# LTX-2.3 22B Video to Video Trainer API

> Melatih LoRA LTX-2.3 22B untuk transformasi video atau penjanaan terkondisi video daripada video rujukan

Melatih LoRA pada model LTX-2.3 22B untuk transformasi video, menggunakan zip video atau imej (mp4, mov, avi, mkv, png, jpg, jpeg) dengan sekurang-kurangnya kira-kira 10 fail disyorkan. `number_of_steps` berjulat daripada 1 hingga 20000 (lalai 2000), dan `frame_rate` lalai ialah 25. `first_frame_conditioning_p` lalai ialah 0.1. Pengesahan menerima sehingga 2 prompt dengan video rujukan.

- Model id: `ltx23-v2v-trainer`
- Made by: Lightricks
- Category: Training
- Output: file
- Price: $0.0135 / step (cheapest run $27.00 (27000 API credits))
- Run: `POST https://api.doitong.com/v1/run/ltx23-v2v-trainer`
- Quote: `POST https://api.doitong.com/v1/quote/ltx23-v2v-trainer`
- Docs page: https://doitong.com/ms/developers/models/ltx23-v2v-trainer

## Pricing

Price: **$0.0135 / step**. Billed per training step (`number_of_steps`).

The full example input below costs $27.00 = 27000 API credits (2000 steps × 13.5 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/ltx23-v2v-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 arkib ZIP untuk set data yang mengandungi imej sahaja atau video sahaja; set data media campuran tidak disokong. Sasarkan 10 fail atau lebih, sebaiknya koleksi yang lebih besar. Sambungan yang diterima ialah .png, .jpg, .jpeg untuk imej dan .mp4, .mov, .avi, .mkv untuk video. Fail teks kapsyen pilihan boleh disertakan bersama media, dengan setiap fail kapsyen dinamakan sepadan dengan fail media berkaitannya. |
| `rank` |  | enum (integer) | no | `32` | `8`, `16`, `32`, `64`, `128` | Rank penyesuaian LoRA, menukar penggunaan memori yang meningkat dengan kapasiti yang lebih besar apabila tetapan dinaikkan. |
| `number_of_steps` |  | integer | no | `2000` | 1 – 20,000 | Jumlah langkah latihan. |
| `learning_rate` |  | number | no | `0.0002` | 0.000001 – 1 | Kadar pembelajaran pengoptimuman, mengimbangi kemungkinan peningkatan kelajuan latihan dengan risiko terlebih suai apabila dinaikkan. |
| `number_of_frames` |  | integer | no | `89` | 9 – 121 | Kiraan bingkai bagi setiap sampel latihan. Membahagikan kiraan dengan 8 mesti meninggalkan baki 1; contohnya 1, 9, 17, 25, 33, 41, 49, 57, 65, 73, 81, 89, 97. |
| `frame_rate` |  | integer | no | `25` | 8 – 60 | Kadar bingkai video sasaran, diukur dalam bingkai sesaat. |
| `resolution` |  | enum (string) | no | `medium` | `low`, `medium`, `high` | Resolusi latihan. Meningkatkan resolusi meningkatkan keperluan memori. |
| `aspect_ratio` |  | enum (string) | no | `1:1` | `16:9`, `1:1`, `9:16` | Nisbah aspek latihan. |
| `trigger_phrase` |  | string | no | `` |  | Frasa pengaktifan gaya LoRA, disisipkan pada permulaan kapsyen semasa latihan. |
| `auto_scale_input` |  | boolean | no | `false` |  | Pelarasan video automatik agar sepadan dengan FPS dan kiraan bingkai yang diminta apabila didayakan; set data imej kekal tidak berubah. |
| `split_input_into_scenes` |  | boolean | no | `true` |  | Pemisahan adegan untuk video yang melebihi ambang tempoh, didayakan apabila true. |
| `split_input_duration_threshold` |  | number | no | `30` | 1 – 60 | Pencetus pemisahan adegan yang dinyatakan sebagai tempoh dalam saat: hanya video yang lebih panjang daripada ambang akan dipisahkan. |
| `debug_dataset` |  | boolean | no | `false` |  | Mod pemeriksaan prapemprosesan untuk menyemak video, imej dan kapsyen sebelum larian latihan penuh. Mendayakannya menyebabkan pelatih mengembalikan set data latihan yang diproses dalam arkib boleh dimuat turun untuk semakan manual. |
| `first_frame_conditioning_p` |  | number | no | `0.1` | 0 – 1 | Utamakan transformasi video-to-video dengan mengurangkan kekerapan latihan menggunakan pengkondisian bingkai pertama; nilai ini menetapkan kebarangkalian tersebut. |
| `validation` |  | array of object {prompt, reference_video_url} | no | `[]` | ≤ 2 items | Senarai input pengesahan yang mengandungi prompt yang digandingkan dengan video rujukan. |
| `validation[].prompt` |  | string | yes |  |  | Prompt yang digunakan semasa pengesahan. |
| `validation[].reference_video_url` |  | string (video URL) | yes |  | ≥ 1 characters | Bekalkan video untuk ditransformasikan semasa pengesahan IC-LoRA melalui URLnya. |
| `validation_negative_prompt` |  | string | no | `worst quality, inconsistent motion, blurry, jittery, distorted` |  | Prompt negatif yang digunakan semasa pengesahan. |
| `validation_number_of_frames` |  | integer | no | `89` | 9 – 121 | Kiraan bingkai bagi setiap video pengesahan. |
| `validation_frame_rate` |  | integer | no | `25` | 8 – 60 | Kadar bingkai video pengesahan sasaran, diukur dalam bingkai sesaat. |
| `validation_resolution` |  | enum (string) | no | `high` | `low`, `medium`, `high` | Resolusi yang digunakan semasa pengesahan. |
| `validation_aspect_ratio` |  | enum (string) | no | `1:1` | `16:9`, `1:1`, `9:16` | Nisbah aspek yang digunakan semasa pengesahan. |
| `stg_scale` |  | number | no | `1` | 0 – 3 | Skala Panduan Ruang-Masa (STG), dengan 1.0 disyorkan dan 0.0 mematikan STG. |

