[Integrations](https://spiral.ai/integrations) › [OpenClaw](https://spiral.ai/integrations/openclaw) › [Seedream 5.5 Image Edit](https://spiral.ai/integrations/openclaw/seedream-5-5-image-edit)

# How to Use Seedream 5.5 Image Edit in OpenClaw

Seedream 5.5 Image Edit refines existing artwork with targeted changes while preserving untouched areas. Unlike Seedream 5.5 Text to Image, it uses reference images to guide the result.

|  |  |
| --- | --- |
| Model | Seedream 5.5 Image Edit |
| Available through | fal |
| Category | Image |
| Price | $0.06825 per run at the default inputs. $0.06825 per unit of `num_images`. Each item in `image_urls` adds $0.0156. |
| Returns | image |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Seedream 5.5 Image Edit in OpenClaw

- Each Friday, use Seedream 5.5 Image Edit on the latest approved cafe poster to change only the featured pastry illustration. Preserve all lettering, colors, and layout; output a 1536 × 2048 draft for review.
- Every Tuesday, use Seedream 5.5 Image Edit on the approved product reference to change only the background surface to limestone, oak, or linen in rotation. Preserve the product and label; output a 2048 × 2048 draft.
- Every Monday at 9am: remove the background from the photo I attach with Seedream 5.5 Image Edit and give me a transparent PNG.
- Use Seedream 5.5 Image Edit to clean up these product shots so they sit on pure white.
- Edit this image with Seedream 5.5 Image Edit: keep the subject, swap the background for a sunlit studio.

