[Integrations](https://spiral.ai/integrations) › [OpenClaw](https://spiral.ai/integrations/openclaw) › [FLUX.1 Kontext Max Multi](https://spiral.ai/integrations/openclaw/flux-1-kontext-max-multi)

# How to Use FLUX.1 Kontext Max Multi in OpenClaw

FLUX.1 Kontext Max Multi combines image references for edits where lettering and detailed instructions matter. Compared with FLUX.1 Kontext Pro Multi, its underlying Max model emphasizes stronger prompt adherence, typography, and editing consistency.

|  |  |
| --- | --- |
| Model | FLUX.1 Kontext Max Multi |
| Available through | fal |
| Category | Image |
| Price | $0.104 per image. 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 Kontext Max Multi in OpenClaw

- Each Friday, use FLUX.1 Kontext Max Multi to update the approved event poster with the headline in the weekly brief. Quote the current and replacement wording in the edit request, preserve the surrounding artwork, and flag lettering errors.
- On the first Monday of each month, use FLUX.1 Kontext Max Multi with the approved illustration style reference. Draft a reading-themed scene featuring the subject named in the monthly brief. Present the source and result together.
- Every Monday, use FLUX.1 Kontext Max Multi with the approved product photo and this week's setting reference. Draft a product scene that preserves the product's shape, color, and label. Present it for review.
- Each week, use FLUX.1 Kontext Max Multi with the approved mascot portrait and the selected location reference. Draft one scene showing the mascot at that location, preserving its face, outfit, and proportions.
- Every Wednesday, use FLUX.1 Kontext Max Multi to apply the color named in the design brief to the mug in the approved product photo. Preserve its shape and surrounding scene. Start from the original photo each time.

## How to set up FLUX.1 Kontext Max Multi 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 Kontext Max Multi**: 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-pro/kontext/max/multi",
    "input": {
      "prompt": "Put the little duckling on top of the woman'\''s t-shirt.",
      "image_urls": [
        "<image_urls>"
      ]
    }
  }'
```

Then paste one of the prompts above: OpenClaw finds FLUX.1 Kontext Max Multi on Spiral, shows the price and runs it.

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

## FLUX.1 Kontext Max Multi tools and prices

- [FLUX.1 Kontext \[max\] · Editing (experimental Multi Image)](https://spiral.ai/tools/fal/fal-ai/flux-pro/kontext/max/multi) (fal): $0.104 per image. Billed on `num_images`, default 1.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| 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. |
| safety_tolerance | 1, 2, 3, 4, 5, 6 | 2 | The safety tolerance level for the generated image. 1 being the most strict and 5 being the most permissive. |
| enhance_prompt |  | false | Whether to enhance the prompt for better results. |

## What can you do with FLUX.1 Kontext Max Multi in OpenClaw?

Prepare recurring visual drafts from approved references with FLUX.1 Kontext Multi. A scheduled agent can repeat a specific edit brief while keeping the original images available for consistency checks.

### Product scene drafts

Combine a product photo with a setting reference to draft a new promotional image. Ask to preserve the product's shape, color, and label, then check those details against the source.

### Poster lettering updates

Replace a short headline in existing artwork without requesting a complete redesign. Quote the old and new wording and specify which surrounding elements should stay.

### Character storyboards

Use a character reference to draft scenes in different environments. Preserve distinctive facial features, clothing, and proportions, and review consistency between scenes.

### Illustration style studies

Use an approved illustration as a style reference for a new scene. Describe the intended subject and compare how well the result retains the reference's visual treatment.

### Object color studies

Recolor a specific object in an existing image to explore design directions. Name the object precisely and ask to preserve its shape and the surrounding scene.

### Background replacement concepts

Move a referenced person or object into a different setting for campaign planning. Specify the subject details to preserve and review unintended changes before using the image.

### Illustrated merchandise mockups

Combine an illustration reference with a garment photo to explore a printed design. Describe the design's placement and ask to preserve the garment's shape and existing scene.

## Overview

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

## FLUX.1 Kontext Max Multi in other agents

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

## More OpenClaw guides

- [FLUX.1 Kontext Max](https://spiral.ai/integrations/openclaw/flux-1-kontext-max)
- [FLUX.1 Kontext Max Text to Image](https://spiral.ai/integrations/openclaw/flux-1-kontext-max-text-to-image)
- [FLUX.1 Dev LoRA](https://spiral.ai/integrations/openclaw/flux-1-dev-lora)
- [FLUX.1 Kontext Pro](https://spiral.ai/integrations/openclaw/flux-1-kontext-pro)
- [FLUX.1 Dev](https://spiral.ai/integrations/openclaw/flux-1-dev)
- [FLUX.1 Kontext Pro Multi](https://spiral.ai/integrations/openclaw/flux-1-kontext-pro-multi)

## Questions about FLUX.1 Kontext Max Multi in OpenClaw

**Can OpenClaw use FLUX.1 Kontext Max Multi?**

Yes. Add Spiral to OpenClaw as an MCP server, and OpenClaw can find and run FLUX.1 Kontext Max Multi like any built-in tool.

**How much does FLUX.1 Kontext Max Multi cost in OpenClaw?**

$0.104 per image. 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 Kontext Max Multi in OpenClaw?**

No. Spiral runs FLUX.1 Kontext Max Multi 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 Kontext Max Multi in OpenClaw?**

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

**Does OpenClaw wait while FLUX.1 Kontext Max Multi runs?**

FLUX.1 Kontext Max Multi runs in the background. OpenClaw starts the run, checks on it and gives you the image when it's ready.

**What is FLUX.1 Kontext Multi useful for?**

Use it to combine image references, change objects, replace lettering, or move a recognizable character into another scene. Both Pro Multi and Max Multi are labeled experimental.

**How do Pro Multi and Max Multi differ?**

Both handle multiple image references. Black Forest Labs positions the underlying Max model around stronger instruction following, typography, and editing consistency, making it worth comparing on lettering or detailed edits.

**Can FLUX.1 Kontext Multi keep a character recognizable?**

Kontext supports preserving character identity and distinctive features across scenes. Name the features that matter in your edit request, then compare the result against the original reference.

**How should I request a text replacement?**

Quote both versions: "Replace 'Summer market' with 'Autumn market'." Add a separate instruction to preserve the lettering style and surrounding artwork.

**Can FLUX.1 Kontext Multi reuse an illustration's style?**

Kontext supports generating new scenes from a style reference. Describe the new subject and identify which reference supplies the visual treatment.

