# Ideogram V4.0q LoRA Trainer API

> Huấn luyện LoRA tùy chỉnh cho Ideogram V4 từ ZIP ảnh có chú thích

Huấn luyện LoRA trên bộ dữ liệu của bạn để cá nhân hóa hoặc tạo phong cách cụ thể. `images_data_url` trỏ đến ZIP ảnh, với chú thích đọc từ các tệp .txt cùng tên, và `default_caption` điền phần còn thiếu. `steps` từ 100 đến 40000 (mặc định 1000), còn `learning_rate` và `resolution` có thể điều chỉnh. Trả về tệp trọng số LoRA và tệp cấu hình.

- Model id: `ideogram/v4/trainer`
- Made by: Ideogram
- Category: Training
- Output: file
- Price: $0.00675 / step (cheapest run $6.75 (6750 API credits))
- Run: `POST https://api.doitong.com/v1/run/ideogram/v4/trainer`
- Quote: `POST https://api.doitong.com/v1/quote/ideogram/v4/trainer`
- Docs page: https://doitong.com/vi/developers/models/ideogram/v4/trainer

## Pricing

Price: **$0.00675 / step**. Billed per training step (`steps`).

The full example input below costs $6.75 = 6750 API credits (1000 steps × 6.75 API credits).

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/ideogram/v4/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 |
|---|---|---|---|---|---|---|
| `images_data_url` |  | string | yes |  |  | URL ZIP dữ liệu huấn luyện chứa hình ảnh và chú thích, trong đó mỗi chú thích được lưu trong tệp .txt có cùng phần tên tệp với hình ảnh. Bộ huấn luyện sử dụng tập dữ liệu chỉ chứa mục tiêu mà prepare_dataset_dir chuẩn bị. |
| `steps` |  | integer | no | `1000` | 100 – 40,000 | Số bước huấn luyện LoRA. |
| `default_caption` |  | string \| null | no |  |  | Chú thích áp dụng cho mọi hình ảnh khi force_default_caption là true, ghi đè các tệp chú thích; nếu không, chỉ dùng cho hình ảnh thiếu tệp chú thích. |
| `resolution` |  | string | no | `auto` |  | Kích thước hình ảnh huấn luyện, được chỉ định dưới dạng giá trị đặt trước, auto hoặc chuỗi WIDTHxHEIGHT tùy chỉnh với mỗi chiều chia hết cho 16. Cắt giữa không bao giờ phóng to hình ảnh; auto chọn phần cắt lớn nhất mà tập dữ liệu dùng chung và không cần phóng to. Các giá trị đặt trước là 1024x1024 (square), 1536x1024 (landscape), 1024x1536 (portrait), 1920x1088 (widescreen), 2048x768 (ultrawide), 1024x1792 (phone_wallpaper) và 1584x400 (social_banner). |
| `learning_rate` |  | number | no | `0.0001` | 0.000001 – 0.01 |  |

## Example input

Required parameters only:

```json
{
  "images_data_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
}
```

A fuller example:

```json
{
  "images_data_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
}
```

## 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/ideogram/v4/trainer?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "images_data_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
  }'

# 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/ideogram/v4/trainer?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "images_data_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
  }),
});
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 = {
    "images_data_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/ideogram/v4/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": "ideogram/v4/trainer",
      "input": {
        "images_data_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
      },
      "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": "ideogram/v4/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": 6750,
    "usd": "6.75",
    "charged": 6750,
    "refunded": 0
  },
  "input": {
    "images_data_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
  },
  "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
    },
    "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} | URL của trọng số LoRA Ideogram V4 được tạo ra sau khi huấn luyện. |
| `config_file` | object {url, content_type, file_name, file_size} | URL của cấu hình huấn luyện công khai. |

## Related models

- [Ideogram V4.0 Text to Image](https://doitong.com/developers/models/ideogram/v4.md) (`ideogram/v4`): from $0.0075 / megapixel of output image
- [Ideogram V4.0q \[fast\]](https://doitong.com/developers/models/ideogram/v4/fast.md) (`ideogram/v4/fast`): from $0.00525 / megapixel of output image
- [Ideogram V4.0q \[instant\]](https://doitong.com/developers/models/ideogram/v4/instant.md) (`ideogram/v4/instant`): $0.0075 / megapixel of output image
- [Ideogram V4.0q Text to Image (LoRA)](https://doitong.com/developers/models/ideogram/v4/lora.md) (`ideogram/v4/lora`): from $0.0113 / megapixel of output image
- [Ideogram V4.0q Image to Image](https://doitong.com/developers/models/ideogram/v4/image-to-image.md) (`ideogram/v4/image-to-image`): from $0.0075 / megapixel of output image
- [Ideogram V4.0q Image to Image LoRA](https://doitong.com/developers/models/ideogram/v4/image-to-image/lora.md) (`ideogram/v4/image-to-image/lora`): from $0.0113 / megapixel of output image
- [Ideogram V4.0q Tiling](https://doitong.com/developers/models/ideogram/v4/tiling.md) (`ideogram/v4/tiling`): from $0.03 / megapixel
- [Ideogram V4.0q Tiling LoRA](https://doitong.com/developers/models/ideogram/v4/tiling/lora.md) (`ideogram/v4/tiling/lora`): from $0.0338 / megapixel

## Links

- HTML page: https://doitong.com/developers/models/ideogram/v4/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=ideogram/v4/trainer
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.com/v1/models/ideogram/v4/trainer