[Integrations](https://spiral.ai/integrations) › [Muse Code](https://spiral.ai/integrations/muse-code) › [FLUX.2 Klein 9B LoRA](https://spiral.ai/integrations/muse-code/flux-2-klein-9b-lora)

# How to Use FLUX.2 Klein 9B LoRA in Muse Code

FLUX.2 Klein 9B LoRA creates images from text with a custom LoRA for a learned style or concept. Choose it over FLUX.2 Klein 9B when your brief needs that specific adaptation.

|  |  |
| --- | --- |
| Model | FLUX.2 Klein 9B LoRA |
| Available through | fal |
| Category | Image |
| Price | $0.0195 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.2 Klein 9B LoRA in Muse Code

- Use FLUX.2 Klein 9B LoRA with the project's selected style adapter to draft a 1024 × 1024 blog illustration. Show a lone commuter waiting under a station roof as rain gathers in shallow puddles. Place the figure to the right, with a warm lamp above and distant tracks fading into gray morning light.
- Generate a product photo with FLUX.2 Klein 9B LoRA: 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 FLUX.2 Klein 9B LoRA.
- Create a 16:9 hero image of a quiet mountain cabin at dusk with FLUX.2 Klein 9B LoRA.
- Generate a 9:16 poster with FLUX.2 Klein 9B LoRA for a jazz night called "Blue Hour", deep navy and brass tones.

