[Integrations](https://spiral.ai/integrations) › [Gemini](https://spiral.ai/integrations/gemini) › [Seedream 5.0 Flash Layerize](https://spiral.ai/integrations/gemini/seedream-5-0-flash-layerize)

# How to Use Seedream 5.0 Flash Layerize in Gemini

Seedream 5.0 Flash Layerize splits finished artwork into a base image and up to 16 editable layers. Choose it for quick asset extraction; Pro puts more emphasis on image quality.

|  |  |
| --- | --- |
| Model | Seedream 5.0 Flash Layerize |
| Available through | fal |
| Category | Image |
| Price | $0.0351 per image. |
| Returns | image |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Seedream 5.0 Flash Layerize in Gemini

- Use Seedream 5.0 Flash Layerize on this poster. Separate the person, headline, and star decoration in the lower-right corner into individual layers, using automatic sizing.
- Use Seedream 5.0 Flash Layerize on this illustration with automatic element selection. Show me the extracted layers and help me identify which ones to move for a tighter composition.
- Use Seedream 5.0 Flash Layerize on this room illustration at the 1K tier. Request separate layers for the chair, lamp, and plant so I can plan a new arrangement.
- Use Seedream 5.0 Flash Layerize on this product image at the 2K resolution tier. Separate the bottle, flowers, and display platform so I can rearrange them.
- Use Seedream 5.0 Flash Layerize on this event artwork. Separate the main title, performer, and decorative circles at the 2K tier, with standard prompt optimization to favor image quality.

## How to set up Seedream 5.0 Flash Layerize in Gemini

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

### Use the Gemini connector

1. **Open Connected Apps**: On your computer, go to gemini.google.com. At the bottom, click Settings › Connected Apps. If you don't see Connected Apps, click Personal Intelligence first, then Connected Apps.

2. **Add Spiral as a custom app**: Under Custom apps, click Add a custom app and paste this MCP server URL:

```text
https://api.spiral.ai/mcp
```

3. **Sign in to Spiral and approve**: Follow the on-screen instructions. Spiral opens: sign in, pick the organization and click Authorize. No API key.

