# MiniMax H3 Reference to Video LoRA Trainer API

> 用于参考条件视频的 LoRA 训练器，支持从已有 LoRA 热启动

根据主体视频片段的 zip 文件训练 LoRA，使参考输入能够引导视频生成。`reference_conditioning_p` 设置训练期间使用参考内容的频率，`resume_from_lora_url` 从之前训练的 LoRA 继续训练。还可配置：`rank`、`number_of_steps`、`number_of_frames`、`frame_rate` 和 `aspect_ratio`。返回权重和配置文件。

- 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.com/v1/run/minimax/h3/ref2va/trainer`
- Quote: `POST https://api.doitong.com/v1/quote/minimax/h3/ref2va/trainer`
- Docs page: https://doitong.com/zh/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.com/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 |  |  | 主题训练视频 ZIP 的 URL；纯图像数据集和混合图像/视频训练压缩包会被拒绝，因此图像必须改为参考侧载资源。可选附加文件与每个片段共享基本名称：例如说明文件 `clip01.txt`，以及从 `ref_1` 到 `ref_4` 的有序参考文件，命名为 `clip01.ref_1.<ext>` 到 `clip01.ref_4.<ext>`；没有参考侧载资源时，会使用片段中的一帧作为自身参考。`<ext>` 决定参考模态：图像 (.png/.jpg/.jpeg)、音频 (.wav/.mp3/.flac/.m4a/.ogg/.aac) 或视频 (.mp4/.mov/.avi/.mkv/.webm)，其中视频的音轨也会成为音频参考。训练片段支持 .mp4、.mov、.avi 和 .mkv；建议至少提供 10 个片段，越多越好。 |
| `rank` |  | enum (integer) | no | `32` | `8`, `16`, `32`, `64`, `128` | LoRA 适配秩；该值越高，容量越大，但内存消耗也越高。 |
| `number_of_steps` |  | integer | no | `2000` | 1 – 15,000 | 训练步数总数。 |
| `learning_rate` |  | number | no | `0.0002` | 0.000001 – 1 | 优化学习率，在训练速度可能提升与增大后过拟合风险之间进行权衡。 |
| `number_of_frames` |  | integer | no | `73` | 22 – 124 | 每个训练样本的帧数；将其除以 17 后余数必须为 5。示例包括 22、39、56、73、90、107 和 124。 |
| `frame_rate` |  | integer | no | `24` | 8 – 60 | 目标视频帧率，以每秒帧数表示。 |
| `resolution` |  | enum (string) | no | `medium` | `low`, `medium`, `high` | 训练分辨率。提高分辨率会增加内存需求。 |
| `aspect_ratio` |  | enum (string) | no | `16:9` | `21:9`, `16:9`, `4:3`, `1:1`, `3:4`, `9:16` | 从 MiniMax H3 API 提供的同一组选项中选择训练宽高比。 |
| `trigger_phrase` |  | string | no | `` |  | LoRA 样式激活短语，训练期间插入字幕开头。 |
| `reference_conditioning_p` |  | number | no | `0.9` | 0 – 1 | 设置训练使用参考图像条件与无条件文本生成视频音频训练的频率。剩余概率用于无条件目标，以保持仅依赖提示词生成时的稳定性。 |
| `resume_from_lora_url` |  | string \| null | no |  |  | 使用此训练器之前创建的 .safetensors LoRA URL 进行热启动训练，随后执行 number_of_steps 个额外训练步骤。除适配器权重外不会恢复任何内容：优化和学习率调度都会重新开始。 |
| `auto_scale_input` |  | boolean | no | `false` |  | 是否通过自动视频缩放匹配目标 fps 和帧数；true 表示启用此调整。 |
| `split_input_into_scenes` |  | boolean | no | `true` |  | 为超过时长阈值的视频启用场景切分；被切分片段的参考侧载资源会被丢弃。 |
| `split_input_duration_threshold` |  | number | no | `30` | 1 – 60 | 以秒数表示的场景拆分触发阈值：只有超过该时长的视频才会被拆分。 |
| `debug_dataset` |  | boolean | no | `false` |  | 在正式开始完整训练前下载压缩包以检查预处理。启用后，训练器会打包处理后的数据集，以便手动检查说明、参考图像、视频和图像是否正确。 |
| `strict_dataset` |  | boolean | no | `false` |  | 严格处理预处理问题，否则这些问题会被记录并使用文档所述的回退方案解决。启用后，如果说明需要空提示词、缺少参考侧载资源或视频音频无法读取，请求会被拒绝，而不是使用这些回退方案。 |

## 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.com/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.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/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.com/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.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": "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.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
```

### Output fields (`output`)

| Field | Type | Description |
|---|---|---|
| `lora_file` | object {url, content_type, file_name, file_size} | 采用 .safetensors 格式的已训练 LoRA 权重 URL。 |
| `config_file` | object {url, content_type, file_name, file_size} | 推理端点设置的配置。 |
| `debug_dataset` | object {url, content_type, file_name, file_size} \| null | 仅适用于启用 `debug_dataset` 的请求；此可下载压缩包包含预处理后的训练数据。 |

## 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.com/v1/models/minimax/h3/ref2va/trainer