# LTX 2.3 Trainer (V2) - Forward Video Extension API

> Melatih LoRA LTX 2.3 untuk ekstensi video ke depan: berikan klip pembuka dan model melanjutkan kejadian berikutnya

Melatih LoRA dari `.zip` berisi klip pelatihan (`training_data_url`) agar model dapat melanjutkan video setelah segmen pembuka yang diberikan. Tetapkan `conditioning_frames` untuk panjang prefiks, dan aktifkan `with_audio` untuk memperpanjang suara bersama video. Rank (8 hingga 128), langkah (100 hingga 10000), jumlah bingkai (9 hingga 121), resolusi, dan rasio aspek (16:9, 1:1, 9:16) dapat disesuaikan. Hingga dua klip validasi dapat dipratinjau, dan hasilnya mencakup file bobot LoRA.

- Model id: `ltx23-trainer-v2/extend-prefix`
- Made by: Lightricks
- Category: Training
- Output: file
- Price: $0.0062 / step (cheapest run $12.40 (12400 API credits))
- Run: `POST https://api.doitong.com/v1/run/ltx23-trainer-v2/extend-prefix`
- Quote: `POST https://api.doitong.com/v1/quote/ltx23-trainer-v2/extend-prefix`
- Docs page: https://doitong.com/id/developers/models/ltx23-trainer-v2/extend-prefix

## Pricing

Price: **$0.0062 / step**. Billed per training step (`number_of_steps`).