### Use the Spiral skill

1. **Send Gemini 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 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 5.0 Flash Layerize**: 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/flash/layerize",
    "input": {
      "image_url": "https://storage.googleapis.com/falserverless/example_inputs/kontext_example_input.webp"
    }
  }'
```

Then paste one of the prompts above: Gemini finds Seedream 5.0 Flash Layerize on Spiral, shows the price and runs it.

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

## Seedream 5.0 Flash Layerize tools and prices

- [Seedream · Layerize](https://spiral.ai/tools/fal/bytedance/seedream/v5/flash/layerize) (fal): $0.0351 per image.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| prompt |  |  | Optional instructions describing which elements to separate. When empty, the model automatically separates the major elements. Normalized `<bbox>left top right bottom</bbox>` tags may be used for precise coordinate targeting. |
| image_size | auto, auto_1K, auto_1.5K, auto_2K | auto | Resolution tier for the output base image and layers. `auto` adapts to the input image while preserving each element's aspect ratio. |
| output_format | jpeg, png | png | Format of the base image. Separated layers always use PNG. |
| watermark |  | false | Whether to add the provider's visible watermark. |
| image_passthrough |  | false | Preserve original input and output image bytes without resizing or re-encoding. |

## What can you do with Seedream 5.0 Flash Layerize in Gemini?

Pull editable elements out of a finished poster, product image, or illustration. Describe the parts you need separately, then review the returned cutouts before recomposing them.

### Rework a finished poster

Separate the headline, subject, and decorative elements so you can adjust their positions in a design tool.

### Extract product artwork

Request separate layers for a product and its surrounding props, then use the cutouts in another composition.

### Prepare a layered web illustration

Separate foreground objects from the rest of an illustration, then use their positions and stacking order to build a browser composition.

### Build an asset review queue

Run an initial separation pass with Flash, inspect the extracted elements, and use Pro when image quality takes priority.

### Rearrange a scene

Extract selected objects as transparent layers, then move or resize them in a design tool while keeping their original proportions.

### Target a small region

Use a normalized bounding box to identify the specific element you want separated when a verbal description leaves room for confusion.

## Overview

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

## Seedream 5.0 Flash Layerize in other agents

- [Amp](https://spiral.ai/integrations/amp/seedream-5-0-flash-layerize)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/seedream-5-0-flash-layerize)
- [Claude](https://spiral.ai/integrations/claude-desktop/seedream-5-0-flash-layerize)
- [Claude Code](https://spiral.ai/integrations/claude-code/seedream-5-0-flash-layerize)
- [Cline](https://spiral.ai/integrations/cline/seedream-5-0-flash-layerize)
- [Codex](https://spiral.ai/integrations/codex/seedream-5-0-flash-layerize)
- [Cursor](https://spiral.ai/integrations/cursor/seedream-5-0-flash-layerize)
- [Devin](https://spiral.ai/integrations/devin/seedream-5-0-flash-layerize)
- [dots](https://spiral.ai/integrations/dots/seedream-5-0-flash-layerize)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/seedream-5-0-flash-layerize)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/seedream-5-0-flash-layerize)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/seedream-5-0-flash-layerize)
- [goose](https://spiral.ai/integrations/goose/seedream-5-0-flash-layerize)
- [Grok](https://spiral.ai/integrations/grok/seedream-5-0-flash-layerize)
- [Grok Build](https://spiral.ai/integrations/grok-build/seedream-5-0-flash-layerize)
- [Hermes](https://spiral.ai/integrations/hermes/seedream-5-0-flash-layerize)
- [Instinct](https://spiral.ai/integrations/instinct/seedream-5-0-flash-layerize)
- [Manus](https://spiral.ai/integrations/manus/seedream-5-0-flash-layerize)
- [Muse](https://spiral.ai/integrations/muse/seedream-5-0-flash-layerize)
- [Muse Code](https://spiral.ai/integrations/muse-code/seedream-5-0-flash-layerize)
- [n8n](https://spiral.ai/integrations/n8n/seedream-5-0-flash-layerize)
- [Notion](https://spiral.ai/integrations/notion/seedream-5-0-flash-layerize)
- [OpenClaw](https://spiral.ai/integrations/openclaw/seedream-5-0-flash-layerize)
- [opencode](https://spiral.ai/integrations/opencode/seedream-5-0-flash-layerize)
- [Perplexity](https://spiral.ai/integrations/perplexity/seedream-5-0-flash-layerize)
- [Raycast](https://spiral.ai/integrations/raycast/seedream-5-0-flash-layerize)
- [VS Code](https://spiral.ai/integrations/vscode/seedream-5-0-flash-layerize)
- [Windsurf](https://spiral.ai/integrations/windsurf/seedream-5-0-flash-layerize)
- [Zapier](https://spiral.ai/integrations/zapier/seedream-5-0-flash-layerize)

## More Gemini guides

- [Seedream 5.0 Flash Image Editing](https://spiral.ai/integrations/gemini/seedream-5-0-flash-image-editing)
- [Seedream 5.0 Flash Text to Image](https://spiral.ai/integrations/gemini/seedream-5-0-flash-text-to-image)
- [Seedream 4.5 Text to Image](https://spiral.ai/integrations/gemini/seedream-4-5-text-to-image)
- [Seedream 5.0 Lite Image Editing](https://spiral.ai/integrations/gemini/seedream-5-0-lite-image-editing)
- [Seedream 4.5 Edit](https://spiral.ai/integrations/gemini/seedream-4-5-edit)
- [Seedream 5.0 Lite Text to Image](https://spiral.ai/integrations/gemini/seedream-5-0-lite-text-to-image)

## Questions about Seedream 5.0 Flash Layerize in Gemini

**Can Gemini use Seedream 5.0 Flash Layerize?**

Yes. Add Spiral to Gemini as an MCP server, and Gemini can find and run Seedream 5.0 Flash Layerize like any built-in tool.

**How much does Seedream 5.0 Flash Layerize cost in Gemini?**

$0.0351 per image. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Gemini plan is separate.

**Do I need a fal account to use Seedream 5.0 Flash Layerize in Gemini?**

No. Spiral runs Seedream 5.0 Flash Layerize 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 5.0 Flash Layerize in Gemini?**

About two minutes: open Connected Apps, then add Spiral as a custom app, then sign in to Spiral and approve.

**Does Gemini wait while Seedream 5.0 Flash Layerize runs?**

Seedream 5.0 Flash Layerize runs in the background. Gemini starts the run, checks on it and gives you the image when it's ready.

**What does Seedream Layerize produce?**

It separates a finished image into one base image and up to 16 editable layers. The separated elements are transparent PNGs you can reuse in a composition.

**How do Flash and Pro differ?**

Flash emphasizes speed, while Pro prioritizes image quality. Both have the same maximum of one base image plus 16 separated layers.

**Can I choose which objects become layers?**

Describe the elements you want separated, such as the person, headline, and lower-right icon. For precise region targeting, use normalized bounding-box tags; without instructions, the model selects the major elements.

**Are all the output layers the same size?**

Each layer keeps the aspect ratio of its corresponding region. Outputs use automatic sizing or a 1K, 1.5K, or 2K tier, so do not assume every layer has the base image's dimensions.

**Can it separate every small object in a crowded image?**

The ceiling is 16 separated layers plus the base image. Requests exceeding that ceiling can lose layer information, so prioritize the elements you need to edit.

