# MiniMax H3 Reference to Video LoRA Trainer API

> Pelatih LoRA untuk video yang dikondisikan referensi, dengan warm start dari LoRA sebelumnya

Melatih LoRA pada zip klip video subjek agar input referensi dapat mengarahkan generasi video. `reference_conditioning_p` menentukan seberapa sering referensi digunakan selama pelatihan, dan `resume_from_lora_url` melanjutkan dari LoRA yang telah dilatih sebelumnya. Dapat dikonfigurasi juga: `rank`, `number_of_steps`, `number_of_frames`, `frame_rate`, dan `aspect_ratio`. Mengembalikan bobot dan file 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.com/v1/run/minimax/h3/ref2va/trainer`
- Quote: `POST https://api.doitong.com/v1/quote/minimax/h3/ref2va/trainer`
- Docs page: https://doitong.com/id/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 |  |  | URL ZIP video pelatihan subjek; dataset yang hanya berisi gambar dan arsip pelatihan campuran gambar/video akan ditolak, sehingga gambar harus digunakan sebagai sidecar referensi. Ekstra opsional menggunakan nama dasar setiap klip: keterangan seperti `clip01.txt` dan referensi berurutan dari `ref_1` hingga `ref_4`, bernama `clip01.ref_1.<ext>` hingga `clip01.ref_4.<ext>`; tanpa sidecar referensi, bingkai dari klip digunakan sebagai referensinya sendiri. `<ext>` menentukan modalitas referensi: gambar (.png/.jpg/.jpeg), audio (.wav/.mp3/.flac/.m4a/.ogg/.aac), atau video (.mp4/.mov/.avi/.mkv/.webm), yang soundtrack-nya juga menjadi referensi audio. Klip pelatihan mendukung .mp4, .mov, .avi, dan .mkv; targetkan setidaknya 10 klip, dengan jumlah lebih banyak lebih baik. |
| `rank` |  | enum (integer) | no | `32` | `8`, `16`, `32`, `64`, `128` | Rank adaptasi LoRA, yang menukar peningkatan konsumsi memori dengan kapasitas yang lebih besar seiring naiknya pengaturan. |
| `number_of_steps` |  | integer | no | `2000` | 1 – 15,000 | Jumlah total langkah pelatihan. |
| `learning_rate` |  | number | no | `0.0002` | 0.000001 – 1 | Laju pembelajaran pengoptimalan, menyeimbangkan kemungkinan percepatan pelatihan dengan risiko overfitting saat dinaikkan. |
| `number_of_frames` |  | integer | no | `73` | 22 – 124 | Jumlah bingkai untuk setiap sampel pelatihan; pembagian dengan 17 harus menyisakan sisa 5. Contohnya 22, 39, 56, 73, 90, 107, dan 124. |
| `frame_rate` |  | integer | no | `24` | 8 – 60 | Laju bingkai video target, diukur dalam bingkai per detik. |
| `resolution` |  | enum (string) | no | `medium` | `low`, `medium`, `high` | Resolusi pelatihan. Meningkatkan resolusi akan meningkatkan kebutuhan memori. |
| `aspect_ratio` |  | enum (string) | no | `16:9` | `21:9`, `16:9`, `4:3`, `1:1`, `3:4`, `9:16` | Pilih rasio aspek pelatihan dari set yang sama seperti yang tersedia melalui MiniMax H3 API. |
| `trigger_phrase` |  | string | no | `` |  | Frasa aktivasi gaya LoRA, disisipkan di awal caption selama pelatihan. |
| `reference_conditioning_p` |  | number | no | `0.9` | 0 – 1 | Atur seberapa sering pelatihan menggunakan conditioning gambar referensi dibandingkan pelatihan text-to-video-audio tanpa conditioning. Probabilitas yang tersisa digunakan untuk objektif tanpa conditioning guna mempertahankan pembuatan yang stabil hanya dari prompt. |
| `resume_from_lora_url` |  | string \| null | no |  |  | URL untuk pelatihan warm-start dengan LoRA .safetensors yang sebelumnya dibuat oleh trainer ini, diikuti jumlah langkah pelatihan tambahan number_of_steps. Tidak ada yang dipulihkan selain bobot adaptor: optimisasi dan penjadwalan laju pembelajaran dimulai kembali dari awal. |
| `auto_scale_input` |  | boolean | no | `false` |  | Apakah fps target dan jumlah bingkai disesuaikan melalui penskalaan video otomatis; true mengaktifkan penyesuaian ini. |
| `split_input_into_scenes` |  | boolean | no | `true` |  | Aktifkan pemisahan adegan untuk video yang lebih panjang dari ambang durasi, dengan membuang sidecar referensi dari klip yang dipisahkan. |
| `split_input_duration_threshold` |  | number | no | `30` | 1 – 60 | Pemicu pemisahan adegan yang dinyatakan sebagai durasi dalam detik: hanya video yang lebih panjang dari ambang batas yang dipisahkan. |
| `debug_dataset` |  | boolean | no | `false` |  | Opsi untuk mengunduh arsip guna memeriksa prapemrosesan sebelum melanjutkan ke pelatihan penuh. Jika diaktifkan, trainer mengemas dataset yang telah diproses agar Anda dapat memeriksa keterangan, gambar referensi, video, dan gambar secara manual. |
| `strict_dataset` |  | boolean | no | `false` |  | Penanganan ketat atas masalah prapemrosesan yang biasanya dicatat dan diselesaikan menggunakan fallback yang didokumentasikan. Mengaktifkannya akan menolak keterangan yang memerlukan prompt kosong, sidecar referensi yang hilang, dan video dengan audio yang tidak dapat dibaca, alih-alih mengizinkan fallback 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.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} | URL bobot LoRA terlatih dalam format .safetensors. |
| `config_file` | object {url, content_type, file_name, file_size} | Konfigurasi untuk penyiapan endpoint inferensi. |
| `debug_dataset` | object {url, content_type, file_name, file_size} \| null | Hanya tersedia untuk permintaan dengan `debug_dataset` yang diaktifkan, arsip yang dapat diunduh ini berisi data pelatihan setelah prapemrosesan. |

## 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