The full example input below costs $12.40 = 12400 API credits (2000 steps × 6.2 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-trainer-v2/extend-prefix` 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 `.zip` yang berisi data pelatihan, diatur sesuai mode pelatihan yang dipilih. Setiap file media dapat memiliki caption `.txt` dengan nama dasar yang sama. |
| `rank` |  | enum (integer) | no | `32` | `8`, `16`, `32`, `64`, `128` | Rank adaptasi LoRA, yang menukar peningkatan konsumsi memori dengan kapasitas yang lebih besar seiring naiknya pengaturan. |
| `number_of_steps` |  | integer | no | `2000` | 100 – 10,000 | Jumlah total langkah pelatihan. |
| `learning_rate` |  | number | no | `0.0002` | 0.000001 – 1 | Laju pembelajaran optimisasi. |
| `number_of_frames` |  | integer | no | `89` | 9 – 121 | Jumlah bingkai untuk setiap sampel pelatihan. Membagi jumlah tersebut dengan 8 harus menyisakan sisa 1; contohnya 1, 9, 17, 25, 33, 41, 49, 57, 65, 73, 81, 89, 97. |
| `frame_rate` |  | integer | no | `24` | 8 – 60 | Laju bingkai target video pelatihan dalam bingkai per detik. Laju native untuk LTX-2.3 adalah 24. |
| `resolution` |  | enum (string) | no | `medium` | `low`, `medium`, `high` | Resolusi pelatihan. Meningkatkan resolusi akan meningkatkan kebutuhan memori. |
| `aspect_ratio` |  | enum (string) | no | `1:1` | `16:9`, `1:1`, `9:16` | Rasio aspek pelatihan. |
| `trigger_phrase` |  | string | no | `` |  | Frasa aktivasi gaya LoRA, disisipkan di awal caption selama pelatihan. |
| `auto_scale_input` |  | boolean | no | `false` |  | Penyesuaian video otomatis agar sesuai dengan FPS dan jumlah bingkai yang diminta saat diaktifkan; dataset gambar tidak berubah. |
| `split_input_into_scenes` |  | boolean | no | `true` |  | Pemisahan adegan untuk video yang melebihi ambang durasi, diaktifkan saat true. |
| `split_input_duration_threshold` |  | number | no | `30` | 1 – 60 | Pemicu pemisahan adegan yang dinyatakan sebagai durasi dalam detik: hanya video yang lebih panjang dari ambang batas yang dipisahkan. |
| `debug_dataset` |  | boolean | no | `false` |  | Mode pemeriksaan prapemrosesan untuk memeriksa video, gambar, dan caption sebelum proses pelatihan penuh. Mengaktifkannya membuat trainer mengembalikan dataset pelatihan yang telah diproses dalam arsip yang dapat diunduh untuk ditinjau secara manual. |
| `with_audio` |  | boolean | no | `false` |  | Mode ekstensi: false, bawaan, memperpanjang video saja dan menghasilkan output tanpa suara. Dengan true, audio dan video dilanjutkan dari jendela awalan bersama, dan setiap klip pelatihan serta validasi harus memiliki trek audio. |
| `audio_normalize` |  | boolean | no | `true` |  | Normalisasi puncak audio untuk menjaga level yang konsisten di seluruh dataset. |
| `audio_preserve_pitch` |  | boolean | no | `true` |  | Pelestarian pitch saat menyesuaikan audio dengan panjang video, bukan memotong atau menambahkan padding. |
| `conditioning_frames` |  | integer | no | `9` | 9 – 121 | Jumlah bingkai awalan bersih, dipetakan ke latent `temporal_boundary` sebagai `(conditioning_frames-1)//8+1`. Awalan menggunakan bingkai piksel awal dan juga mengondisikan audio dengan `with_audio`; jumlah yang valid adalah 1 modulo 8, misalnya 9, 17, atau 25. Klip harus memiliki lebih banyak bingkai laten daripada batas ini agar pembuatan lanjutan dapat dilakukan. |
| `validation` |  | array of object {prompt, video_url} | no | `[]` | ≤ 2 items | Data validasi untuk ekstensi video maju, disediakan sebagai daftar entri yang berisi prompt dan video untuk dilanjutkan. |
| `validation[].prompt` |  | string | yes |  |  | Prompt yang digunakan selama validasi. |
| `validation[].video_url` |  | string (video URL) | yes |  | ≥ 1 characters | URL video untuk ekstensi sepanjang sumbu waktu. |
| `validation_negative_prompt` |  | string | no | `blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio, incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts.` |  | Prompt negatif yang diterapkan selama validasi, yang menggunakan proses pratinjau satu tahap. Karena proses tersebut mendekati inferensi produksi distilled dengan dua tahap, panduan dan kualitas pratinjaunya berbeda dari hasil akhir. |
| `validation_number_of_frames` |  | integer | no | `89` | 9 – 121 | Jumlah bingkai untuk setiap video validasi. |
| `validation_frame_rate` |  | integer | no | `24` | 8 – 60 | Laju bingkai target untuk video validasi, dalam bingkai per detik; LTX-2.3 berjalan secara native pada 24. |
| `validation_resolution` |  | enum (string) | no | `high` | `low`, `medium`, `high` | Resolusi yang digunakan selama validasi. |
| `validation_aspect_ratio` |  | enum (string) | no | `1:1` | `16:9`, `1:1`, `9:16` | Rasio aspek yang digunakan selama validasi. |
| `stg_scale` |  | number | no | `1` | 0 – 3 | Skala Spatio-Temporal Guidance (STG), dengan 1.0 direkomendasikan dan 0.0 menonaktifkan 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-trainer-v2/extend-prefix?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-trainer-v2/extend-prefix?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-trainer-v2/extend-prefix", 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-trainer-v2/extend-prefix",
      "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-trainer-v2/extend-prefix",
  "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": 12400,
    "usd": "12.40",
    "charged": 12400,
    "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
    },
    "audio": {
      "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 | Pratinjau video gabungan dari validasi, jika tersedia untuk endpoint yang menghasilkan video. |
| `audio` | object {url, content_type, file_name, file_size} \| null | Audio gabungan dari validasi, diberikan sebagai pratinjau jika tersedia untuk rute khusus audio berikut: /audio-inpaint, /audio-extend-suffix, /audio-extend-prefix, /t2a, /a2a, dan /v2a. |
| `lora_file` | object {url, content_type, file_name, file_size} | URL bobot LoRA terlatih dalam format .safetensors. |
| `config_file` | object {url, content_type, file_name, file_size} | Konfigurasi untuk penyiapan endpoint inferensi. |
| `debug_dataset` | object {url, content_type, file_name, file_size} \| null | Output debug yang tersedia saat `debug_dataset` diaktifkan: arsip yang dapat diunduh dan berisi data pelatihan setelah prapemrosesan. |

## 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-trainer-v2/extend-prefix
- 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-trainer-v2/extend-prefix
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.com/v1/models/ltx23-trainer-v2/extend-prefix