[Integrations](https://spiral.ai/integrations) › [Claude Code](https://spiral.ai/integrations/claude-code) › [Juggernaut Flux Lightning](https://spiral.ai/integrations/claude-code/juggernaut-flux-lightning)

# How to Use Juggernaut Flux Lightning in Claude Code

Juggernaut Flux Lightning turns text descriptions into images for mood boards and quick concept testing. Compared with Juggernaut Pro Flux, it prioritizes speed over photorealistic detail and fine-grained prompt control.

|  |  |
| --- | --- |
| Model | Juggernaut Flux Lightning |
| Available through | fal |
| Category | Image |
| Price | $0.0078 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 Juggernaut Flux Lightning in Claude Code

- Read the homepage copy and layout in this project. Use Juggernaut Flux Lightning to generate a 1280 by 720 image of a coastal observatory at dawn, with the building on the right and open sky on the left for the headline. Start at four steps.
- Read the project's design brief and use Juggernaut Flux Lightning to create three mood-board images of a quiet ceramic studio. Keep the composition similar while testing window light, overcast light, and warm evening light.
- Use the game's environment notes in this repository to write a focused scene description, then generate a digital painting with Juggernaut Flux Lightning. Show a forest settlement from a wide viewpoint and use four steps.
- Read the illustration brief in this project. Use Juggernaut Flux Lightning to depict a cyclist crossing a stone bridge in three treatments: cartoon, digital art, and oil painting. Keep the subject and viewpoint the same.
- Use Juggernaut Flux Lightning to generate a 1280 by 720 editorial photograph concept for this project's gardening article: hands planting a seedling in dark soil, soft side light, close framing. Compare four steps with eight steps and show both results.

## How to set up Juggernaut Flux Lightning 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 Juggernaut Flux Lightning**: 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": "rundiffusion-fal/juggernaut-flux/lightning",
    "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: Claude Code finds Juggernaut Flux Lightning on Spiral, shows the price and runs it.

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

## Juggernaut Flux Lightning tools and prices

- [Juggernaut Flux Lightning](https://spiral.ai/tools/fal/rundiffusion-fal/juggernaut-flux/lightning) (fal): $0.0078 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 12 | 4 | 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. |
| num_images | 1 to 4 | 1 | The number of images to generate. |
| output_format | jpeg, png | png | The format of the generated image. |

## What can you do with Juggernaut Flux Lightning in Claude Code?

Turn a project's written creative brief into image candidates you can assess in the actual layout. Use quick concept tests to choose framing and visual style before refining the page.

### Campaign mood boards

Explore a campaign's visual direction with separate images of the same scene under different lighting and color treatments.

### Website image concepts

Generate landscape image candidates from a written creative brief, then compare how each composition leaves room for a headline.

### Portrait direction studies

Test portrait framing, lighting, clothing, and background descriptions before choosing an editorial direction.

### Illustration style studies

Render one written scene as a cartoon, digital painting, and oil painting to compare possible illustration treatments.

### Game environment concepts

Explore written descriptions of forests, settlements, and imagined interiors as digital art for an early art-direction review.

### Cover artwork exploration

Draft artwork directions for a book or album from a written brief. Compare imagery first, then add the title during layout.

## Overview

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

## Juggernaut Flux Lightning in other agents

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

## More Claude Code guides

- [Juggernaut Flux Base Image to Image](https://spiral.ai/integrations/claude-code/juggernaut-flux-base-image-to-image)
- [Juggernaut Flux Pro](https://spiral.ai/integrations/claude-code/juggernaut-flux-pro)
- [Juggernaut Flux Base](https://spiral.ai/integrations/claude-code/juggernaut-flux-base)
- [Juggernaut Flux Pro Image to Image](https://spiral.ai/integrations/claude-code/juggernaut-flux-pro-image-to-image)
- [Image to SVG](https://spiral.ai/integrations/claude-code/image-to-svg)
- [Kling Image 3.0 Edit](https://spiral.ai/integrations/claude-code/kling-image-3-0-edit)

## Questions about Juggernaut Flux Lightning in Claude Code

**Can Claude Code use Juggernaut Flux Lightning?**

Yes. Add Spiral to Claude Code as an MCP server, and Claude Code can find and run Juggernaut Flux Lightning like any built-in tool.

**How much does Juggernaut Flux Lightning cost in Claude Code?**

$0.0078 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 Claude Code plan is separate.

**Do I need a fal account to use Juggernaut Flux Lightning in Claude Code?**

No. Spiral runs Juggernaut Flux Lightning on its own fal account. You sign in to Spiral once and never paste a key.

**How long does it take to set up Juggernaut Flux Lightning in Claude Code?**

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

**Does Claude Code wait while Juggernaut Flux Lightning runs?**

Juggernaut Flux Lightning runs in the background. Claude Code starts the run, checks on it and gives you the image when it's ready.

**What is Juggernaut Flux Lightning best for?**

Use it to explore visual directions before committing to one: mood boards, concept sketches, and prompt comparisons. Realism and prompt adherence are documented strengths.

**How does Juggernaut Flux Lightning compare with Juggernaut Pro Flux?**

Lightning prioritizes fast exploration, with less emphasis on fine-grained prompt control. RunDiffusion positions Pro for enhanced photorealism and detail.

**Is Juggernaut Flux Lightning only for realistic images?**

No. RunDiffusion also lists cartoons, anime, digital art, oil paintings, and graphic design for Juggernaut Flux. Specify the intended medium in your prompt.

**How should I write a Juggernaut Flux Lightning prompt?**

Describe the subject, then specify the style, lighting, mood, and composition. For a useful comparison, keep the scene description fixed and change one detail, such as the lighting.

**Can Juggernaut Flux Lightning make widescreen images?**

Yes. The documentation includes a custom size of 1280 by 720 pixels, suitable for a 16:9 composition. Plan where the subject and any later text overlay should sit.

