[Integrations](https://spiral.ai/integrations) › [OpenClaw](https://spiral.ai/integrations/openclaw) › [FLUX.1 Redux \[dev\]](https://spiral.ai/integrations/openclaw/flux-1-redux-dev)

# How to Use FLUX.1 Redux [dev] in OpenClaw

FLUX.1 Redux [dev] creates slight variations of a reference image for visual exploration. Choose it when you already have a visual direction and want nearby alternatives to compare.

|  |  |
| --- | --- |
| Model | FLUX.1 Redux [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 Redux [dev] in OpenClaw

- Every Monday, use FLUX.1 Redux [dev] to create three alternatives from the current approved campaign reference image. Prepare a comparison with the original for our weekly design review.
- Each Friday, use FLUX.1 Redux [dev] with the latest selected editorial illustration. Make two candidates and summarize the visible changes for the next editorial meeting.
- Before the monthly presentation review, use FLUX.1 Redux [dev] to make two alternatives from the selected abstract artwork. Prepare 1280 by 720 pixel images and compare their suitability behind slide titles.
- Each week, use FLUX.1 Redux [dev] with the selected game environment concept image. Create three alternatives and prepare a review comparing the subject and composition with the original.
- At the next scheduled artwork review, use FLUX.1 Redux [dev] with the approved reference and generate one image using 50 sampling steps and a guidance value of 2.5. Compare it with the previous candidate and report the visible differences.

## How to set up FLUX.1 Redux [dev] in OpenClaw

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

### Use the Spiral skill

1. **Send OpenClaw 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. **Add the server**: On the machine that runs OpenClaw's Gateway:

```bash
openclaw mcp add spiral \
  --url https://api.spiral.ai/mcp \
  --transport streamable-http \
  --auth oauth
```

2. **Sign in**: In Settings › MCP, select Sign in on the Spiral server, sign in to Spiral and click Authorize. No API key.

```bash
openclaw mcp login spiral
```

3. **Reload and check**: A running Gateway may keep its old tool list: restart it, or Save & Publish in the Control UI.

```bash
openclaw mcp reload
openclaw mcp doctor spiral --probe
```

### 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 Redux [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/redux",
    "input": {
      "image_url": "https://fal.media/files/kangaroo/acQvq-Kmo2lajkgvcEHdv.png"
    }
  }'
```

Then paste one of the prompts above: OpenClaw finds FLUX.1 Redux [dev] on Spiral, shows the price and runs it.

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

## FLUX.1 Redux [dev] tools and prices

- [FLUX.1 \[dev\] Redux · Image to Image](https://spiral.ai/tools/fal/fal-ai/flux-1/dev/redux) (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 \[dev\] Redux · Image to Image](https://spiral.ai/tools/fal/fal-ai/flux/dev/redux) (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 Redux [dev] in OpenClaw?

Build a recurring review of visual alternatives from selected reference images. A scheduled agent can prepare candidates and comparisons for the next creative review.

### Website image exploration

Generate alternatives from an existing website illustration, then compare each in the actual layout before selecting one.

### Editorial illustration drafts

Start from an approved illustration and explore nearby visual interpretations for an article. Review the results against the editorial brief.

### Campaign concept review

Use an existing campaign concept as the reference for a new round of visual candidates. Compare changes before committing to production artwork.

### Game environment concepts

Explore alternatives to an environment concept image. Use the outputs as discussion material for an artist's next pass.

### Presentation artwork

Create related alternatives from an existing abstract illustration, then choose the image that leaves enough room for slide content.

### Thumbnail candidate selection

Generate slight variations of a thumbnail image and compare how clearly the subject reads at a small display size.

## Overview

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

## FLUX.1 Redux [dev] in other agents

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

## More OpenClaw guides

- [FLUX.1 Krea Redux](https://spiral.ai/integrations/openclaw/flux-1-krea-redux)
- [FLUX.1 SRPO](https://spiral.ai/integrations/openclaw/flux-1-srpo)
- [FLUX.1 Krea LoRA](https://spiral.ai/integrations/openclaw/flux-1-krea-lora)
- [FLUX.1 SRPO Dev](https://spiral.ai/integrations/openclaw/flux-1-srpo-dev)
- [FLUX.1 Krea Dev](https://spiral.ai/integrations/openclaw/flux-1-krea-dev)
- [FLUX.1 Schnell](https://spiral.ai/integrations/openclaw/flux-1-schnell)

## Questions about FLUX.1 Redux [dev] in OpenClaw

**Can OpenClaw use FLUX.1 Redux [dev]?**

Yes. Add Spiral to OpenClaw as an MCP server, and OpenClaw can find and run FLUX.1 Redux [dev] like any built-in tool.

**How much does FLUX.1 Redux [dev] cost in OpenClaw?**

$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 OpenClaw plan is separate.

**Do I need a fal account to use FLUX.1 Redux [dev] in OpenClaw?**

No. Spiral runs FLUX.1 Redux [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 Redux [dev] in OpenClaw?**

About two minutes: add the server, then sign in, then reload and check.

**Does OpenClaw wait while FLUX.1 Redux [dev] runs?**

FLUX.1 Redux [dev] runs in the background. OpenClaw starts the run, checks on it and gives you the image when it's ready.

**What is FLUX.1 Redux best for?**

Use it to explore slight changes to an image you already like. It suits concept selection, illustration alternatives, and visual drafts where you want several related results to compare.

**How should I choose a reference image?**

Start with an image close to your intended subject, composition, and overall look. BFL says the input image heavily influences the output, so treat reference selection as your main creative decision.

**Will FLUX.1 Redux preserve every detail?**

Treat the result as a new interpretation to inspect. Redux is designed for slight variation; compare any details that matter before using an output in finished work.

**Can FLUX.1 Redux produce a widescreen image?**

Yes. The documentation includes a custom 1280 by 720 pixel output example, which is a 16:9 image.

**Which generation settings are worth comparing?**

Hugging Face's Redux example uses 50 sampling steps and guidance 2.5. Try that combination as a comparison using the same reference image, then judge the visible result before adopting it.

