# Ltx 2.3 Quality · Reference Video to Video · LoRA API

> Penjanaan berasaskan video rujukan seperti versi asasnya, tetapi menggunakan sehingga 3 LoRA tersuai

Menjana video daripada `prompt` yang diperlukan dan `video_url` rujukan untuk gerakan serta struktur, dan turut memerlukan `loras`, sehingga 3 fail LoRA berukuran maksimum 3 GB setiap satu. Imej bingkai utama pertama, tengah dan terakhir pilihan (`image_url`, `mid_image_url`, `end_image_url`) menetapkan rupa. `video_strength` dan `strength` berjulat dari 0 hingga 1, manakala `num_frames` dari 9 hingga 481.

- Model id: `ltx-2.3-quality/reference-video-to-video/lora`
- Made by: Lightricks
- Category: Video to Video
- Output: video
- Price per megapixel of your output video: $0.00271 / megapixel of output video (cheapest run $0.003 (3 API credits))
- Run: `POST https://api.doitong.ru/v1/run/ltx-2.3-quality/reference-video-to-video/lora`
- Quote: `POST https://api.doitong.ru/v1/quote/ltx-2.3-quality/reference-video-to-video/lora`
- Docs page: https://doitong.com/ms/developers/models/ltx-2.3-quality/reference-video-to-video/lora

## Pricing

Price: **$0.00271 / megapixel of output video**. Price per megapixel of your output video: the input files are measured before the run (length, resolution, frame rate). The quote measures the same files and is exactly what the run charges.

The full example input below costs $0.304 = 304 API credits (112 MP output video × $0.002708).

Prices are the upstream price in USD, paid from the API balance in API credits (1000 API credits = 1 USD). `POST https://api.doitong.ru/v1/quote/ltx-2.3-quality/reference-video-to-video/lora` 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

Send either the canonical name or the native field name (not both). Canonical names are the same across models.