## 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/ltx23-v2v-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/ltx23-v2v-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/ltx23-v2v-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": "ltx23-v2v-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": "ltx23-v2v-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": 27000,
    "usd": "27.00",
    "charged": 27000,
    "refunded": 0
  },
  "input": {
    "training_data_url": "https://example.com/your-file.zip"
  },
  "output": {
    "video": {
      "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
    },
    "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 |
|---|---|---|
| `video` | object {url, content_type, file_name, file_size} \| null | URL untuk mana-mana video pengesahan yang tersedia, dipaparkan bersama video rujukannya. |
| `lora_file` | object {url, content_type, file_name, file_size} | URL fail berat IC-LoRA terlatih dalam format .safetensors. |
| `config_file` | object {url, content_type, file_name, file_size} | Konfigurasi untuk persediaan endpoint inferens. |
| `debug_dataset` | object {url, content_type, file_name, file_size} \| null | Arkib nyahpepijat yang boleh dimuat turun, hanya tersedia untuk input yang mendayakan `debug_dataset`; kandungan data latihannya telah dipraproses dan termasuk video dalam bentuk dinyahkod. |

## Related models

- [LTX 2.3 Trainer (V2) - Audio Inpainting](https://doitong.com/developers/models/ltx23-trainer-v2/audio-inpaint.md) (`ltx23-trainer-v2/audio-inpaint`): $0.0023 / step
- [LTX 2.3 Trainer (V2) - Audio+Video Reference IC-LoRA](https://doitong.com/developers/models/ltx23-trainer-v2/ic-lora/av2av.md) (`ltx23-trainer-v2/ic-lora/av2av`): $0.0068 / step
- [LTX 2.3 Trainer (V2) - Audio+Video Reference Transformation](https://doitong.com/developers/models/ltx23-trainer-v2/av2av.md) (`ltx23-trainer-v2/av2av`): $0.0068 / step
- [LTX 2.3 Trainer (V2) - Audio-to-Audio](https://doitong.com/developers/models/ltx23-trainer-v2/a2a.md) (`ltx23-trainer-v2/a2a`): $0.0023 / step
- [LTX 2.3 Trainer (V2) - Audio-to-Audio IC-LoRA](https://doitong.com/developers/models/ltx23-trainer-v2/ic-lora/a2a.md) (`ltx23-trainer-v2/ic-lora/a2a`): $0.0023 / step
- [LTX 2.3 Trainer (V2) - Audio-to-Video](https://doitong.com/developers/models/ltx23-trainer-v2/a2v.md) (`ltx23-trainer-v2/a2v`): $0.006 / step
- [LTX 2.3 Trainer (V2) - Backward Audio Extension](https://doitong.com/developers/models/ltx23-trainer-v2/audio-extend-suffix.md) (`ltx23-trainer-v2/audio-extend-suffix`): $0.0023 / step
- [LTX 2.3 Trainer (V2) - Backward Video Extension](https://doitong.com/developers/models/ltx23-trainer-v2/extend-suffix.md) (`ltx23-trainer-v2/extend-suffix`): $0.0061 / step

## Links

- HTML page: https://doitong.com/developers/models/ltx23-v2v-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=ltx23-v2v-trainer
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.com/v1/models/ltx23-v2v-trainer