[Integrations](https://spiral.ai/integrations) › [Muse Code](https://spiral.ai/integrations/muse-code) › [Bria Fast](https://spiral.ai/integrations/muse-code/bria-fast)

# How to Use Bria Fast in Muse Code

Bria Fast suits quick visual exploration for campaign concepts, illustrations, and website imagery. Choose it over Bria HD when you want to explore directions quickly; choose HD when native image detail matters more.

|  |  |
| --- | --- |
| Model | Bria Fast |
| Available through | fal |
| Category | Image |
| Price | $0.0364 per generation. Billed on `num_images`, default 4. |
| Returns | image |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Bria Fast in Muse Code

- Read the homepage copy and use Bria Fast to generate a 16:9 photograph of a small woodworking studio in morning window light. Put the workbench on the right and leave the left third uncluttered for the heading.
- Use Bria Fast to create a square illustration for the garden planning screen: raised vegetable beds viewed from above, muted green and brown colors, clear paths, no lettering. Match the palette in the project's styles.
- Use Bria Fast to generate a 16:9 landscape concept for the game's harbor level: low viewpoint, wooden docks in the foreground, stone warehouses behind, overcast morning. Save the seed and exact prompt beside the asset.
- Generate a product photo with Bria Fast: 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 Bria Fast.

## How to set up Bria Fast 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 Bria Fast**: 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/bria/text-to-image/fast",
    "input": {
      "prompt": "A lone figure stands on the edge of a serene cliff at sunset, gazing out over a vast, mystical valley. The figure is clad in flowing robes that ripple in the…"
    }
  }'
```

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

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

## Bria Fast tools and prices

- [Bria Fast · Text to Image](https://spiral.ai/tools/fal/fal-ai/bria/text-to-image/fast) (fal): $0.0364 per generation. Billed on `num_images`, default 4.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| negative_prompt |  |  | The negative prompt you would like to use to generate images. |
| num_images | 1 to 4 | 4 | How many images you would like to generate. When using any Guidance Method, Value is set to 1. |
| aspect_ratio | 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9 | 1:1 | The aspect ratio of the image. When a guidance method is being used, the aspect ratio is defined by the guidance image and this parameter is ignored. |
| seed | 0 to 2147483647 | — | The same seed and the same prompt given to the same version of the model will output the same image every time. |
| num_inference_steps | 4 to 10 | 8 | The number of iterations the model goes through to refine the generated image. This parameter is optional. |
| guidance_scale | 0 to 20 | 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. |

## What can you do with Bria Fast in Muse Code?

Bria lets a coding agent create website imagery and visual concepts from a project's written brief. Ask the agent to match the intended layout and keep generated artwork separate from page typography.

### Website hero imagery

Generate a scene with the subject on one side and open space for a headline. Specify the light direction and background materials before adding the image to a page.

### Campaign concept exploration

Explore different settings for the same campaign brief, such as a kitchen, garden, or studio. Compare the visual directions before choosing an image for closer review.

### Social post artwork

Create square still lifes or portrait scenes around a seasonal theme. Leave space for captions and add the final copy separately.

### Product concept scenes

Visualize an imagined product in a specific setting, such as a ceramic soap dispenser on a stone sink. Use these images to review presentation ideas before photographing the actual item.

### Game environment concepts

Turn a written location brief into a landscape or interior concept. Specify viewpoint, weather, materials, and lighting so the image communicates a clear art direction.

### Composition studies from references

Use an existing image's edges or depth to guide a new scene. Explore different materials and lighting while using the reference to direct the layout.

## Overview

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

## Bria Fast in other agents

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

## More Muse Code guides

- [Bria FIBO Edit 1.5 Expand](https://spiral.ai/integrations/muse-code/bria-fibo-edit-1-5-expand)
- [Bria Fibo](https://spiral.ai/integrations/muse-code/bria-fibo)
- [Bria Extract Object](https://spiral.ai/integrations/muse-code/bria-extract-object)
- [Bria GenFill](https://spiral.ai/integrations/muse-code/bria-genfill)
- [Bria Expand](https://spiral.ai/integrations/muse-code/bria-expand)
- [Bria GenFill v2](https://spiral.ai/integrations/muse-code/bria-genfill-v2)

## Questions about Bria Fast in Muse Code

**Can Muse Code use Bria Fast?**

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

**How much does Bria Fast cost in Muse Code?**

$0.0364 per generation. Billed on `num_images`, default 4. 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 Bria Fast in Muse Code?**

No. Spiral runs Bria Fast on its own fal account. You sign in to Spiral once and never paste a key.

**How long does it take to set up Bria Fast in Muse Code?**

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

**Does Muse Code wait while Bria Fast runs?**

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

**When should I choose Bria Fast or Bria HD?**

Choose Bria Fast to explore visual directions quickly. Choose Bria HD when native detail is the priority, such as inspecting surfaces, lighting, and scene texture.

**How should I write a Bria prompt?**

Describe the subject, setting, framing, light direction, and visible materials. A description such as matte ceramic beside a window gives clearer direction than a stack of words such as masterpiece or stunning.

**Which language should I use for Bria prompts?**

Write prompts in English and avoid special characters. Translate a non-English brief into a concrete English scene description before generating.

**Can Bria reproduce an image I generated earlier?**

Yes, the documentation states that the same prompt and seed on the same model version produce the same image. Save the exact prompt and seed with an image you want to reproduce.

**Can a reference image guide Bria's composition?**

Yes. Use edge guidance for structural outlines or depth guidance for spatial arrangement; when combining guidance images, make sure their aspect ratios match.

