# MiniMax H3 Reference to Video LoRA Trainer API

> LoRA trainer vaś referencença-conditioned video, le warm start andar angluno LoRA

Sikavel jekh LoRA pe zip subjektoske video-kliponça, te referencikane inputura šaj keren drom e video-generaciǎke. `reference_conditioning_p` phenel sar butvar si referencura përdžime ande trening, thaj `resume_from_lora_url` pokračuil andar angluno trenirime LoRA. Aver šaj regulirime: `rank`, `number_of_steps`, `number_of_frames`, `frame_rate` thaj `aspect_ratio`. Del weightura thaj config fajlo.

- 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/rom/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 adresa vaš jekh ZIP le subjekteske sikavipeske videonca; le datenge khetanipena numaj kipenca thaj mišime kipo/video sikavipeske arhivura čhuden pes avri, vaśoda le kipa trubul te aven paše phandle referentne fajlura. Le naobligatorne dodatki len sakole kliposko bazno anav: jekh teksto sar `clip01.txt` thaj rendime reference katar `ref_1` dži ko `ref_4`, anavenca `clip01.ref_1.<ext>` dži ko `clip01.ref_4.<ext>`; bi paše phandle referentne fajlonengo, jekh kadro andar o klipo del leski korkorutni referenca. O `<ext>` alosarel le referencako tipo: kipa (.png/.jpg/.jpeg), audio (.wav/.mp3/.flac/.m4a/.ogg/.aac), vaj video (.mp4/.mov/.avi/.mkv/.webm), savenge zvukoske trake vi aven audio reference. Le sikavipeske klipura phiraven .mp4, .mov, .avi thaj .mkv; de najcerra 10 klipura, maj but si maj lačhe. |
| `rank` |  | enum (integer) | no | `32` | `8`, `16`, `32`, `64`, `128` | LoRA adaptation rank, savo lel maj-baro memory thaj del maj-bari capacity kana vazdel pes. |
| `number_of_steps` |  | integer | no | `2000` | 1 – 15,000 | Sa e training steps-enge gind. |
| `learning_rate` |  | number | no | `0.0002` | 0.000001 – 1 | Optimization learning rate, balancirinel jek possible speedup ande traininga riskoha overfittingesko kana bararel. |
| `number_of_frames` |  | integer | no | `73` | 22 – 124 | Kadro-count vaš sako training sample; kana delpe ko 17, trubul te avel remainder 5. Examples si 22, 39, 56, 73, 90, 107, taj 124. |
| `frame_rate` |  | integer | no | `24` | 8 – 60 | Ciljno frekvencija e videokadrenge, merime ande kadra pe sekunda. |
| `resolution` |  | enum (string) | no | `medium` | `low`, `medium`, `high` | Training rezolucija. Maj-bari rezolucija mangel maj-baro memory. |
| `aspect_ratio` |  | enum (string) | no | `16:9` | `21:9`, `16:9`, `4:3`, `1:1`, `3:4`, `9:16` | Avrirod e trainingosko aspect ratio katar sajekh set savo si dostupno ande MiniMax H3 API. |
| `trigger_phrase` |  | string | no | `` |  | LoRA stiloski activation fraza, thovi pes andro captionsko starto andro training. |
| `reference_conditioning_p` |  | number | no | `0.9` | 0 – 1 | Sikav keci var training lel reference-image conditioning karing unconditioned text-to-video-audio training. Sako probability savo ačhel džal ko unconditioned objective vaš stable prompt-only keripe. |
| `resume_from_lora_url` |  | string \| null | no |  |  | URL vaš warm-start training jekh .safetensors LoRA-sa savo anglal kerdo kava traineresa, palal number_of_steps additional training steps. Nane restorime khanchi avri e adapter weights: optimization taj learning-rate scheduling startin nevo. |
| `auto_scale_input` |  | boolean | no | `false` |  | Te si target fps taj kadro-count matchime automatic video scalingesa; true aktivinel kava adjustment. |
| `split_input_into_scenes` |  | boolean | no | `true` |  | Aktivisar scene splitting vaš videos save si maj lunge sar duration threshold, chudel avri reference sidecars katar sako splitime klipa. |
| `split_input_duration_threshold` |  | number | no | `30` | 1 – 60 | Scene-splitting trigger, sikavdo durata andro sekunda: numa videona maj-bare sar threshold si split-ime. |
| `debug_dataset` |  | boolean | no | `false` |  | Opcija te download-el archive vaš preprocessing checking angle full trainingosko. Te aktivime, o trainer paketin-el o processime dataset kaj šaj manušes te kontrolis captions, reference kipi, videos taj kipi. |
| `strict_dataset` |  | boolean | no | `false` |  | Strogo arakhipen le problemengo anglal o proceso, save averčhane sas te registrisaren pes thaj te lačharen pes pe dokumentirime rezervne metodasa. Kana si aktivirimo, čhudel avri le tekstura save mangen čuče promptura, le video saven naj paše phandle referentne fajlura, thaj le video savengo audio našti te drabarel pes, umal te mukhel kadala rezervne metode. |

## 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 trained LoRA weights-enge andro .safetensors formato. |
| `config_file` | object {url, content_type, file_name, file_size} | Konfiguracija vašo inference endpoint setup. |
| `debug_dataset` | object {url, content_type, file_name, file_size} \| null | Dostupno numa bašo mangipena `debug_dataset` aktivime, kava downloadable archive lel e training data palal preprocessing. |

## 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