[Integrations](https://spiral.ai/integrations) › [OpenClaw](https://spiral.ai/integrations/openclaw) › [851 Labs Background Remover](https://spiral.ai/integrations/openclaw/851-labs-background-remover)

# How to Use 851 Labs Background Remover in OpenClaw

851 Labs Background Remover turns product photos, portraits, and other images into reusable cutouts. Its soft alpha output keeps gradual edge transitions, while hard segmentation produces a binary cutout.

|  |  |
| --- | --- |
| Model | 851 Labs Background Remover |
| Available through | Replicate |
| Category | Image |
| Price | $0.000293 per second of processing. |
| Returns | image |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with 851 Labs Background Remover in OpenClaw

- Every morning, use 851 Labs Background Remover on newly submitted product photos. Return transparent PNG cutouts and keep the original images with the results.
- Each Friday, use 851 Labs Background Remover on the week's new team portraits. Keep soft edge transparency and collect the PNG cutouts for review.
- Each evening, use 851 Labs Background Remover to make green overlay previews of new catalog photos. Put the previews in a review report beside the originals.
- Every Monday, use 851 Labs Background Remover on newly approved promotional product photos. Prepare transparent PNG assets for the design team.
- For each newly submitted sample photo, use 851 Labs Background Remover to produce a soft-edged cutout and a hard-edged cutout with a midpoint cutoff. Collect both for the weekly image review.

