# MiniMax H3 Reference to Video LoRA Trainer API

> Pelatih LoRA untuk video berpandukan rujukan, dengan permulaan hangat daripada LoRA terdahulu

Melatih LoRA pada zip klip video subjek supaya input rujukan dapat memandu penjanaan video. `reference_conditioning_p` menetapkan kekerapan rujukan digunakan semasa latihan, dan `resume_from_lora_url` meneruskan daripada LoRA yang telah dilatih. Boleh dikonfigurasikan juga: `rank`, `number_of_steps`, `number_of_frames`, `frame_rate` dan `aspect_ratio`. Mengembalikan berat dan fail konfigurasi.

- 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/ms/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 |  |  | URL ZIP video latihan subjek; set data imej sahaja dan arkib latihan imej/video campuran akan ditolak, jadi imej mesti digunakan sebagai sidecar rujukan. Tambahan pilihan berkongsi nama asas setiap klip: kapsyen seperti `clip01.txt` dan rujukan tersusun daripada `ref_1` hingga `ref_4`, dinamakan `clip01.ref_1.<ext>` hingga `clip01.ref_4.<ext>`; tanpa sidecar rujukan, bingkai daripada klip membekalkan rujukannya sendiri. `<ext>` menentukan modaliti rujukan: imej (.png/.jpg/.jpeg), audio (.wav/.mp3/.flac/.m4a/.ogg/.aac) atau video (.mp4/.mov/.avi/.mkv/.webm), yang runut bunyinya turut menjadi rujukan audio. Klip latihan menyokong .mp4, .mov, .avi dan .mkv; sasarkan sekurang-kurangnya 10 klip, dengan lebih banyak adalah lebih baik. |
| `rank` |  | enum (integer) | no | `32` | `8`, `16`, `32`, `64`, `128` | Rank penyesuaian LoRA, menukar penggunaan memori yang meningkat dengan kapasiti yang lebih besar apabila tetapan dinaikkan. |
| `number_of_steps` |  | integer | no | `2000` | 1 – 15,000 | Jumlah langkah latihan. |
| `learning_rate` |  | number | no | `0.0002` | 0.000001 – 1 | Kadar pembelajaran pengoptimuman, mengimbangi kemungkinan peningkatan kelajuan latihan dengan risiko terlebih suai apabila dinaikkan. |
| `number_of_frames` |  | integer | no | `73` | 22 – 124 | Bilangan bingkai bagi setiap sampel latihan; pembahagiannya dengan 17 mesti meninggalkan baki 5. Contohnya termasuk 22, 39, 56, 73, 90, 107 dan 124. |
| `frame_rate` |  | integer | no | `24` | 8 – 60 | Kadar bingkai video sasaran, diukur dalam bingkai sesaat. |
| `resolution` |  | enum (string) | no | `medium` | `low`, `medium`, `high` | Resolusi latihan. Meningkatkan resolusi meningkatkan keperluan memori. |
| `aspect_ratio` |  | enum (string) | no | `16:9` | `21:9`, `16:9`, `4:3`, `1:1`, `3:4`, `9:16` | Pilih nisbah aspek latihan daripada set yang sama yang tersedia melalui MiniMax H3 API. |
| `trigger_phrase` |  | string | no | `` |  | Frasa pengaktifan gaya LoRA, disisipkan pada permulaan kapsyen semasa latihan. |
| `reference_conditioning_p` |  | number | no | `0.9` | 0 – 1 | Tetapkan kekerapan latihan menggunakan pelaziman imej rujukan berbanding latihan teks-ke-video-audio tanpa pelaziman. Sebarang kebarangkalian yang berbaki digunakan untuk objektif tanpa pelaziman bagi mengekalkan penjanaan stabil berasaskan prompt sahaja. |
| `resume_from_lora_url` |  | string \| null | no |  |  | URL untuk latihan warm-start dengan LoRA .safetensors yang sebelum ini dicipta oleh pelatih ini, diikuti number_of_steps langkah latihan tambahan. Tiada apa-apa selain pemberat penyesuai dipulihkan: pengoptimuman dan penjadualan kadar pembelajaran bermula semula. |
| `auto_scale_input` |  | boolean | no | `false` |  | Sama ada fps sasaran dan bilangan bingkai dipadankan melalui penskalaan video automatik; true mendayakan pelarasan ini. |
| `split_input_into_scenes` |  | boolean | no | `true` |  | Dayakan pemisahan adegan untuk video yang melebihi ambang durasi, dengan membuang sidecar rujukan daripada mana-mana klip yang dipisahkan. |
| `split_input_duration_threshold` |  | number | no | `30` | 1 – 60 | Pencetus pemisahan adegan yang dinyatakan sebagai tempoh dalam saat: hanya video yang lebih panjang daripada ambang akan dipisahkan. |
| `debug_dataset` |  | boolean | no | `false` |  | Pilihan untuk memuat turun arkib bagi menyemak prapemprosesan sebelum memulakan latihan penuh. Apabila didayakan, pelatih membungkus set data yang diproses supaya anda boleh memeriksa kapsyen, imej rujukan, video dan imej secara manual. |
| `strict_dataset` |  | boolean | no | `false` |  | Pengendalian ketat masalah prapemprosesan yang sebaliknya akan dilog dan diselesaikan menggunakan sandaran yang didokumenkan. Mendayakannya menolak kapsyen yang memerlukan prompt kosong, sidecar rujukan yang hilang dan video dengan audio tidak boleh dibaca, bukannya membenarkan sandaran tersebut. |

## 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} | URL untuk pemberat LoRA terlatih dalam format .safetensors. |
| `config_file` | object {url, content_type, file_name, file_size} | Konfigurasi untuk persediaan endpoint inferens. |
| `debug_dataset` | object {url, content_type, file_name, file_size} \| null | Hanya tersedia untuk permintaan dengan `debug_dataset` didayakan, arkib boleh dimuat turun ini mengandungi data latihan selepas prapemprosesan. |

## 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