# MiniMax H3 Reference to Video LoRA Trainer API

> LoRA-træner til referencebetinget video med varm start fra en tidligere LoRA

Træner en LoRA på en zip-fil med videoklip af motiver, så referenceinput kan styre videogenereringen. `reference_conditioning_p` angiver, hvor ofte referencer bruges under træningen, og `resume_from_lora_url` fortsætter fra en tidligere trænet LoRA. Kan også konfigureres: `rank`, `number_of_steps`, `number_of_frames`, `frame_rate` og `aspect_ratio`. Returnerer vægte og en konfigurationsfil.

- 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/da/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 til en ZIP med motivtræningsvideoer; datasæt kun med billeder og blandede billed/video-træningsarkiver afvises, så billeder skal i stedet være reference-sidecars. Valgfrit ekstraindhold deler hvert klips basisnavn: en billedtekst som `clip01.txt` og ordnede referencer fra `ref_1` til `ref_4`, navngivet `clip01.ref_1.<ext>` til `clip01.ref_4.<ext>`; uden reference-sidecars leverer en frame fra klippet dets egen reference. `<ext>` bestemmer referencens modalitet: billeder (.png/.jpg/.jpeg), lyd (.wav/.mp3/.flac/.m4a/.ogg/.aac) eller videoer (.mp4/.mov/.avi/.mkv/.webm), hvis lydspor også bliver lydreferencer. Træningsklip understøtter .mp4, .mov, .avi og .mkv; sigt efter mindst 10 klip, gerne flere. |
| `rank` |  | enum (integer) | no | `32` | `8`, `16`, `32`, `64`, `128` | LoRA-tilpasningsrang, der bytter øget hukommelsesforbrug for større kapacitet, når indstillingen øges. |
| `number_of_steps` |  | integer | no | `2000` | 1 – 15,000 | Samlet antal træningstrin. |
| `learning_rate` |  | number | no | `0.0002` | 0.000001 – 1 | Optimeringens læringsrate, der afvejer en mulig hastighedsforøgelse i træningen mod risikoen for overtilpasning, når den øges. |
| `number_of_frames` |  | integer | no | `73` | 22 – 124 | Frameantal for hver træningsprøve; division med 17 skal give resten 5. Eksempler er 22, 39, 56, 73, 90, 107 og 124. |
| `frame_rate` |  | integer | no | `24` | 8 – 60 | Målvideoframefrekvens målt i frames per sekund. |
| `resolution` |  | enum (string) | no | `medium` | `low`, `medium`, `high` | Træningsopløsning. En højere opløsning øger hukommelseskravene. |
| `aspect_ratio` |  | enum (string) | no | `16:9` | `21:9`, `16:9`, `4:3`, `1:1`, `3:4`, `9:16` | Vælg træningens formatforhold fra det samme sæt, der er tilgængeligt via MiniMax H3 API. |
| `trigger_phrase` |  | string | no | `` |  | Aktiveringsudtryk for LoRA-stilen, indsat i begyndelsen af beskrivelserne under træning. |
| `reference_conditioning_p` |  | number | no | `0.9` | 0 – 1 | Angiv, hvor ofte træningen bruger conditioning med referencebilleder frem for ubetinget tekst-til-video-lyd-træning. Den resterende sandsynlighed går til det ubetingede mål for at opretholde stabil promptbaseret generering. |
| `resume_from_lora_url` |  | string \| null | no |  |  | URL til warm-start-træning med en .safetensors-LoRA, der tidligere er oprettet af denne træner, efterfulgt af antallet af yderligere træningstrin i number_of_steps. Intet ud over adaptervægtene gendannes: både optimering og læringsratestyring begynder på ny. |
| `auto_scale_input` |  | boolean | no | `false` |  | Om mål-fps og frameantal matches gennem automatisk videoskalering; true aktiverer denne justering. |
| `split_input_into_scenes` |  | boolean | no | `true` |  | Aktivér scenedeling for videoer, der er længere end en varighedstærskel, og kassér reference-sidecars fra alle klip, der deles. |
| `split_input_duration_threshold` |  | number | no | `30` | 1 – 60 | Trigger for scenedeling angivet som en varighed i sekunder: kun videoer, der er længere end tærsklen, opdeles. |
| `debug_dataset` |  | boolean | no | `false` |  | Mulighed for at downloade et arkiv til kontrol af preprocessing før fuld træning startes. Når dette er aktiveret, pakker træneren det behandlede datasæt, så du manuelt kan kontrollere billedtekster, referencebilleder, videoer og billeder. |
| `strict_dataset` |  | boolean | no | `false` |  | Streng håndtering af preprocessing-problemer, som ellers ville blive logget og løst ved hjælp af den dokumenterede fallback. Når den aktiveres, afvises billedtekster, der kræver tomme prompts, manglende reference-sidecars og videoer med ulæselig lyd i stedet for at tillade disse fallbacks. |

## 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 til trænede LoRA-vægte i .safetensors-format. |
| `config_file` | object {url, content_type, file_name, file_size} | Konfiguration til opsætning af inferens-endpointet. |
| `debug_dataset` | object {url, content_type, file_name, file_size} \| null | Kun tilgængelig for anmodninger med `debug_dataset` aktiveret; dette downloadbare arkiv indeholder træningsdataene efter 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