## How to set up Seedream 5.5 Image Edit 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 Seedream 5.5 Image Edit**: 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": "bytedance/seedream/v5.5/edit",
    "input": {
      "prompt": "Replace the product in Figure 1 with that in Figure 2. Seamlessly render the logo in Figure 3 into the product design, in a frosted glass texture.",
      "image_urls": [
        "<image_urls>"
      ]
    }
  }'
```

Then paste one of the prompts above: OpenClaw finds Seedream 5.5 Image Edit on Spiral, shows the price and runs it.

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

## Seedream 5.5 Image Edit tools and prices

- [Seedream 5.5 Image Edit](https://spiral.ai/tools/fal/bytedance/seedream/v5.5/edit) (fal): $0.06825 per run at the default inputs. $0.06825 per unit of `num_images`. Each item in `image_urls` adds $0.0156.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| image_size |  | auto_2K | The size of the generated image. Total pixels must be between 921600 and 4624220, with aspect ratio between 1/16 and 16. |
| num_images | 1 to 6 | 1 | Number of separate model generations to run with the prompt. |
| output_format | jpeg, png | png | The file format of the generated image. |
| watermark |  | false | Whether to add the provider's visible watermark. |
| background | auto, opaque, transparent | auto | `auto` lets the model choose from the prompt and output format. `transparent` returns an RGBA image and requires `output_format=png`. |

## What can you do with Seedream 5.5 Image Edit in OpenClaw?

Produce recurring visual drafts from approved briefs, such as weekly posters or seasonal product scenes. Keep Seedream 5.5 instructions consistent across runs and send the results for review.

### Transparent sticker artwork

Create a sticker concept from a written description, or refine supplied sticker artwork. Ask for a transparent PNG so the design can sit over different backgrounds.

### Game character assets

Develop character artwork from a brief or an existing character reference. Request an isolated pose with a transparent background for use in a game layout.

### Editorial photography concepts

Explore a portrait or still-life idea from text, or adjust a supplied image. Specify the light direction, visible materials, camera angle, and intended mood.

### Posters with readable copy

Draft a poster from a written brief or revise existing poster artwork. Supply the exact English or Chinese wording, describe its placement, and check the finished lettering.

### Product scene concepts

Use text to explore a proposed product scene, including glass, fabric, or metal surfaces. Use a product reference when the task starts from an existing product image.

### Interior design studies

Sketch a room concept from a description, or revise furnishings in a supplied room image. Name the materials, lighting, and furniture placement to explore.

### Controlled campaign revisions

Revise supplied campaign artwork one change at a time, such as replacing a prop or changing a jacket color. Identify the face, layout, lettering, and lighting that should stay unchanged.

### Illustrated information layouts

Draft an illustrated information sheet from text, or refine an existing layout. Provide approved captions and review every label before sharing the result.

## Overview

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

## Seedream 5.5 Image Edit in other agents

- [Amp](https://spiral.ai/integrations/amp/seedream-5-5-image-edit)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/seedream-5-5-image-edit)
- [Claude](https://spiral.ai/integrations/claude-desktop/seedream-5-5-image-edit)
- [Claude Code](https://spiral.ai/integrations/claude-code/seedream-5-5-image-edit)
- [Cline](https://spiral.ai/integrations/cline/seedream-5-5-image-edit)
- [Codex](https://spiral.ai/integrations/codex/seedream-5-5-image-edit)
- [Cursor](https://spiral.ai/integrations/cursor/seedream-5-5-image-edit)
- [Devin](https://spiral.ai/integrations/devin/seedream-5-5-image-edit)
- [dots](https://spiral.ai/integrations/dots/seedream-5-5-image-edit)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/seedream-5-5-image-edit)
- [Gemini](https://spiral.ai/integrations/gemini/seedream-5-5-image-edit)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/seedream-5-5-image-edit)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/seedream-5-5-image-edit)
- [goose](https://spiral.ai/integrations/goose/seedream-5-5-image-edit)
- [Grok](https://spiral.ai/integrations/grok/seedream-5-5-image-edit)
- [Grok Build](https://spiral.ai/integrations/grok-build/seedream-5-5-image-edit)
- [Hermes](https://spiral.ai/integrations/hermes/seedream-5-5-image-edit)
- [Instinct](https://spiral.ai/integrations/instinct/seedream-5-5-image-edit)
- [Manus](https://spiral.ai/integrations/manus/seedream-5-5-image-edit)
- [Muse](https://spiral.ai/integrations/muse/seedream-5-5-image-edit)
- [Muse Code](https://spiral.ai/integrations/muse-code/seedream-5-5-image-edit)
- [n8n](https://spiral.ai/integrations/n8n/seedream-5-5-image-edit)
- [Notion](https://spiral.ai/integrations/notion/seedream-5-5-image-edit)
- [opencode](https://spiral.ai/integrations/opencode/seedream-5-5-image-edit)
- [Perplexity](https://spiral.ai/integrations/perplexity/seedream-5-5-image-edit)
- [Raycast](https://spiral.ai/integrations/raycast/seedream-5-5-image-edit)
- [VS Code](https://spiral.ai/integrations/vscode/seedream-5-5-image-edit)
- [Windsurf](https://spiral.ai/integrations/windsurf/seedream-5-5-image-edit)
- [Zapier](https://spiral.ai/integrations/zapier/seedream-5-5-image-edit)

## More OpenClaw guides

- [Seedream 5.0 Pro Text to Image](https://spiral.ai/integrations/openclaw/seedream-5-0-pro-text-to-image)
- [Seedream 5.5 Layerize](https://spiral.ai/integrations/openclaw/seedream-5-5-layerize)
- [Seedream 5.0 Pro Layerize](https://spiral.ai/integrations/openclaw/seedream-5-0-pro-layerize)
- [Seedream 5.5 Text to Image](https://spiral.ai/integrations/openclaw/seedream-5-5-text-to-image)
- [Seedream 5.0 Pro Image Editing](https://spiral.ai/integrations/openclaw/seedream-5-0-pro-image-editing)
- [Smart Resize](https://spiral.ai/integrations/openclaw/smart-resize)

## Questions about Seedream 5.5 Image Edit in OpenClaw

**Can OpenClaw use Seedream 5.5 Image Edit?**

Yes. Add Spiral to OpenClaw as an MCP server, and OpenClaw can find and run Seedream 5.5 Image Edit like any built-in tool.

**How much does Seedream 5.5 Image Edit cost in OpenClaw?**

$0.06825 per run at the default inputs. $0.06825 per unit of `num_images`. Each item in `image_urls` adds $0.0156. 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 Seedream 5.5 Image Edit in OpenClaw?**

No. Spiral runs Seedream 5.5 Image Edit on its own fal account. You sign in to Spiral once and never paste a key.

**How long does it take to set up Seedream 5.5 Image Edit in OpenClaw?**

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

**Does OpenClaw wait while Seedream 5.5 Image Edit runs?**

Seedream 5.5 Image Edit runs in the background. OpenClaw starts the run, checks on it and gives you the image when it's ready.

**What is Seedream 5.5 good at?**

Seedream 5.5 is useful for photographic scenes where lighting, materials, and skin texture matter. Its documented Chinese and English text rendering also makes posters and illustrated information layouts worth trying.

**How large can Seedream 5.5 images be?**

Images must contain 921,600 to 4,624,220 pixels, with a width-to-height ratio between 1:16 and 16:1. A 2048 × 2048 square fits; a 4096 × 4096 square exceeds the limit.

**Can Seedream 5.5 create transparent assets?**

Yes. Seedream 5.5 supports full and partial transparency, which is useful for stickers, character art, and elements placed over other artwork. Request PNG output to retain transparency.

**Can Seedream 5.5 render Chinese and English text?**

ByteDance documents text-rendering evaluations in both languages, including densely arranged small text. For a poster or infographic, provide the exact wording and review the rendered copy before using it.

**Why does Seedream 5.5 sometimes miss details in a brief?**

BytePlus warns that very long prompts can scatter information and cause missing elements. Keep English prompts under its recommended 600 words and put the essential subject, composition, and constraints first.

