> ## Documentation Index
> Fetch the complete documentation index at: https://docs.leapx-hub.com/llms.txt
> Use this file to discover all available pages before exploring further.

# 万物迁移-服装模式-提交任务

## 简介

提交万物迁移-服装模式任务，用于实现虚拟试装功能。

## 认证

<ParamField header="Authorization" type="string" required>
  Bearer Token，如 `Bearer eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9...`
  获取方法：依照左侧最上面认证模块的post接口获取，`https://docs.leapx-hub.com/cn/leapx-lab-v4/endpoint/get-token`
</ParamField>

## 请求参数

<ParamField body="cVDressingV4DTO.model.url" type="string" required>
  模特图片 URL
</ParamField>

<ParamField body="cVDressingV4DTO.garment.data" type="object[]" required>
  服装素材列表
</ParamField>

<ParamField body="cVDressingV4DTO.garment.data[].type" type="string" required>
  素材类型（如：image）
</ParamField>

<ParamField body="cVDressingV4DTO.garment.data[].url" type="string" required>
  素材 URL
</ParamField>

<ParamField body="cVDressingV4DTO.req_key" type="string">
  请求标识，用于业务侧关联或去重
</ParamField>

<ParamField body="cVDressingV4DTO.return_url" type="boolean">
  是否直接返回结果 URL
</ParamField>

<ParamField body="cVDressingV4DTO.inference_config.do_sr" type="boolean">
  是否开启超分
</ParamField>

<ParamField body="cVDressingV4DTO.inference_config.seed" type="integer">
  随机种子
</ParamField>

<ParamField body="cVDressingV4DTO.inference_config.keep_head" type="boolean">
  保留头部
</ParamField>

<ParamField body="cVDressingV4DTO.inference_config.keep_hand" type="boolean">
  保留手部
</ParamField>

<ParamField body="cVDressingV4DTO.inference_config.keep_foot" type="boolean">
  保留脚部
</ParamField>

<ParamField body="cVDressingV4DTO.inference_config.num_steps" type="integer">
  生成步数
</ParamField>

<ParamField body="cVDressingV4DTO.inference_config.keep_upper" type="boolean">
  保留上半身
</ParamField>

<ParamField body="cVDressingV4DTO.inference_config.keep_lower" type="boolean">
  保留下半身
</ParamField>

<ParamField body="cVDressingV4DTO.inference_config.tight_mask" type="string">
  紧致蒙版
</ParamField>

<ParamField body="cVDressingV4DTO.inference_config.p_bbox_iou_ratio" type="number">
  人体框 IOU 比例
</ParamField>

<ParamField body="cVDressingV4DTO.inference_config.p_bbox_expand_ratio" type="number">
  人体框扩展比例
</ParamField>

<ParamField body="cVDressingV4DTO.inference_config.max_process_side_length" type="integer">
  最大处理边长
</ParamField>

<ParamField body="cVDressingV4DTO.logoInfo.add_logo" type="boolean">
  是否添加 Logo
</ParamField>

<ParamField body="cVDressingV4DTO.logoInfo.position" type="integer">
  Logo 位置
</ParamField>

<ParamField body="cVDressingV4DTO.logoInfo.language" type="integer">
  Logo 语言
</ParamField>

<ParamField body="cVDressingV4DTO.logoInfo.opacity" type="number">
  Logo 透明度
</ParamField>

### 示例代码

<Tabs>
  <Tab title="cURL示例">
    ```bash theme={null}
    curl -X POST "https://leapx-hub.com/prod-api/nebula/v4/api/dressing2Submitv4" \
      -H "Content-Type: application/json" \
      -H "Authorization: Bearer sk-xxxxxxxxxx" \
      -d '{
        "imageUrl": "https://example.com/model.jpg",
        "clothingUrl": "https://example.com/clothing.jpg"
      }'
    ```
  </Tab>

  <Tab title="Python示例">
    ```python theme={null}
    import requests
    import json

    url = "https://leapx-hub.com/prod-api/nebula/v4/api/dressing2Submitv4"
    headers = {
        "Content-Type": "application/json",
        "Authorization": "Bearer sk-xxxxxxxxxx"
    }
    data = {
        "imageUrl": "https://example.com/model.jpg",
        "clothingUrl": "https://example.com/clothing.jpg"
    }

    response = requests.post(url, headers=headers, data=json.dumps(data))
    print(response.json())
    ```
  </Tab>
</Tabs>

### 响应示例

<ResponseExample>
  ```json theme={null}
  {
    "code": 200,
    "msg": "操作成功",
    "data": {
      "task_id": "task-1234567890"
    }
  }
  ```
</ResponseExample>