## How to set up 851 Labs Background Remover 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 851 Labs Background Remover**: 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": "replicate",
    "model": "851-labs/background-remover",
    "input": {
      "image": "<image>"
    }
  }'
```

Then paste one of the prompts above: OpenClaw finds 851 Labs Background Remover on Spiral, shows the price and runs it.

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

## 851 Labs Background Remover tools and prices

- [851 Labs Background Remover](https://spiral.ai/tools/replicate/851-labs/background-remover) (Replicate): $0.000293 per second of processing.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| format |  | png | Output format (e.g., png, jpg). Defaults to png. |
| reverse |  | false | If True, remove the foreground instead of the background. |
| threshold |  | 0 | Threshold for hard segmentation (0.0-1.0). If 0.0, uses soft alpha. |
| background_type |  | rgba | Background type: 'rgba', 'map', 'green', 'white', [R,G,B] array, 'blur', 'overlay', or path to an image. |

## What can you do with 851 Labs Background Remover in OpenClaw?

Prepare incoming product photos and portraits as reusable cutouts on a schedule. A recurring agent can keep originals, collect overlay previews, and assemble results for review.

### Product listing cutouts

Remove the photographed backdrop from product shots and save transparent assets for listing layouts.

### Profile photo preparation

Isolate a person from a portrait before placing the cutout into a profile or team layout.

### Promotional graphics

Extract a product from an existing photo for use in banners, announcements, and promotional compositions.

### Presentation assets

Turn photographed objects into transparent cutouts that can sit on slide backgrounds.

### Catalog image preparation

Process catalog photos individually into reusable cutouts, then review the results before assembling the catalog.

### Website image assets

Prepare transparent product or portrait images for page compositions that use their own backgrounds.

### Cutout quality review

Create overlay previews to inspect the selected foreground and boundary before approving image assets.

## Overview

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

## 851 Labs Background Remover in other agents

- [Amp](https://spiral.ai/integrations/amp/851-labs-background-remover)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/851-labs-background-remover)
- [Claude](https://spiral.ai/integrations/claude-desktop/851-labs-background-remover)
- [Claude Code](https://spiral.ai/integrations/claude-code/851-labs-background-remover)
- [Cline](https://spiral.ai/integrations/cline/851-labs-background-remover)
- [Codex](https://spiral.ai/integrations/codex/851-labs-background-remover)
- [Cursor](https://spiral.ai/integrations/cursor/851-labs-background-remover)
- [Devin](https://spiral.ai/integrations/devin/851-labs-background-remover)
- [dots](https://spiral.ai/integrations/dots/851-labs-background-remover)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/851-labs-background-remover)
- [Gemini](https://spiral.ai/integrations/gemini/851-labs-background-remover)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/851-labs-background-remover)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/851-labs-background-remover)
- [goose](https://spiral.ai/integrations/goose/851-labs-background-remover)
- [Grok](https://spiral.ai/integrations/grok/851-labs-background-remover)
- [Grok Build](https://spiral.ai/integrations/grok-build/851-labs-background-remover)
- [Hermes](https://spiral.ai/integrations/hermes/851-labs-background-remover)
- [Instinct](https://spiral.ai/integrations/instinct/851-labs-background-remover)
- [Manus](https://spiral.ai/integrations/manus/851-labs-background-remover)
- [Muse](https://spiral.ai/integrations/muse/851-labs-background-remover)
- [Muse Code](https://spiral.ai/integrations/muse-code/851-labs-background-remover)
- [n8n](https://spiral.ai/integrations/n8n/851-labs-background-remover)
- [Notion](https://spiral.ai/integrations/notion/851-labs-background-remover)
- [opencode](https://spiral.ai/integrations/opencode/851-labs-background-remover)
- [Perplexity](https://spiral.ai/integrations/perplexity/851-labs-background-remover)
- [Raycast](https://spiral.ai/integrations/raycast/851-labs-background-remover)
- [VS Code](https://spiral.ai/integrations/vscode/851-labs-background-remover)
- [Windsurf](https://spiral.ai/integrations/windsurf/851-labs-background-remover)
- [Zapier](https://spiral.ai/integrations/zapier/851-labs-background-remover)

## More OpenClaw guides

- [gnomAD gene variation search](https://spiral.ai/integrations/openclaw/gnomad-gene-variation-search)
- [Age Modify](https://spiral.ai/integrations/openclaw/age-modify)
- [gnomAD gene constraint](https://spiral.ai/integrations/openclaw/gnomad-gene-constraint)
- [Age Progression](https://spiral.ai/integrations/openclaw/age-progression)
- [gnomAD allele frequencies](https://spiral.ai/integrations/openclaw/gnomad-allele-frequencies)
- [BEN v2](https://spiral.ai/integrations/openclaw/ben-v2)

## Questions about 851 Labs Background Remover in OpenClaw

**Can OpenClaw use 851 Labs Background Remover?**

Yes. Add Spiral to OpenClaw as an MCP server, and OpenClaw can find and run 851 Labs Background Remover like any built-in tool.

**How much does 851 Labs Background Remover cost in OpenClaw?**

$0.000293 per second of processing. 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 Replicate account to use 851 Labs Background Remover in OpenClaw?**

No. Spiral runs 851 Labs Background Remover on its own Replicate account. You sign in to Spiral once and never paste a key.

**How long does it take to set up 851 Labs Background Remover in OpenClaw?**

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

**Does OpenClaw wait while 851 Labs Background Remover runs?**

851 Labs Background Remover runs in the background. OpenClaw starts the run, checks on it and gives you the image when it's ready.

**What is 851 Labs Background Remover useful for?**

Use it to isolate products, people, or other foreground subjects from existing images. Documented uses include product listings, profile photos, and marketing assets.

**How should I handle hair and other soft edges?**

Start with soft alpha output so edge pixels can remain partly transparent. Hard segmentation makes a binary decision at each pixel, so compare it carefully before using it on fine detail.

**Can I tell it exactly which object to keep?**

It detects visually prominent foreground objects automatically. As a practical consequence, review images with several competing subjects instead of assuming it will isolate the particular object you intended.

**What should I save for a transparent cutout?**

Use RGBA output saved as PNG. The alpha channel carries the cutout's transparency, including gradual edge transitions.

**Does background removal increase image resolution?**

Treat it as a cutout operation. The underlying package resizes the predicted mask to the input dimensions rather than generating a larger, more detailed image.