| Parameter | Canonical name | Type | Required | Default | Allowed values / range | Description |
|---|---|---|---|---|---|---|
| `prompt` |  | string | yes |  |  | Prompt yang digunakan untuk mengarahkan penjanaan. |
| `video_url` | `video` | string (video URL) | yes |  |  | URL yang merujuk kepada video rujukan untuk memandu gerakan dan struktur. |
| `control_video_url` |  | string (video URL) \| null | no |  |  | Video kawalan prapengiraan pilihan, digunakan dan bukannya anggaran kawalan terbina dalam apabila dibekalkan bersama `skip_control_preprocess`. Video ini menjadi isyarat kawalan langsung selepas pensampelan semula agar sepadan dengan dimensi output dan kiraan bingkai. Video tersebut boleh mengandungi, contohnya, komposit kedalaman, tepi atau pose yang telah dirender. |
| `skip_control_preprocess` |  | boolean | no | `false` |  | Mod kawalan langsung menggunakan `control_video_url` dan bukannya menganggar kedalaman, tepi atau pose secara dalaman; tanpa URL tersebut, tetapan ini diabaikan. Pensaizan output dalam mod ini mematuhi dimensi eksplisit dengan penjajaran 64 untuk memastikan video RGB dan kawalan sepadan, manakala `auto` menggunakan dimensi dan nisbah aspek sumber dalam had LTX. |
| `preserve_original_video` |  | boolean | no | `false` |  | Mod pengekalan video asal, hanya tersedia dengan `skip_control_preprocess`, `video_url` dan `control_video_url`. Dilumpuhkan secara lalai, mod ini mengekalkan pemprosesan kawalan standard; apabila didayakan, penjanaan bermula daripada `video_url` sambil mengekalkan panduan struktur daripada `control_video_url`. Penyahbisingan melalui `strength` menetapkan jumlah yang dikekalkan, dengan tetapan lebih rendah mengekalkan lebih banyak piksel asal. |
| `image_url` | `image` | string (image URL) \| null | no |  |  | Gaya penambatan imej atau identiti watak pilihan sebagai bingkai kunci bingkai pertama. |
| `mid_image_url` |  | string (image URL) \| null | no |  |  | Penampilan penambatan imej pilihan berhampiran titik tengah klip, melengkapi bingkai kunci `image_url` awal. Ia membantu penampilan menjejaki pergerakan kamera dan bukannya menyimpang; memerlukan `image_url`. |
| `end_image_url` | `end_image` | string (image URL) \| null | no |  |  | Penampilan penambatan imej pilihan pada bingkai akhir klip. Berguna apabila pergerakan kamera berakhir di lokasi yang berbeza daripada imej permulaan; memerlukan `image_url`. |
| `video_strength` |  | number | no | `0.6` | 0 – 1 | Kebebasan untuk mengubah gerakan dan struktur daripada video rujukan dikawal oleh kekuatan pengkondisian ini: tetapan lebih kecil membenarkan perubahan yang lebih besar. |
| `strength` |  | number | no | `1` | 0 – 1 | Kawalan penyahbisingan untuk pensampelan video-ke-video video rujukan yang kesannya bergantung pada `preserve_original_video`. Apabila mod itu dimatikan, ia hanya memendekkan jadual penyahbisingan; apabila dihidupkan, ia mengawal transformasi piksel sumber, dengan 1.0 menjana semula semuanya dan tetapan lebih rendah mengekalkan lebih banyak (contohnya, 0.5 mengekalkan kira-kira 50%). |
| `num_frames` |  | integer | no | `121` | 9 – 481 | Kiraan bingkai output, tertakluk pada belanjawan kestabilan IC-LoRA berdasarkan resolusi didarab dengan bingkai. Respons 422 bermaksud belanjawan itu telah melebihi had: kurangkan resolusi atau `num_frames`. Belanjawan membenarkan kira-kira 150 bingkai pada dimensi kelas 720p dan lebih banyak pada saiz lebih kecil. |
| `resolution` |  | object {width, height} \| enum (string) | no | `auto` | `auto`, `square_hd`, `square`, `portrait_4_3`, `portrait_16_9`, `landscape_4_3`, `landscape_16_9` | Dimensi video output, yang turut mempengaruhi tempoh stabil: saiz lebih kecil membenarkan lebih banyak bingkai, manakala saiz lebih besar mengurangkan maksimum. Anggaran kawalan terbina dalam mengekalkan saiz hampir dengan aliran kerja kawalan rasmi; kawalan langsung melalui `skip_control_preprocess` dan `control_video_url` sebaliknya mematuhi dimensi eksplisit dengan penjajaran 64px. Dalam mod kawalan langsung, `auto` mewarisi dimensi dan nisbah aspek sumber dalam had LTX. |
| `frames_per_second` |  | number | no | `24` | 1 – 60 | Kadar bingkai video output, diukur dalam bingkai sesaat. |
| `num_inference_steps` |  | integer | no | `15` | 8 – 30 | Tetapkan jumlah langkah inferens untuk dijalankan, sehingga 30; membiarkannya tidak berubah menggunakan 15. |
| `guidance_scale` |  | number | no | `1` | 1 – 20 | Laraskan panduan tanpa pengelas menggunakan skala ini; penalaan lalainya menyasarkan kualiti tinggi dan penjanaan pantas. |
| `generate_audio` |  | boolean | no | `true` |  | Togol trek audio untuk MP4 yang dikembalikan: mati menghasilkan fail video sahaja, manakala hidup menyertakan audio. |
| `negative_prompt` |  | string | no | `color distortion, overexposure, static, blurry details, subtitles, style, artwork, painting, frame, still, dim overall tone, worst quality, low quality, JPEG compression artifacts, ugly, mutilated, extra fingers, poorly drawn hands, poorly drawn face, deformed, disfigured, malformed limbs, fused fingers, motionless frame, cluttered background, three legs, crowded background, walking backwards` |  | Prompt negatif yang menyatakan perkara yang perlu dielakkan oleh penjanaan. |
| `seed` |  | integer \| null | no |  |  | Seed yang menjadikan penjanaan boleh diulang. Menetapkannya kepada None memilih seed secara rawak. |
| `enable_prompt_expansion` |  | boolean | no | `true` |  | Mengawal sama ada pengembangan prompt didayakan. |
| `enable_safety_checker` |  | boolean | no | `true` |  | Mengawal sama ada pemeriksaan keselamatan didayakan. |
| `video_quality` |  | enum (string) | no | `high` | `low`, `medium`, `high`, `maximum` | Praset kualiti yang digunakan pada video output. |
| `video_write_mode` |  | enum (string) | no | `balanced` | `fast`, `balanced`, `small` | Mod penulisan untuk video yang terhasil. |
| `loras` |  | array of object {path, scale, transformer} | yes |  | ≤ 3 items | Tambahan LoRA untuk LTX-2.3, setiap satu terhad kepada 3 GB, dengan maksimum 3 entri dibenarkan. Pemuatan berlaku hanya selepas pemuat turun selamat SSRF registry mendapatkan setiap laluan. |
| `loras[].path` |  | string | yes |  | ≤ 2048 characters | URL HTTP(S) terus untuk fail LoRA .safetensors yang tidak melebihi 3 GB. Pemuatan didahului oleh pengambilan menggunakan pemuat turun selamat SSRF. |
| `loras[].scale` |  | number | no | `1` | 0 – 2 | Pengaruh LoRA terhadap video yang dijana meningkat apabila kekuatan ini meningkat dalam julat 0.0–2.0. |
| `loras[].transformer` |  | enum (string) | no | `both` | `high`, `low`, `both` | Bendera pemilihan Transformer: 'both' sesuai untuk hampir semua pengguna LTX-2.3 kerana model itu hanya mempunyai satu Transformer. Bendera ini wujud untuk menyokong seni bina masa depan dengan berbilang Transformer. |

File parameters (`video`, `control_video_url`, `image`, `mid_image_url`, `end_image`) take a public `https://` URL, a `data:` URI up to 10 MB, or the `file_url` of an upload from `POST /files`.

