# MiniMax H3 Reference to Video LoRA Trainer API

> 用於參考條件影片的 LoRA 訓練器，可從先前的 LoRA 暖啟動

在主體影片片段的 zip 檔上訓練 LoRA，讓參考輸入引導影片生成。`reference_conditioning_p` 設定訓練期間使用參考內容的頻率，`resume_from_lora_url` 可從先前訓練的 LoRA 繼續。另可設定：`rank`、`number_of_steps`、`number_of_frames`、`frame_rate` 與 `aspect_ratio`。回傳權重與設定檔。

- Model id: `minimax/h3/ref2va/trainer`
- Made by: MiniMax
- Category: Training
- Output: file
- Price: $0.015 / step (cheapest run $30.00 (30000 API credits))
- Run: `POST https://api.doitong.ru/v1/run/minimax/h3/ref2va/trainer`
- Quote: `POST https://api.doitong.ru/v1/quote/minimax/h3/ref2va/trainer`
- Docs page: https://doitong.com/zh-TW/developers/models/minimax/h3/ref2va/trainer

## Pricing

Price: **$0.015 / step**. Billed per training step (`number_of_steps`).

The full example input below costs $30.00 = 30000 API credits (2000 steps × 15 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.ru/v1/quote/minimax/h3/ref2va/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 |  |  | 主體訓練影片 ZIP URL；純圖像資料集和混合圖像／影片訓練封存檔會被拒絕，因此圖像必須改作參考側載檔。可選附加檔案與各片段共用基本檔名：例如 `clip01.txt` 說明檔，以及從 `ref_1` 到 `ref_4` 的依序參考檔，命名為 `clip01.ref_1.<ext>` 至 `clip01.ref_4.<ext>`；若沒有參考側載檔，則使用片段中的影格作為自身參考。`<ext>` 決定參考模態：圖像 (.png/.jpg/.jpeg)、音訊 (.wav/.mp3/.flac/.m4a/.ogg/.aac) 或影片 (.mp4/.mov/.avi/.mkv/.webm)，其中影片的音軌也會成為音訊參考。訓練片段支援 .mp4、.mov、.avi 和 .mkv；建議至少 10 個片段，越多越好。 |
| `rank` |  | enum (integer) | no | `32` | `8`, `16`, `32`, `64`, `128` | LoRA 適配階數；設定越高，記憶體消耗越大，但容量也越高。 |
| `number_of_steps` |  | integer | no | `2000` | 1 – 15,000 | 訓練步驟總數。 |
| `learning_rate` |  | number | no | `0.0002` | 0.000001 – 1 | 最佳化學習率，在提高時權衡訓練可能加速與過度擬合的風險。 |
| `number_of_frames` |  | integer | no | `73` | 22 – 124 | 每個訓練樣本的影格數；除以 17 後餘數必須為 5。範例包括 22、39、56、73、90、107 和 124。 |
| `frame_rate` |  | integer | no | `24` | 8 – 60 | 目標影片影格速率，以每秒影格數表示。 |
| `resolution` |  | enum (string) | no | `medium` | `low`, `medium`, `high` | 訓練解析度。提高解析度會增加記憶體需求。 |
| `aspect_ratio` |  | enum (string) | no | `16:9` | `21:9`, `16:9`, `4:3`, `1:1`, `3:4`, `9:16` | 從 MiniMax H3 API 提供的相同集合中選擇訓練長寬比。 |
| `trigger_phrase` |  | string | no | `` |  | LoRA 風格啟用片語，訓練時插入說明的開頭。 |
| `reference_conditioning_p` |  | number | no | `0.9` | 0 – 1 | 設定訓練使用參考圖像條件控制與無條件文字轉影片音訊訓練的頻率。剩餘的機率會分配給無條件目標，以維持穩定的純提示詞生成。 |
| `resume_from_lora_url` |  | string \| null | no |  |  | 使用此訓練器先前建立的 .safetensors LoRA 進行暖啟動訓練的 URL，後接 number_of_steps 個額外訓練步驟。除了配接器權重外不會還原任何內容：最佳化和學習率排程都會重新開始。 |
| `auto_scale_input` |  | boolean | no | `false` |  | 是否透過自動影片縮放來匹配目標 fps 和影格數；true 會啟用此調整。 |
| `split_input_into_scenes` |  | boolean | no | `true` |  | 為超過持續時間門檻的影片啟用場景分割；分割片段的參考側載檔會被捨棄。 |
| `split_input_duration_threshold` |  | number | no | `30` | 1 – 60 | 以秒數表示的場景分割觸發門檻：只有長於該門檻的影片才會分割。 |
| `debug_dataset` |  | boolean | no | `false` |  | 在提交完整訓練前下載封存檔以檢查預處理的選項。啟用後，訓練器會封裝處理後的資料集，供你手動檢查說明、參考圖像、影片和圖像是否正確。 |
| `strict_dataset` |  | boolean | no | `false` |  | 嚴格處理預處理問題；否則這些問題會被記錄並使用文件所述的備援方式解決。啟用後，若說明需要空白提示詞、缺少參考側載檔，或影片音訊無法讀取，請求會被拒絕，而不會使用這些備援方式。 |

