# Wan 2.2 14B Image Trainer API

> 使用你的圖片訓練 Wan 2.2 14B LoRA，以建立主體或風格，並回傳低雜訊與高雜訊 LoRA 檔案

使用 `training_data_url` 中的資料集，為 Wan 2.2 文字轉圖片微調 LoRA，並以必要的 `trigger_phrase` 作為觸發詞。`steps` 範圍為 10 到 6000，`learning_rate` 為 1e-6 到 0.1。可切換臉部偵測、臉部裁切與遮罩；`is_style` 會關閉臉部專用選項。輸出包括設定檔，以及分開的低雜訊和高雜訊 LoRA 檔案。

- Model id: `wan-22-image-trainer`
- Made by: Alibaba
- Category: Training
- Output: file
- Price per run: from $0.45 / run (cheapest run $0.45 (450 API credits))
- Run: `POST https://api.doitong.com/v1/run/wan-22-image-trainer`
- Quote: `POST https://api.doitong.com/v1/quote/wan-22-image-trainer`
- Docs page: https://doitong.com/zh-TW/developers/models/wan-22-image-trainer

## Pricing

Price: **from $0.45 / run** (the lowest tier; the quote prices your exact input). Price per run: the input files are measured before the run (length, resolution, frame rate). The quote measures the same files and is exactly what the run charges.

The full example input below costs $4.50 = 4500 API credits (1 run × $4.50).

Prices are the upstream price in USD, paid from the API balance in API credits (1000 API credits = 1 USD). `POST https://api.doitong.com/v1/quote/wan-22-image-trainer` with the same JSON body returns the exact price for that input; the quote is exactly what a run charges. Invalid input is never charged and failed or canceled requests are refunded automatically.

## Input parameters

| Parameter | Canonical name | Type | Required | Default | Allowed values / range | Description |
|---|---|---|---|---|---|---|
| `training_data_url` |  | string | yes |  |  | 以 URL 表示的訓練資料位置。 |
| `trigger_phrase` |  | string | yes |  |  | 用於觸發模型的詞組。 |
| `include_synthetic_captions` |  | boolean | no | `false` |  | 控制是否包含合成說明文字。 |
| `use_face_detection` |  | boolean | no | `true` |  | 訓練圖像的臉部置中調整大小切換開關：啟用臉部偵測後，調整大小時會將偵測到的臉部中心設為圖像中心。 |
| `use_face_cropping` |  | boolean | no | `false` |  | 訓練圖像的臉部裁切切換開關；啟用後，會在調整大小前於臉部周圍新增裁切區域。 |
| `use_masks` |  | boolean | no | `true` |  | 控制訓練資料的遮罩使用方式。 |
| `steps` |  | integer | no | `1000` | 10 – 6,000 | 訓練步驟總數。 |
| `learning_rate` |  | number | no | `0.0007` | 0.000001 – 0.1 | 訓練期間的學習速率。 |
| `is_style` |  | boolean | no | `false` |  | 訓練用的風格資料標記；設為 true 會關閉臉部專屬功能，包括遮罩和臉部偵測。 |

## Example input

Required parameters only:

```json
{
  "training_data_url": "https://example.com/your-file.zip",
  "trigger_phrase": "example"
}
```

A fuller example:

```json
{
  "training_data_url": "https://example.com/your-file.zip",
  "trigger_phrase": "example"
}
```

## Run it

Set `DOITONG_API_KEY` to a key from https://doitong.com/developers/dashboard#keys. `?wait=20` returns the finished request in the same call when it is ready within 20 seconds; otherwise poll `GET /requests/{id}` (it also accepts `?wait=`), or pass `webhook_url`.

### curl

```bash
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.com/v1/run/wan-22-image-trainer?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "training_data_url": "https://example.com/your-file.zip",
    "trigger_phrase": "example"
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.com/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"
```

### JavaScript

```javascript
const API = "https://api.doitong.com/v1";
const headers = {
  "Authorization": "Bearer " + process.env.DOITONG_API_KEY,
  "Content-Type": "application/json",
};

// Run the model; wait up to 20 s for the finished result in the same call
let res = await fetch(API + "/run/wan-22-image-trainer?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "training_data_url": "https://example.com/your-file.zip",
    "trigger_phrase": "example"
  }),
});
let request = await res.json();
if (!res.ok) throw new Error(request.error.code + ": " + request.error.message);

// Not finished yet: long-poll until it is
while (request.status === "queued" || request.status === "running") {
  res = await fetch(API + "/requests/" + request.id + "?wait=20", { headers });
  request = await res.json();
}
if (request.status !== "succeeded") throw new Error(JSON.stringify(request.error));
console.log(request.outputs.map((o) => o.url), request.cost.credits + " API credits ($" + request.cost.usd + ")");
```