## How to set up FLUX.2 Klein 9B LoRA 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.2 Klein 9B LoRA**: 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-2/klein/9b/lora",
    "input": {
      "prompt": "A bright, surreal scene on a vast white salt flat under a clear blue sky, featuring two fluffy white alpacas standing in the foreground. Behind them sits a…"
    }
  }'
```

Then paste one of the prompts above: Muse Code finds FLUX.2 Klein 9B LoRA on Spiral, shows the price and runs it.

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

## FLUX.2 Klein 9B LoRA tools and prices

- [FLUX.2 \[klein\] 9B LoRA · Text to Image](https://spiral.ai/tools/fal/fal-ai/flux-2/klein/9b/lora) (fal): $0.0195 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 |
| --- | --- | --- | --- |
| seed |  | — | The seed to use for the generation. If not provided, a random seed will be used. |
| num_inference_steps | 4 to 8 | 4 | The number of inference steps to perform. |
| image_size |  | landscape_4_3 | The size of the image to generate. |
| num_images | 1 to 4 | 1 | The number of images to generate. |
| output_format | jpeg, png, webp | png | The format of the generated image. |
| loras |  | [] | List of LoRA weights to apply (maximum 3). |

## What can you do with FLUX.2 Klein 9B LoRA in Muse Code?

Create artwork drafts that fit the pages and features in your project. A coding agent can turn repository copy into image briefs and place the chosen assets in the site.

### Website artwork drafts

Turn a page brief into a scene with room for a headline. Compare composition and lighting before choosing artwork for the page.

### Editorial illustrations

Translate an article's central idea into a visual metaphor, such as a crowded workbench for an essay about information overload.

### Product concept scenes

Describe an imagined product, its materials, and its surroundings to explore presentation ideas before a photo shoot or physical prototype.

### Campaign art exploration

Create alternative scenes for the same campaign brief. Keep the subject constant while comparing framing, backgrounds, or lighting.

### Game environment concepts

Explore a location's mood through written descriptions of terrain, architecture, weather, and light. Use the results as visual direction for an artist.

### Presentation illustrations

Create one clear scene for a slide, with the subject placed away from the area reserved for your explanation. Add slide text afterward.

### Custom illustration styles

Use FLUX.2 Klein 9B LoRA with a suitable trained style adapter to create new scenes in a learned visual style.

## Overview

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

## FLUX.2 Klein 9B LoRA in other agents

- [Amp](https://spiral.ai/integrations/amp/flux-2-klein-9b-lora)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/flux-2-klein-9b-lora)
- [Claude](https://spiral.ai/integrations/claude-desktop/flux-2-klein-9b-lora)
- [Claude Code](https://spiral.ai/integrations/claude-code/flux-2-klein-9b-lora)
- [Cline](https://spiral.ai/integrations/cline/flux-2-klein-9b-lora)
- [Codex](https://spiral.ai/integrations/codex/flux-2-klein-9b-lora)
- [Cursor](https://spiral.ai/integrations/cursor/flux-2-klein-9b-lora)
- [Devin](https://spiral.ai/integrations/devin/flux-2-klein-9b-lora)
- [dots](https://spiral.ai/integrations/dots/flux-2-klein-9b-lora)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/flux-2-klein-9b-lora)
- [Gemini](https://spiral.ai/integrations/gemini/flux-2-klein-9b-lora)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/flux-2-klein-9b-lora)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/flux-2-klein-9b-lora)
- [goose](https://spiral.ai/integrations/goose/flux-2-klein-9b-lora)
- [Grok](https://spiral.ai/integrations/grok/flux-2-klein-9b-lora)
- [Grok Build](https://spiral.ai/integrations/grok-build/flux-2-klein-9b-lora)
- [Hermes](https://spiral.ai/integrations/hermes/flux-2-klein-9b-lora)
- [Instinct](https://spiral.ai/integrations/instinct/flux-2-klein-9b-lora)
- [Manus](https://spiral.ai/integrations/manus/flux-2-klein-9b-lora)
- [Muse](https://spiral.ai/integrations/muse/flux-2-klein-9b-lora)
- [n8n](https://spiral.ai/integrations/n8n/flux-2-klein-9b-lora)
- [Notion](https://spiral.ai/integrations/notion/flux-2-klein-9b-lora)
- [OpenClaw](https://spiral.ai/integrations/openclaw/flux-2-klein-9b-lora)
- [opencode](https://spiral.ai/integrations/opencode/flux-2-klein-9b-lora)
- [Perplexity](https://spiral.ai/integrations/perplexity/flux-2-klein-9b-lora)
- [Raycast](https://spiral.ai/integrations/raycast/flux-2-klein-9b-lora)
- [VS Code](https://spiral.ai/integrations/vscode/flux-2-klein-9b-lora)
- [Windsurf](https://spiral.ai/integrations/windsurf/flux-2-klein-9b-lora)
- [Zapier](https://spiral.ai/integrations/zapier/flux-2-klein-9b-lora)

## More Muse Code guides

- [FLUX.2 Klein 9B Base LoRA](https://spiral.ai/integrations/muse-code/flux-2-klein-9b-base-lora)
- [FLUX.2 LoRA](https://spiral.ai/integrations/muse-code/flux-2-lora)
- [FLUX.2 Klein 9B Base](https://spiral.ai/integrations/muse-code/flux-2-klein-9b-base)
- [FLUX.2 LoRA Edit](https://spiral.ai/integrations/muse-code/flux-2-lora-edit)
- [FLUX.2 Klein 9B](https://spiral.ai/integrations/muse-code/flux-2-klein-9b)
- [FLUX.2 Max](https://spiral.ai/integrations/muse-code/flux-2-max)

## Questions about FLUX.2 Klein 9B LoRA in Muse Code

**Can Muse Code use FLUX.2 Klein 9B LoRA?**

Yes. Add Spiral to Muse Code as an MCP server, and Muse Code can find and run FLUX.2 Klein 9B LoRA like any built-in tool.

**How much does FLUX.2 Klein 9B LoRA cost in Muse Code?**

$0.0195 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.2 Klein 9B LoRA in Muse Code?**

No. Spiral runs FLUX.2 Klein 9B LoRA 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.2 Klein 9B LoRA 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.2 Klein 9B LoRA runs?**

FLUX.2 Klein 9B LoRA runs in the background. Muse Code starts the run, checks on it and gives you the image when it's ready.

**What is FLUX.2 Klein 9B good for?**

Use it to explore visual ideas, draft illustrations, and compare compositions from a written brief. Black Forest Labs positions Klein for rapid prototyping, previews, and high-volume image generation.

**How should I write a prompt for FLUX.2 Klein 9B?**

Describe a scene in connected prose: the subject, setting, framing, and lighting. Black Forest Labs suggests roughly 40 to 70 words, with particular attention to the light source and atmosphere.

**Does FLUX.2 Klein expand a short prompt automatically?**

No. Include the visual details you care about in your own description, such as the material of an object, its position, and the direction of the light.

**Can I trust text inside a generated image?**

Check every word before using it. Black Forest Labs warns that generated text can be inaccurate or distorted, so consider adding important headlines and labels afterward.

**What image size is a documented starting point?**

Black Forest Labs demonstrates 1024 × 1024 output with four inference steps. That is a useful starting point for square illustrations and concept drafts.

