[Integrations](https://spiral.ai/integrations) › [OpenClaw](https://spiral.ai/integrations/openclaw) › [fal Scene Composition](https://spiral.ai/integrations/openclaw/fal-scene-composition)

# How to Use fal Scene Composition in OpenClaw

Use fal Scene Composition to place an existing subject in a new setting. It composes the surrounding scene and lighting, making it useful for product scene concepts, editorial images, and imagined environments.

|  |  |
| --- | --- |
| Model | fal Scene Composition |
| Available through | fal |
| Category | Image |
| Price | $0.052 per image. |
| Returns | image |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with fal Scene Composition in OpenClaw

- Every Monday, use fal Scene Composition with the product image supplied in the weekly brief. Request a scene based on that week's season and location, specify the lighting, and collect the result for review.
- Each morning, use fal Scene Composition with the featured mug image supplied for the day. Alternate between a kitchen table, café counter, and garden patio; save the full description with each result.
- Every Friday, use fal Scene Composition with the supplied backpack photo. Explore one travel setting from the weekly brief, describing the ground surface, time of day, and light direction.
- Once a week, use fal Scene Composition with the character image supplied in the story brief. Request the next described location and collect the composition for an illustrator to review.
- At the start of each month, use fal Scene Composition with the supplied campaign product image. Request that month's seasonal setting and record the scene description and seed with the result.

## How to set up fal Scene Composition 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 fal Scene Composition**: 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/image-editing/scene-composition",
    "input": {
      "image_url": "https://v3.fal.media/files/zebra/hAjCkcyly4gsS9-cptD3Y_image%20(20).png"
    }
  }'
```

Then paste one of the prompts above: OpenClaw finds fal Scene Composition on Spiral, shows the price and runs it.

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

## fal Scene Composition tools and prices

- [Image Editing Scene Composition](https://spiral.ai/tools/fal/fal-ai/image-editing/scene-composition) (fal): $0.052 per image.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| guidance_scale | 0 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_inference_steps | 1 to 50 | 30 | Number of inference steps for sampling. |
| safety_tolerance | 1, 2, 3, 4, 5, 6 | 2 | The safety tolerance level for the generated image. 1 being the most strict and 6 being the most permissive. |
| output_format | jpeg, png | jpeg | The format of the generated image. |
| aspect_ratio | 21:9, 16:9, 4:3, 3:2, 1:1, 2:3, 3:4, 9:16, 9:21 | — | The aspect ratio of the generated image. |
| seed |  | — | The same seed and the same prompt given to the same version of the model will output the same image every time. |

## What can you do with fal Scene Composition in OpenClaw?

Build recurring scene studies around product or character images supplied with each brief. A scheduled agent can request new settings and collect the results for review.

### Product lifestyle concepts

Place a product from an existing image into a specific setting, such as a coffee mug on a breakfast table beside a window.

### Seasonal campaign images

Try seasonal surroundings around a photographed subject, such as autumn leaves, a winter storefront, or a summer patio.

### Editorial portrait settings

Explore a library, city street, or theater as the setting around a portrait subject. Compare the results before choosing an editorial direction.

### Story illustration concepts

Place an existing character image into an enchanted forest, castle courtyard, or moonlit clearing to explore a story's setting.

### Merchandise scene studies

Try a photographed bag, shoe, or accessory in surroundings that suggest its use, such as a train platform or mountain lodge.

### Website image exploration

Compose alternative settings around an existing subject for a landing page. Request deliberate subject placement and space for separately added copy.

## Overview

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

## fal Scene Composition in other agents

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

## More OpenClaw guides

- [fal Retouch](https://spiral.ai/integrations/openclaw/fal-retouch)
- [fal Sharpen](https://spiral.ai/integrations/openclaw/fal-sharpen)
- [fal Object Removal](https://spiral.ai/integrations/openclaw/fal-object-removal)
- [fal Style Transfer](https://spiral.ai/integrations/openclaw/fal-style-transfer)
- [fal Hair Change](https://spiral.ai/integrations/openclaw/fal-hair-change)
- [fal Text Removal](https://spiral.ai/integrations/openclaw/fal-text-removal)

## Questions about fal Scene Composition in OpenClaw

**Can OpenClaw use fal Scene Composition?**

Yes. Add Spiral to OpenClaw as an MCP server, and OpenClaw can find and run fal Scene Composition like any built-in tool.

**How much does fal Scene Composition cost in OpenClaw?**

$0.052 per image. 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 fal Scene Composition in OpenClaw?**

No. Spiral runs fal Scene Composition on its own fal account. You sign in to Spiral once and never paste a key.

**How long does it take to set up fal Scene Composition in OpenClaw?**

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

**Does OpenClaw wait while fal Scene Composition runs?**

fal Scene Composition runs in the background. OpenClaw starts the run, checks on it and gives you the image when it's ready.

**What is fal Scene Composition useful for?**

It places an existing subject into a described setting. Try it for product scene concepts, editorial backdrops, or fantasy environments.

**What should I write in the scene description?**

Describe where the subject should appear. For example, ask for a wooden café table beside a rain-covered window, then specify the lighting and framing you want.

**Can fal Scene Composition create both realistic and imaginary settings?**

Its stated scope includes urban settings and enchanted forests. Describe a concrete destination, whether that is a city sidewalk or a moonlit woodland.

**Which setting matters for following my description?**

Guidance scale controls prompt adherence. When a result misses a scene detail, try adjusting guidance while keeping the description unchanged so you can compare the effect.

**Can I reproduce an image later?**

fal documents repeatability with the same seed, prompt, and model version. Save those details with an image you want to revisit.

