[Integrations](https://spiral.ai/integrations) › [Instinct](https://spiral.ai/integrations/instinct) › [FLUX.2 Klein 9B Base LoRA](https://spiral.ai/integrations/instinct/flux-2-klein-9b-base-lora)

# How to Use FLUX.2 Klein 9B Base LoRA in Instinct

FLUX.2 Klein 9B Base LoRA generates images from text with custom style adapters. It adds LoRA adaptation to FLUX.2 Klein 9B Base, making it useful when a project calls for a trained visual style.

|  |  |
| --- | --- |
| Model | FLUX.2 Klein 9B Base LoRA |
| Available through | fal |
| Category | Image |
| Price | $0.02054 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, with a Spiral API key |

## Prompts to try with FLUX.2 Klein 9B Base LoRA in Instinct

- Every month, use FLUX.2 Klein 9B Base LoRA with the selected compatible campaign style adapter to create a square cycling illustration, 1024 pixels on each side. Choose a seasonal setting and describe the rider, weather, and composition.
- Every Monday at 9am: generate a product photo with FLUX.2 Klein 9B Base LoRA: a matte black water bottle on wet slate, soft morning light, 1:1. Tell me the price first.
- Make four logo concepts for a coffee brand called "Northline" with FLUX.2 Klein 9B Base LoRA.
- Create a 16:9 hero image of a quiet mountain cabin at dusk with FLUX.2 Klein 9B Base LoRA.
- Generate a 9:16 poster with FLUX.2 Klein 9B Base LoRA for a jazz night called "Blue Hour", deep navy and brass tones.

## How to set up FLUX.2 Klein 9B Base LoRA in Instinct

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

### Use the Spiral skill

1. **Send Instinct 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 Spiral's MCP server

1. **Create an API key**: In the console, open API keys and create a key for Instinct. Copy it.

2. **Send Instinct this message**: Instinct reads Spiral's skill and asks for your API key.

```text
set up https://spiral.ai/SKILL.md
```

3. **Give Instinct the key**: When Instinct asks for the key, add it where Instinct keeps secrets, never in the chat itself.

### 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 Base 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/base/lora",
    "input": {
      "prompt": "A serene Japanese garden with cherry blossoms, koi pond, and traditional wooden bridge at golden hour"
    }
  }'
```

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

Setup guide in the docs: https://spiral.ai/docs/quickstarts/instinct

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

- [FLUX.2 \[klein\] 9B Base LoRA · Text to Image](https://spiral.ai/tools/fal/fal-ai/flux-2/klein/9b/base/lora) (fal): $0.02054 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 |
| --- | --- | --- | --- |
| negative_prompt |  |  | Negative prompt for classifier-free guidance. Describes what to avoid in the image. |
| guidance_scale | 0 to 20 | 5 | Guidance scale for classifier-free guidance. |
| seed |  | — | The seed to use for the generation. If not provided, a random seed will be used. |
| num_inference_steps | 4 to 50 | 28 | 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. |

## What can you do with FLUX.2 Klein 9B Base LoRA in Instinct?

Prepare recurring image drafts from a standing editorial or campaign brief. An agent running on a schedule can create fresh scene concepts and collect them for review.

### Website artwork from a written brief

Generate a photographic or illustrated scene with the subject placed away from the area reserved for a headline. Explore several compositions before choosing artwork for the page.

### Product concept images

Describe a proposed product's shape, materials, color, and studio lighting. Use the images to discuss a design direction before arranging a real shoot.

### Editorial illustrations

Turn an article's central idea into a specific visual scene. Name the medium, focal subject, and mood so the image serves the story.

### Photography mood boards

Explore a planned shoot through descriptions of lenses, lighting, framing, and textures. Compare close-ups, environmental scenes, and different lighting directions.

### Poster concepts

Draft a poster around one short headline and a clearly described illustration. Specify where the lettering belongs, then proofread the generated text.

### Color direction studies

Compare product or scene concepts by assigning hex colors to named surfaces. Review the rendered colors before approving a direction.

### Campaign concept exploration

Generate alternative scenes from the same campaign brief, changing the setting or composition. Use the results to select a visual direction for further production.

## Overview

- [fal](https://spiral.ai/providers/fal)
- [All Instinct guides](https://spiral.ai/integrations/instinct)

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

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

## More Instinct guides

- [FLUX.2 Klein 9B Base](https://spiral.ai/integrations/instinct/flux-2-klein-9b-base)
- [FLUX.2 Klein 9B LoRA](https://spiral.ai/integrations/instinct/flux-2-klein-9b-lora)
- [FLUX.2 Klein 9B](https://spiral.ai/integrations/instinct/flux-2-klein-9b)
- [FLUX.2 LoRA](https://spiral.ai/integrations/instinct/flux-2-lora)
- [FLUX.2 Klein 4B LoRA](https://spiral.ai/integrations/instinct/flux-2-klein-4b-lora)
- [FLUX.2 LoRA Edit](https://spiral.ai/integrations/instinct/flux-2-lora-edit)

## Questions about FLUX.2 Klein 9B Base LoRA in Instinct

**Can Instinct use FLUX.2 Klein 9B Base LoRA?**

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

**How much does FLUX.2 Klein 9B Base LoRA cost in Instinct?**

$0.02054 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 Instinct plan is separate.

**Do I need a fal account to use FLUX.2 Klein 9B Base LoRA in Instinct?**

You need no fal account. Instinct uses one Spiral API key for every tool, and Spiral runs FLUX.2 Klein 9B Base LoRA on its own fal account.

**How long does it take to set up FLUX.2 Klein 9B Base LoRA in Instinct?**

About two minutes: create an API key, then send Instinct this message, then give Instinct the key.

**Does Instinct wait while FLUX.2 Klein 9B Base LoRA runs?**

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

**What is FLUX.2 Klein 9B Base good at?**

Use it to explore different visual directions from a written brief, including photographic scenes and illustrated concepts. Black Forest Labs reports greater output diversity than with distilled Klein models.

**How is Base different from distilled Klein?**

Base keeps the undistilled model for creative exploration and customization. Distilled Klein is the speed-focused choice; Base favors flexibility and visual diversity.

**How should I write a prompt?**

Write a short scene description that names the subject, setting, composition, and lighting. Klein does not automatically expand a vague prompt, so include the details that should appear in the image.

**Can I trust text inside the image?**

Check every word before using it. Lettering can be inaccurate or distorted, so treat text-heavy output as a draft that needs review.

**What resolution and settings should I test first?**

A useful starting experiment is the maker's example: 1024 by 1024 pixels, 50 inference steps, and guidance of 4.0. Treat that as a baseline to compare with your results, rather than a guarantee of the best image.

