**Cost**: 13 credits per successful call.

Image Layering supports two input modes:

1. **JSON URL mode**: send `application/json` with the existing URL field.
2. **Direct upload mode**: send `multipart/form-data` with a local image file in the `image` field. The compatible field name `file` is also accepted for the primary image. Codia checks credits before reading and uploading the file, so insufficient-credit requests return `402` without uploading anything.

Direct upload example:

```bash
curl 'https://openapi.codia.ai/v2/open/image/layering' \
  -H 'Authorization: Bearer {codia_api_key}' \
  -F 'image=@./image.png'
```

Decompose a single image into an **ordered stack of editable layers** — background, subject(s), and overlays — each rendered separately. The output is a JSON DSL describing the layer tree plus the per-layer image data. Use this when you want a designer-style PSD-equivalent, not a single flat composition.

## What this API is for

Turning a flat marketing image back into editable components; pre-processing for downstream compositing; setting up animated reveals where each layer animates separately; segmenting photo content for fine-grained editing.

Different from `image_to_design`: that one returns a structural design-tree (Body / Layer / Text / Image nodes with positions and styles). `image_layering` returns visual layers (independent rendered images that you can stack). They complement each other.

## Request

| Field | Required | Notes |
|---|---|---|
| `image_url` | yes | Public URL of the image to decompose. |

No `model` parameter — uses Codia's layering pipeline.

## Response

Unique to this endpoint:

| Field | Type | Meaning |
|---|---|---|
| `data.type` | integer | Result-type code. Identifies the schema variant of `dsl`. |
| `data.dsl` | string | **JSON-encoded** layer tree. Parse client-side. Contains layer metadata + URLs to the rendered layer images. |

```json
{ "code": 0, "message": "ok", "data": { "type": 1, "dsl": "{\"layers\":[…]}" } }
```

The `dsl` field is intentionally a string (not a nested object) so you can store it verbatim or stream it without re-encoding.

## Billing & limits

- 13 credits per request from the unified Codia Open API balance.
- Synchronous.

## Errors

Standard set.

> **Sync vs. async**
> This synchronous endpoint returns the result inline — the simplest path. For production pipelines that need webhook delivery, automatic retry with idempotency, or explicit task cancellation, call `POST /v2/open/tasks` with `operation=image_layering` instead. Inputs and credit cost are identical.

可选，由用户自定义的幂等键（最多 255 个字符）。设置后，成功（2xx）的响应会缓存 7 天。使用相同的键 + 相同的请求体重试，会返回缓存的响应（不额外扣除积分）；使用相同的键但不同的请求体重试，则返回 409。用于确保 POST 请求在网络故障时可以安全重试。对于 multipart/form-data 上传，请求会按表单字段和文件内容进行比较，因此即使客户端生成了新的 multipart boundary，重试的上传也会被重放。

Idempotency-Key

image_url

image

兼容用的源图片文件字段（已弃用：请改用 `image`）。

file

code

message

type

data

请求体格式错误或缺少必填参数

Idempotency-Key 已被用于不同的请求体。

请求频率超限。请等待 `Retry-After` 响应头中指定的秒数后再重试。

Image

LAUNCH OFFER

SHOP NOW

skin tone.

Vitamin C + hyaluronic acid for a bright

Vitamin C + hyaluronic acid for a brighter, even

Glow Serum

SKINCARE · NEW

VELORA

将一张扁平图片拆分为有序的图层堆栈（背景、主体、文字和叠加元素），每层均可单独编辑。

图像分层

输入

输出

相关 API