions for a location by describing its architecture, weather, time of day, and camera position.

### Cover artwork

Draft an illustrated book or podcast cover from a scene description, reserving space for lettering added during layout.

### Interior design studies

Compare written room concepts with different furniture, materials, and light. Use the results to discuss appearance during planning.

### Campaign visual exploration

Try several compositions for one campaign brief, keeping the subject and palette explicit while changing one creative choice at a time.

## Overview

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

## FLUX.1 Dev in other agents

- [Amp](https://spiral.ai/integrations/amp/flux-1-dev)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/flux-1-dev)
- [Claude](https://spiral.ai/integrations/claude-desktop/flux-1-dev)
- [Claude Code](https://spiral.ai/integrations/claude-code/flux-1-dev)
- [Cline](https://spiral.ai/integrations/cline/flux-1-dev)
- [Codex](https://spiral.ai/integrations/codex/flux-1-dev)
- [Cursor](https://spiral.ai/integrations/cursor/flux-1-dev)
- [Devin](https://spiral.ai/integrations/devin/flux-1-dev)
- [dots](https://spiral.ai/integrations/dots/flux-1-dev)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/flux-1-dev)
- [Gemini](https://spiral.ai/integrations/gemini/flux-1-dev)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/flux-1-dev)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/flux-1-dev)
- [goose](https://spiral.ai/integrations/goose/flux-1-dev)
- [Grok](https://spiral.ai/integrations/grok/flux-1-dev)
- [Grok Build](https://spiral.ai/integrations/grok-build/flux-1-dev)
- [Hermes](https://spiral.ai/integrations/hermes/flux-1-dev)
- [Instinct](https://spiral.ai/integrations/instinct/flux-1-dev)
- [Manus](https://spiral.ai/integrations/manus/flux-1-dev)
- [Muse](https://spiral.ai/integrations/muse/flux-1-dev)
- [n8n](https://spiral.ai/integrations/n8n/flux-1-dev)
- [Notion](https://spiral.ai/integrations/notion/flux-1-dev)
- [OpenClaw](https://spiral.ai/integrations/openclaw/flux-1-dev)
- [opencode](https://spiral.ai/integrations/opencode/flux-1-dev)
- [Perplexity](https://spiral.ai/integrations/perplexity/flux-1-dev)
- [Raycast](https://spiral.ai/integrations/raycast/flux-1-dev)
- [VS Code](https://spiral.ai/integrations/vscode/flux-1-dev)
- [Windsurf](https://spiral.ai/integrations/windsurf/flux-1-dev)
- [Zapier](https://spiral.ai/integrations/zapier/flux-1-dev)

## More Muse Code guides

- [FLUX Kontext LoRA Text to Image](https://spiral.ai/integrations/muse-code/flux-kontext-lora-text-to-image)
- [FLUX.1 Dev LoRA](https://spiral.ai/integrations/muse-code/flux-1-dev-lora)
- [FLUX 3 Klein Text to Image](https://spiral.ai/integrations/muse-code/flux-3-klein-text-to-image)
- [FLUX.1 Kontext Max](https://spiral.ai/integrations/muse-code/flux-1-kontext-max)
- [FLUX 3 Klein Image Edit](https://spiral.ai/integrations/muse-code/flux-3-klein-image-edit)
- [FLUX.1 Kontext Max Multi](https://spiral.ai/integrations/muse-code/flux-1-kontext-max-multi)

## Questions about FLUX.1 Dev in Muse Code

**Can Muse Code use FLUX.1 Dev?**

Yes. Add Spiral to Muse Code as an MCP server, and Muse Code can find and run FLUX.1 Dev like any built-in tool.

**How much does FLUX.1 Dev cost in Muse Code?**

$0.0325 per megapixel. `image_size` presets count as 1 MP; custom sizes round up to whole megapixels. 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 Muse Code plan is separate.

**Do I need a fal account to use FLUX.1 Dev in Muse Code?**

No. Spiral runs FLUX.1 Dev on its own fal account. You sign in to Spiral once and never paste a key.

**How long does it take to set up FLUX.1 Dev in Muse Code?**

About two minutes: install Muse Code, then ask Muse to add the server, then sign in.

**Does Muse Code wait while FLUX.1 Dev runs?**

FLUX.1 Dev runs in the background. Muse Code starts the run, checks on it and gives you the image when it's ready.

**What should I use FLUX.1 Dev for?**

Use it to turn a written visual brief into an image. Practical starting points include article illustrations, fictional product concepts, scene studies, and website artwork.

**What image resolution does FLUX.1 Dev support?**

Black Forest Labs describes FLUX.1 as supporting different aspect ratios and resolutions from 0.1 to 2.0 megapixels. For a starting point, try a 1024 × 1024 square.

**How should I write a FLUX.1 Dev prompt?**

Write a short visual description in complete sentences. Name the subject, its action, the setting, lighting, and desired medium; describe what should appear using positive language.

**How long can a FLUX.1 Dev prompt be?**

Its T5 encoder supports up to 512 tokens. Treat that as a ceiling: start with a focused paragraph and add details only when they help define the image.

**Should I increase guidance to improve FLUX.1 Dev results?**

Start around 3.5 and inspect the result before increasing it. Higher guidance encourages closer adherence to the prompt, but it can reduce image quality.

