# Ltx 2.3 Quality · Extend Video · LoRA API

> Extiende un video hacia adelante o atrás con hasta 3 LoRAs personalizadas aplicadas

Extensión de video que también recibe una lista `loras` obligatoria de hasta 3 LoRAs personalizadas, de hasta 3 GB cada una. Un `prompt` describe cómo continúa el clip, y `extend_direction` selecciona `forward` o `backward`. `num_context_frames` (9 to 121) controla la superposición con la fuente, `num_frames` (9 to 481) el tamaño del segmento, y `end_image_url` puede establecer un fotograma clave final.

- Model id: `ltx-2.3-quality/extend-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/extend-video/lora`
- Quote: `POST https://api.doitong.ru/v1/quote/ltx-2.3-quality/extend-video/lora`
- Docs page: https://doitong.com/es-MX/developers/models/ltx-2.3-quality/extend-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/extend-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 que especifica la continuación deseada del video. |
| `video_url` | `video` | string (video URL) | yes |  |  | URL que apunta al video que se extenderá. |
| `extend_direction` |  | enum (string) | no | `forward` | `forward`, `backward` | Modo de extensión del video: 'backward' crea un nuevo inicio, mientras que 'forward' continúa el video después de su final. |
| `num_frames` |  | integer | no | `121` | 9 – 481 | Número de fotogramas de extensión, sujeto a un presupuesto de generación estable basado en la resolución multiplicada por los fotogramas: a 24 fps, aproximadamente 20 segundos para la clase 480p, 11 segundos para la clase 720p o 5 segundos para la clase 1080p. Las solicitudes que superan el presupuesto devuelven 422; reduce `num_frames` o elige una resolución menor. El número incluye `num_context_frames` superpuestos con el origen, por lo que la duración agregada es aproximadamente (`num_frames` - `num_context_frames`) / `frames_per_second` segundos. |
| `num_context_frames` |  | integer | no | `25` | 9 – 121 | Número de fotogramas de origen solicitado para el contexto o la superposición de la extensión, limitado por la cantidad de fotogramas que contiene el origen. El número se redondea hacia abajo para ajustarse a la cuadrícula LTX de 8k+1. |
| `end_image_url` | `end_image` | string (image URL) \| null | no |  |  | Imagen de fotograma clave opcional que establece el nuevo primer fotograma de la extensión al extender hacia atrás o su último fotograma al extender hacia adelante. |
| `end_image_strength` |  | number | no | `1` | 0 – 1 | Intensidad opcional del condicionamiento del fotograma clave final: reducirla permite mayor libertad al modelo, mientras que 1.0 exige una coincidencia exacta. |
| `resolution` |  | object {width, height} \| enum (string) | no | `auto` | `auto`, `square_hd`, `square`, `portrait_4_3`, `portrait_16_9`, `landscape_4_3`, `landscape_16_9` | Dimensiones del video generado, alineadas con incrementos de 32px; por ejemplo, 1920x1080 se convierte en 1888x1056, y el origen se redimensiona a estas dimensiones para la salida unida. Las extensiones estables pueden ser más largas con resoluciones menores y más cortas con resoluciones mayores. Elegir 'auto' conserva las dimensiones y la relación de aspecto del origen dentro de los límites de LTX. |
| `match_input_fps` |  | boolean | no | `true` |  | Coincidencia de la velocidad de fotogramas de salida con el origen cuando está activada, anulando `frames_per_second`. El FPS del origen se redondea a un entero y se restringe al rango admitido. |
| `frames_per_second` |  | number | no | `24` | 1 – 60 | Velocidad de fotogramas del video de salida, medida en fotogramas por segundo. |
| `video_strength` |  | number | no | `1` | 0 – 1 | Intensidad del condicionamiento del contexto de origen: reducirla permite mayor libertad al modelo. En 1.0, los fotogramas superpuestos permanecen fijados al origen, lo que hace uniforme la transición. |
| `num_inference_steps` |  | integer | no | `15` | 8 – 30 | Establece cuántos pasos de inferencia ejecutar, hasta 30; dejarlo sin cambios usa 15. |
| `guidance_scale` |  | number | no | `1` | 1 – 20 | Ajusta la guía sin clasificador mediante esta escala; su configuración predeterminada busca alta calidad y generación rápida. |
| `generate_audio` |  | boolean | no | `true` |  | Interruptor de audio de la extensión: desactivado deja el segmento agregado en silencio y conserva la pista de audio del video de origen. Activado genera audio para la extensión y aplica un crossfade con el origen en la unión. |
| `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 negativo que especifica lo que la generación debe evitar. |
| `seed` |  | integer \| null | no |  |  | Semilla que hace reproducible la generación. Establecerla en None selecciona una semilla aleatoriamente. |
| `enable_prompt_expansion` |  | boolean | no | `true` |  | Controla si la expansión del prompt está habilitada. |
| `enable_safety_checker` |  | boolean | no | `true` |  | Controla si la comprobación de seguridad está activada. |
| `video_quality` |  | enum (string) | no | `high` | `low`, `medium`, `high`, `maximum` | Preajuste de calidad aplicado al video de salida. |
| `video_write_mode` |  | enum (string) | no | `balanced` | `fast`, `balanced`, `small` | Modo de escritura del video resultante. |
| `loras` |  | array of object {path, scale, transformer} | yes |  | ≤ 3 items | Adiciones de LoRA para LTX-2.3, cada una limitada a 3 GB, con un máximo de 3 entradas. La carga ocurre solo después de que el descargador seguro contra SSRF del registro recupera cada ruta. |
| `loras[].path` |  | string | yes |  | ≤ 2048 characters | URL HTTP(S) directa a un archivo LoRA .safetensors de hasta 3 GB. La carga es precedida por la recuperación mediante un descargador seguro contra SSRF. |
| `loras[].scale` |  | number | no | `1` | 0 – 2 | La influencia de LoRA en el video generado aumenta a medida que aumenta esta intensidad dentro del rango 0.0–2.0. |
| `loras[].transformer` |  | enum (string) | no | `both` | `high`, `low`, `both` | Indicador de selección del transformador: 'both' es adecuado para casi todos los usuarios de LTX-2.3 porque el modelo tiene un solo transformador. El indicador existe para admitir arquitecturas futuras con varios transformadores. |

File parameters (`video`, `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/extend-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/extend-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/extend-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/extend-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/extend-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 producido por el modelo. |
| `seed` | integer | Semilla aplicada durante la generación. |
| `prompt` | string | Prompt de generación, incluida cualquier expansión aplicada antes de usarlo. |

## 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/extend-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/extend-video/lora
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.ru/v1/models/ltx-2.3-quality/extend-video/lora