# MiniMax H3 Reference to Video LoRA Trainer API

> LoRA-Trainer fir referenzgesteiert Videoe mat engem Warmstart vun enger fréierer LoRA

Trainéiert eng LoRA op engem ZIP mat Sujet-Videoclips, sou datt Referenzinputs d'Videogeneratioun steiere kënnen. `reference_conditioning_p` setzt fest, wéi dacks Referenze beim Training benotzt ginn, an `resume_from_lora_url` féiert vun enger virdru trainéierter LoRA weider. Och konfiguréierbar: `rank`, `number_of_steps`, `number_of_frames`, `frame_rate` an `aspect_ratio`. Gëtt Gewiichter an eng Konfiguratiounsdatei zréck.

- 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/lb/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 fir e ZIP mat Trainingsvideoe vu Motiver; Bild-nëmmen-Datasets a gemëschte Bild/Video-Trainingsarchiver ginn ofgeleent, dofir mussen d'Biller als Referenz-Sidecars geliwwert ginn. Optional Extras deelen de Basisnumm vum Clip: eng Caption wéi `clip01.txt` an zortéiert Referenzen vun `ref_1` bis `ref_4`, benannt `clip01.ref_1.<ext>` bis `clip01.ref_4.<ext>`; ouni Referenz-Sidecars liwwert e Frame aus dem Clip seng eege Referenz. `<ext>` bestëmmt d'Referenzmodalitéit: Biller (.png/.jpg/.jpeg), Audio (.wav/.mp3/.flac/.m4a/.ogg/.aac) oder Videoen (.mp4/.mov/.avi/.mkv/.webm), deenen hir Soundtracks och zu Audio-Referenze ginn. Trainingsclips ënnerstëtzen .mp4, .mov, .avi an .mkv; mindestens 10 Clips si recommandéiert, méi sinn erwënscht. |
| `rank` |  | enum (integer) | no | `32` | `8`, `16`, `32`, `64`, `128` | LoRA-Adaptatiounsrang, bei deem méi héije Wäerter méi Kapazitéit géint méi héije Memoryverbrauch ofwiichten. |
| `number_of_steps` |  | integer | no | `2000` | 1 – 15,000 | Gesamtzuel vun Trainingsschrëtt. |
| `learning_rate` |  | number | no | `0.0002` | 0.000001 – 1 | Léierquote fir d'Optimiséierung, déi e méigleche Geschwindegkeetsgewënn beim Training géint de Risiko vun Overfitting bei méi héije Wäerter ofwiicht. |
| `number_of_frames` |  | integer | no | `73` | 22 – 124 | Framezuel fir all Trainingssample; d'Deele duerch 17 muss e Rescht vu 5 erginn. Beispiller sinn 22, 39, 56, 73, 90, 107 an 124. |
| `frame_rate` |  | integer | no | `24` | 8 – 60 | Zil-Video-Frame-Rate, gemooss a Frames pro Sekonn. |
| `resolution` |  | enum (string) | no | `medium` | `low`, `medium`, `high` | Trainingsopléisung. Eng Erhéijung vun der Opléisung erhéicht d'Memoryufuerderungen. |
| `aspect_ratio` |  | enum (string) | no | `16:9` | `21:9`, `16:9`, `4:3`, `1:1`, `3:4`, `9:16` | Wielt d'Trainings-Aspektverhältnis aus dem selwechte Set, deen iwwer d'MiniMax H3 API disponibel ass. |
| `trigger_phrase` |  | string | no | `` |  | LoRA-Stil-Aktivéierungsphrase, déi beim Training um Ufank vun de Captions agefouert gëtt. |
| `reference_conditioning_p` |  | number | no | `0.9` | 0 – 1 | Setzt fest, wéi dacks d'Training Referenzbild-Conditioning géintiwwer onconditionéiertem Text-zu-Video-Audio-Training benotzt. Déi iwwereg Wahrscheinlechkeet geet un dat onconditionéiert Zil, fir stabil Prompt-nëmmen-Generatioun ze behalen. |
| `resume_from_lora_url` |  | string \| null | no |  |  | URL fir Warm-Start-Training mat enger .safetensors-LoRA, déi virdrun vun dësem Trainer erstallt gouf, gefollegt vun der Zuel vun zousätzleche number_of_steps-Trainingsschrëtt. Näischt ausser den Adapter-Gewiichter gëtt restauréiert: Optimisatioun a Learning-Rate-Planung fänken allebéid nei un. |
| `auto_scale_input` |  | boolean | no | `false` |  | Ob d'Zil-fps an d'Framezuel duerch automatesch Videoskaléierung ugepasst ginn; true aktivéiert dës Upassung. |
| `split_input_into_scenes` |  | boolean | no | `true` |  | Szenenopdeelung fir Videoe méi laang wéi e Dauergrenzwäert aktivéieren; Referenz-Sidecars ginn aus all opgedeelte Clips verworf. |
| `split_input_duration_threshold` |  | number | no | `30` | 1 – 60 | Trigger fir d'Szenendeelung als Dauer a Sekonnen: nëmme Videoe méi laang wéi de Schwellwäert ginn gedeelt. |
| `debug_dataset` |  | boolean | no | `false` |  | Optioun fir en Archiv erofzelueden, fir d'Virveraarbechtung virum komplette Training ze kontrolléieren. Wann aktivéiert, packt den Trainer den veraarbechten Dataset, fir datt Dir Captions, Referenzbiller, Videoen a Biller manuell op Korrektheet iwwerpréiwe kënnt. |
| `strict_dataset` |  | boolean | no | `false` |  | Streng Behandlung vu Virveraarbechtungsproblemer, déi soss protokolléiert a mam dokumentéierte Fallback geléist géife ginn. Wann aktivéiert, ginn Captions, déi e eidele Prompt brauchen, fehlend Referenz-Sidecars a Videoe mat onliesbarem Audio ofgeleent amplaz dës Fallbacks z'erlaben. |

## 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 fir trainéiert LoRA-Gewiichter am .safetensors-Format. |
| `config_file` | object {url, content_type, file_name, file_size} | Konfiguratioun fir d'Ariichtung vum Inferenz-Endpunkts. |
| `debug_dataset` | object {url, content_type, file_name, file_size} \| null | Nëmme fir Ufroe mat aktivéiertem `debug_dataset` disponibel; dësen erofluedbaren Archiv enthält d'Trainingsdaten no der Virveraarbechtung. |

## 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