## Example input

Required parameters only:

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

A fuller example:

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

## 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.ru/v1/run/minimax/h3/ref2va/trainer?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "training_data_url": "https://example.com/your-file.zip"
  }'

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

### JavaScript

```javascript
const API = "https://api.doitong.ru/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/minimax/h3/ref2va/trainer?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "training_data_url": "https://example.com/your-file.zip"
  }),
});
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.ru/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}

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

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/minimax/h3/ref2va/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.ru/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": "minimax/h3/ref2va/trainer",
      "input": {
        "training_data_url": "https://example.com/your-file.zip"
      },
      "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": "minimax/h3/ref2va/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": 30000,
    "usd": "30.00",
    "charged": 30000,
    "refunded": 0
  },
  "input": {
    "training_data_url": "https://example.com/your-file.zip"
  },
  "output": {
    "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
    },
    "debug_dataset": {
      "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.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
```

### Output fields (`output`)

| Field | Type | Description |
|---|---|---|
| `lora_file` | object {url, content_type, file_name, file_size} | `.safetensors` 格式訓練 LoRA 權重的 URL。 |
| `config_file` | object {url, content_type, file_name, file_size} | 推論端點設定的組態。 |
| `debug_dataset` | object {url, content_type, file_name, file_size} \| null | 僅適用於啟用 `debug_dataset` 的請求；此可下載封存檔包含預處理後的訓練資料。 |

## Related models

- [MiniMax H3 First Last Frame LoRA Trainer](https://doitong.com/developers/models/minimax/h3/flf2v/trainer.md) (`minimax/h3/flf2v/trainer`): $0.01 / step
- [MiniMax H3 Image to Video Audio LoRA Trainer](https://doitong.com/developers/models/minimax/h3/i2v/trainer.md) (`minimax/h3/i2v/trainer`): $0.01 / step
- [MiniMax H3 Text to Video LoRA Trainer](https://doitong.com/developers/models/minimax/h3/t2v/trainer.md) (`minimax/h3/t2v/trainer`): $0.005 / step
- [ERNIE-Image Trainer](https://doitong.com/developers/models/ernie-image-trainer.md) (`ernie-image-trainer`): $0.0012 / step
- [FLUX 2 \[klein\] 9b Base Trainer](https://doitong.com/developers/models/flux-2-klein-9b-base-trainer.md) (`flux-2-klein-9b-base-trainer`): $0.0043 / step
- [Flux 2 Klein 9B Base Trainer](https://doitong.com/developers/models/flux-2-klein-9b-base-trainer/edit.md) (`flux-2-klein-9b-base-trainer/edit`): $0.0139 / step
- [FLUX 2 Trainer](https://doitong.com/developers/models/flux-2-trainer.md) (`flux-2-trainer`): $0.0064 / step
- [FLUX 2 Trainer Edit](https://doitong.com/developers/models/flux-2-trainer/edit.md) (`flux-2-trainer/edit`): $0.0389 / step

## Links

- HTML page: https://doitong.com/developers/models/minimax/h3/ref2va/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=minimax/h3/ref2va/trainer
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.ru/v1/models/minimax/h3/ref2va/trainer