## Example input

Required parameters only:

```json
{
  "loras": [
    {
      "path": "https://example.com/your-file.safetensors"
    }
  ],
  "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
  "video": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
}
```

A fuller example:

```json
{
  "loras": [
    {
      "path": "https://example.com/your-file.safetensors"
    }
  ],
  "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
  "video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
}
```

## 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.ru/v1/run/ltx-2.3-quality/reference-video-to-video/lora?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "loras": [
      {
        "path": "https://example.com/your-file.safetensors"
      }
    ],
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.ru/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"
```

### JavaScript

```javascript
const API = "https://api.doitong.ru/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/ltx-2.3-quality/reference-video-to-video/lora?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "loras": [
      {
        "path": "https://example.com/your-file.safetensors"
      }
    ],
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
  }),
});
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.ru/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}

payload = {
    "loras": [
        {
            "path": "https://example.com/your-file.safetensors",
        },
    ],
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/ltx-2.3-quality/reference-video-to-video/lora", 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.ru/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": "ltx-2.3-quality/reference-video-to-video/lora",
      "input": {
        "loras": [
          {
            "path": "https://example.com/your-file.safetensors"
          }
        ],
        "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
        "video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
      },
      "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": "ltx-2.3-quality/reference-video-to-video/lora",
  "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": 304,
    "usd": "0.304",
    "charged": 304,
    "refunded": 0
  },
  "input": {
    "loras": [
      {
        "path": "https://example.com/your-file.safetensors"
      }
    ],
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
  },
  "output": {
    "video": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp4",
      "content_type": "video/mp4",
      "file_name": "0-output.mp4",
      "file_size": 1843200
    },
    "seed": 42,
    "prompt": "string"
  },
  "outputs": [
    {
      "type": "video",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp4",
      "content_type": "video/mp4",
      "file_size": 1843200,
      "width": 1280,
      "height": 720,
      "duration": 5,
      "stored": true
    }
  ],
  "error": null,
  "metrics": {
    "inference_seconds": 6.8
  },
  "urls": {
    "self": "https://api.doitong.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
```

### Output fields (`output`)

| Field | Type | Description |
|---|---|---|
| `video` | object {url, content_type, file_name, file_size} | Video yang dihasilkan oleh model. |
| `seed` | integer | Seed sebenar yang digunakan semasa penjanaan. |
| `prompt` | string | Prompt penjanaan, termasuk sebarang pengembangan yang digunakan sebelum pemprosesan. |

## Related models

- [Ltx 2.3 Quality · Text to Video](https://doitong.com/developers/models/ltx-2.3-quality/text-to-video.md) (`ltx-2.3-quality/text-to-video`): $0.00241 / megapixel of output video
- [Ltx 2.3 Quality · Text to Video · LoRA](https://doitong.com/developers/models/ltx-2.3-quality/text-to-video/lora.md) (`ltx-2.3-quality/text-to-video/lora`): $0.00271 / megapixel of output video
- [Ltx 2.3 Quality · Image to Video](https://doitong.com/developers/models/ltx-2.3-quality/image-to-video.md) (`ltx-2.3-quality/image-to-video`): $0.00241 / megapixel of output video
- [Ltx 2.3 Quality · Image to Video · LoRA](https://doitong.com/developers/models/ltx-2.3-quality/image-to-video/lora.md) (`ltx-2.3-quality/image-to-video/lora`): $0.00271 / megapixel of output video
- [Ltx 2.3 Quality · Ingredient](https://doitong.com/developers/models/ltx-2.3-quality/ingredient.md) (`ltx-2.3-quality/ingredient`): $0.00241 / megapixel of output video
- [Ltx 2.3 Quality · Clean Plate](https://doitong.com/developers/models/ltx-2.3-quality/clean-plate.md) (`ltx-2.3-quality/clean-plate`): $0.00241 / megapixel of output video
- [Ltx 2.3 Quality · Colorization](https://doitong.com/developers/models/ltx-2.3-quality/colorization.md) (`ltx-2.3-quality/colorization`): $0.00241 / megapixel of output video
- [Ltx 2.3 Quality · Cross Eyed](https://doitong.com/developers/models/ltx-2.3-quality/cross-eyed.md) (`ltx-2.3-quality/cross-eyed`): $0.00241 / megapixel of output video

## Links

- HTML page: https://doitong.com/developers/models/ltx-2.3-quality/reference-video-to-video/lora
- 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=ltx-2.3-quality/reference-video-to-video/lora
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.ru/v1/models/ltx-2.3-quality/reference-video-to-video/lora