### Python

```python
import os
import requests

API = "https://api.doitong.com/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}

payload = {
    "training_data_url": "https://example.com/your-file.zip",
    "trigger_phrase": "example",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/wan-22-image-trainer", params={"wait": 20}, json=payload, headers=headers)
request = r.json()
if not r.ok:
    raise RuntimeError(request["error"]["code"] + ": " + request["error"]["message"])

# Not finished yet: long-poll until it is
while request["status"] in ("queued", "running"):
    request = requests.get(API + "/requests/" + request["id"], params={"wait": 20}, headers=headers).json()
if request["status"] != "succeeded":
    raise RuntimeError(request["error"])
print([o["url"] for o in request["outputs"]], request["cost"]["credits"], "API credits", "$" + request["cost"]["usd"])
```

### MCP

The MCP server at `https://api.doitong.com/v1/mcp` exposes the tools `search_models`, `get_model`, `quote`, `run`, `get_request`, `cancel_request`, `list_requests`, `create_upload` and `get_account`. A `run` call for this model:

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "run",
    "arguments": {
      "model_id": "wan-22-image-trainer",
      "input": {
        "training_data_url": "https://example.com/your-file.zip",
        "trigger_phrase": "example"
      },
      "wait_seconds": 20
    }
  }
}
```

## Response

Every call returns a request object. `status` is one of `queued`, `running`, `succeeded`, `failed`, `canceled`. `outputs` lists the generated files with URLs on our storage (kept forever, or 7 days with `?storage=temporary`; `storage` says which); `output` is the model's own result object with the same URLs.

```json
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "wan-22-image-trainer",
  "status": "succeeded",
  "created_at": "2026-10-20T12:00:00Z",
  "started_at": "2026-10-20T12:00:02Z",
  "completed_at": "2026-10-20T12:00:09Z",
  "queue_position": null,
  "cost": {
    "credits": 4500,
    "usd": "4.50",
    "charged": 4500,
    "refunded": 0
  },
  "input": {
    "training_data_url": "https://example.com/your-file.zip",
    "trigger_phrase": "example"
  },
  "output": {
    "diffusers_lora_file": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_name": "0-output.jpeg",
      "file_size": 1843200
    },
    "high_noise_lora": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_name": "0-output.jpeg",
      "file_size": 1843200
    },
    "config_file": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_name": "0-output.jpeg",
      "file_size": 1843200
    }
  },
  "outputs": [
    {
      "type": "file",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_size": 1843200,
      "stored": true
    }
  ],
  "error": null,
  "metrics": {
    "inference_seconds": 6.8
  },
  "urls": {
    "self": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
```

### Output fields (`output`)

| Field | Type | Description |
|---|---|---|
| `diffusers_lora_file` | object {url, content_type, file_name, file_size} | 低雜訊用的 LoRA 檔案。 |
| `high_noise_lora` | object {url, content_type, file_name, file_size} | 高雜訊用的 LoRA 檔案。 |
| `config_file` | object {url, content_type, file_name, file_size} | 支援訓練後推論端點的設定檔。 |

## Related models

- [Qwen Image 2512 Trainer](https://doitong.com/developers/models/qwen-image-2512-trainer.md) (`qwen-image-2512-trainer`): from $0.75 / run
- [Qwen Image Edit 2509 Trainer](https://doitong.com/developers/models/qwen-image-edit-2509-trainer.md) (`qwen-image-edit-2509-trainer`): from $0.40 / run
- [Wan-2.1 LoRA Trainer · I2V 720p](https://doitong.com/developers/models/wan-trainer/i2v-720p.md) (`wan-trainer/i2v-720p`): $0.005 / step
- [Wan-2.1 LoRA Trainer · T2V](https://doitong.com/developers/models/wan-trainer/t2v.md) (`wan-trainer/t2v`): $0.005 / step
- [Wan-2.1 LoRA Trainer · T2V 14b](https://doitong.com/developers/models/wan-trainer/t2v-14b.md) (`wan-trainer/t2v-14b`): $0.005 / step
- [Wan-2.2 LoRA Trainer · I2V A14b](https://doitong.com/developers/models/wan-22-trainer/i2v-a14b.md) (`wan-22-trainer/i2v-a14b`): $0.005 / step
- [Wan-2.2 LoRA Trainer · T2V A14b](https://doitong.com/developers/models/wan-22-trainer/t2v-a14b.md) (`wan-22-trainer/t2v-a14b`): $0.004 / step
- [Z Image Trainer](https://doitong.com/developers/models/z-image-trainer.md) (`z-image-trainer`): $0.00226 / step

## Links

- HTML page: https://doitong.com/developers/models/wan-22-image-trainer
- All models and guides for AI agents: https://doitong.com/developers/llms.txt
- OpenAPI 3.1 with this model's typed request body: https://doitong.com/developers/openapi.json?model=wan-22-image-trainer
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.com/v1/models/wan-22-image-trainer