# MiniMax H3 Reference to Video LoRA Trainer API

> LoRA-þjálfari fyrir viðmiðunarskilyrt myndband, með hlýræsingu frá fyrri LoRA

Þjálfar LoRA á zip-skrá með myndbandsbútum af myndefni svo viðmiðunarinntak geti stýrt myndbandsgerð. `reference_conditioning_p` stillir hversu oft viðmiðanir eru notaðar í þjálfun og `resume_from_lora_url` heldur áfram frá áður þjálfaðri LoRA. Einnig stillanlegt: `rank`, `number_of_steps`, `number_of_frames`, `frame_rate` og `aspect_ratio`. Skilar vogum og stillingaskrá.

- 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/is/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 |  |  | Slóð að ZIP-skrá með þjálfunarmyndböndum af myndefni; gagnasöfnum eingöngu með myndum og blönduðum mynda-/myndbands-þjálfunarsöfnum er hafnað, þannig að myndir verða að vera hliðargögn fyrir tilvísanir. Valfrjáls aukagögn bera sama grunnnafn og hver bútur: textalýsing eins og `clip01.txt` og raðaðar tilvísanir frá `ref_1` til `ref_4`, nefndar `clip01.ref_1.<ext>` til `clip01.ref_4.<ext>`; án tilvísunarhliðargagna gefur rammi úr bútinum eigin tilvísun. `<ext>` ákvarðar miðlunargerð tilvísunar: myndir (.png/.jpg/.jpeg), hljóð (.wav/.mp3/.flac/.m4a/.ogg/.aac) eða myndbönd (.mp4/.mov/.avi/.mkv/.webm), en hljóðrásir þeirra verða einnig hljóðtilvísanir. Þjálfunarbútar styðja .mp4, .mov, .avi og .mkv; stefndu að að minnsta kosti 10 bú\|\|\|\|tum og fleiri eru æskileg. |
| `rank` |  | enum (integer) | no | `32` | `8`, `16`, `32`, `64`, `128` | Aðlögunarstig LoRA, þar sem aukin minnisnotkun fæst gegn meiri getu eftir því sem stillingin hækkar. |
| `number_of_steps` |  | integer | no | `2000` | 1 – 15,000 | Heildarfjöldi þjálfunarskrefa. |
| `learning_rate` |  | number | no | `0.0002` | 0.000001 – 1 | Námshraði bestunar, sem vegur mögulegan hraðaauka í þjálfun á móti hættu á ofþjálfun þegar hann er hækkaður. |
| `number_of_frames` |  | integer | no | `73` | 22 – 124 | Rammafjöldi fyrir hvert þjálfunarsýni; deiling með 17 verður að gefa afganginn 5. Dæmi eru 22, 39, 56, 73, 90, 107 og 124. |
| `frame_rate` |  | integer | no | `24` | 8 – 60 | Markrammatíðni myndbands, mæld í römmum á sekúndu. |
| `resolution` |  | enum (string) | no | `medium` | `low`, `medium`, `high` | Þjálfunarupplausn. Hærri upplausn eykur minnisþörf. |
| `aspect_ratio` |  | enum (string) | no | `16:9` | `21:9`, `16:9`, `4:3`, `1:1`, `3:4`, `9:16` | Veldu stærðarhlutfall þjálfunar úr sama mengi og er tiltækt í MiniMax H3 API. |
| `trigger_phrase` |  | string | no | `` |  | LoRA-stílvirkjunarsetning, sett fremst í texta við þjálfun. |
| `reference_conditioning_p` |  | number | no | `0.9` | 0 – 1 | Stilltu hversu oft þjálfun notar skilyrðingu með tilvísunarmynd samanborið við óskilyrta texta-í-myndband-hljóð-þjálfun. Líkur sem eftir standa fara í óskilyrta markmiðið til að viðhalda stöðugri efnisgerð eingöngu úr kvaðningu. |
| `resume_from_lora_url` |  | string \| null | no |  |  | Slóð fyrir warm-start-þjálfun með .safetensors LoRA sem þessi þjálfari bjó áður til, ásamt fjölda additional training steps í number_of_steps. Ekkert nema millistykkisþyngdir eru endurheimtar: bæði bestun og námsstigaskipulag byrja upp á nýtt. |
| `auto_scale_input` |  | boolean | no | `false` |  | Hvort mark-fps og rammafjöldi séu samræmd með sjálfvirkri myndbandsstærðun; true virkjar þessa aðlögun. |
| `split_input_into_scenes` |  | boolean | no | `true` |  | Virkjaðu senuskiptingu fyrir myndbönd sem eru lengri en lengdarmörk og fargaðu tilvísunarhliðargögnum úr öllum bú\|\|\|\|tum sem eru skiptir. |
| `split_input_duration_threshold` |  | number | no | `30` | 1 – 60 | Kveikja senuskiptingar gefin upp sem lengd í sekúndum: aðeins myndböndum sem eru lengri en þröskuldurinn er skipt. |
| `debug_dataset` |  | boolean | no | `false` |  | Valkostur til að sækja safn til að yfirfara forvinnslu áður en full þjálfun er hafin. Þegar þetta er virkt pakkar þjálfarinn unnu gagnasafni svo hægt sé að skoða textalýsingar, tilvísunarmyndir, myndbönd og myndir handvirkt. |
| `strict_dataset` |  | boolean | no | `false` |  | Ströng meðhöndlun forvinnsluvandamála sem annars væru skráð og leyst með skjalfestri varaleið. Þegar þetta er virkt er hafnað textalýsingum sem þurfa tómar kvaðningar, vantar tilvísunarhliðargögn eða innihalda myndbönd með ólæsilegu hljóði í stað þess að leyfa þessar varaleiðir. |

## 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 á þjálfaðar LoRA-vigtir á .safetensors-sniði. |
| `config_file` | object {url, content_type, file_name, file_size} | Uppsetning fyrir uppsetningu ályktunarendapunkts. |
| `debug_dataset` | object {url, content_type, file_name, file_size} \| null | Aðeins tiltækt fyrir beiðnir með `debug_dataset` virkt; þetta niðurhalanlega safn inniheldur þjálfunargögnin eftir forvinnslu. |

## 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