# LTX-2.3 22B Distilled · Reference Video to Video · LoRA API

> Geração destilada de vídeo de referência com LoRAs personalizadas e opções de pré-processador e tipo de IC LoRA

Recebe um `video_url` de referência, um `prompt` e uma lista `loras` obrigatória. `preprocessor` aceita mapa de profundidade, canny, pose ou none, e `ic_lora_type` escolhe o modo IC LoRA. `video_strength` e `audio_strength` variam de 0 a 1, com entradas opcionais `audio_url`, `image_url` e `end_image_url`.

- Model id: `ltx-2.3-22b/distilled/reference-video-to-video/lora`
- Made by: Lightricks
- Category: Video to Video
- Output: video
- Price per megapixel of your output video: $0.00141 / megapixel of output video (cheapest run $0.002 (2 API credits))
- Run: `POST https://api.doitong.ru/v1/run/ltx-2.3-22b/distilled/reference-video-to-video/lora`
- Quote: `POST https://api.doitong.ru/v1/quote/ltx-2.3-22b/distilled/reference-video-to-video/lora`
- Docs page: https://doitong.com/pt-BR/developers/models/ltx-2.3-22b/distilled/reference-video-to-video/lora

## Pricing

Price: **$0.00141 / 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 $0.397 = 397 API credits (282 MP output video × $0.001405).

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-2.3-22b/distilled/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 usado como base para a geração do vídeo. |
| `video_url` | `video` | string (video URL) | yes |  |  | URL que identifica o vídeo de referência. |
| `audio_url` | `audio` | string (audio URL) \| null | no |  |  | URL opcional do áudio que fornece a faixa de áudio do vídeo. Quando omitida, o áudio do vídeo de origem é usado, se presente. |
| `image_url` | `image` | string (image URL) \| null | no |  |  | URL opcional da imagem que define o quadro inicial do vídeo. |
| `end_image_url` | `end_image` | string (image URL) \| null | no |  |  | URL da imagem que define o quadro final do vídeo. |
| `match_video_length` |  | boolean | no | `true` |  | Modo de seleção da quantidade de quadros: desabilitado usa `num_frames`, enquanto habilitado calcula a quantidade usando FPS e a duração do vídeo. |
| `num_frames` |  | integer | no | `121` | 9 – 481 | Contagem de quadros da saída gerada. |
| `video_size` |  | object {width, height} \| enum (string) | no | `auto` | `auto`, `square_hd`, `square`, `portrait_4_3`, `portrait_16_9`, `landscape_4_3`, `landscape_16_9` | Dimensões do vídeo gerado. |
| `generate_audio` |  | boolean | no | `true` |  | Controla se o vídeo inclui áudio gerado. |
| `use_multiscale` |  | boolean | no | `true` |  | Alternância de geração em múltiplas escalas para melhorar a coerência e os detalhes. Com True, um vídeo preliminar menor orienta uma segunda geração cujo tamanho atende ou excede as dimensões solicitadas. |
| `match_input_fps` |  | boolean | no | `true` |  | Substituição da taxa de quadros da saída que troca o FPS alvo padrão pelo FPS do vídeo de origem quando habilitada. |
| `fps` |  | number | no | `24` | 1 – 60 | Taxa de quadros do vídeo de saída, medida em quadros por segundo. |
| `scheduler` |  | enum (string) | no | `ltx2` | `ltx2`, `linear_quadratic`, `beta` | Seleção do scheduler. |
| `acceleration` |  | enum (string) | no | `none` | `none`, `regular`, `high`, `full` | Nível de aceleração aplicado ao processamento. |
| `camera_lora` |  | enum (string) | no | `none` | `dolly_in`, `dolly_out`, `dolly_left`, `dolly_right`, `jib_up`, `jib_down`, `static`, `none` | Seleção do Camera LoRA para controlar o movimento no vídeo gerado com mais precisão do que apenas prompts de movimento da câmera. |
| `camera_lora_scale` |  | number | no | `1` | 0 – 1 | Intensidade do Camera LoRA para controlar o movimento no vídeo gerado com mais precisão do que apenas prompts de movimento da câmera. |
| `negative_prompt` |  | string | no | `news broadcast, 3d animation, computer graphics, pc game, console game, video game, cartoon, childish, watermark, logo, text, on screen text, subtitles, titles, signature, slowmo, static` |  | Prompt negativo usado durante a geração de vídeo. |
| `seed` |  | integer \| null | no |  |  | Valor de seed que inicializa a geração de números aleatórios. |
| `enable_prompt_expansion` |  | boolean | no | `true` |  | Controla se a expansão do prompt está ativada. |
| `enable_safety_checker` |  | boolean | no | `true` |  | Controla se a verificação de segurança está ativada. |
| `video_output_type` |  | enum (string) | no | `X264 (.mp4)` | `X264 (.mp4)`, `VP9 (.webm)`, `PRORES4444 (.mov)`, `GIF (.gif)` | Tipo de saída do vídeo resultante. |
| `video_quality` |  | enum (string) | no | `high` | `low`, `medium`, `high`, `maximum` | Nível de qualidade do vídeo resultante. |
| `video_write_mode` |  | enum (string) | no | `balanced` | `fast`, `balanced`, `small` | Modo de gravação do vídeo resultante. |
| `loras` |  | array of object {path, weight_name, scale} | yes |  |  | Seleção de LoRA para geração. |
| `loras[].path` |  | string | yes |  |  | Localização dos pesos do LoRA, fornecida como URL ou ID de repositório do HuggingFace no formato owner/repo. |
| `loras[].weight_name` |  | string \| null | no |  |  | Nome do peso do LoRA para selecionar entre vários pesos em um repositório do HuggingFace; somente repositórios com vários pesos exigem esse valor. Esta configuração não tem efeito a menos que `path` identifique um repositório do HuggingFace. |
| `loras[].scale` |  | number | no | `1` | 0 – 4 | Fator de escala aplicado ao LoRA, variando de 0.0 a 4.0. |
| `distill_lora_second_pass_scale` |  | number | no | `0.5` | 0 – 1 | Controle a escala do distill LoRA em cada passagem após a primeira. |
| `video_strength` |  | number | no | `1` | 0 – 1 | A liberdade para alterar o conteúdo do vídeo é controlada por esta intensidade de condicionamento: valores menores dão mais liberdade ao modelo. |
| `audio_strength` |  | number | no | `1` | 0 – 1 | A liberdade para alterar o conteúdo do áudio é controlada por esta intensidade de condicionamento: valores menores dão mais liberdade ao modelo. |
| `preprocessor` |  | enum (string) | no | `none` | `depth`, `canny`, `pose`, `none` | Pré-processador aplicado durante a geração. |
| `ic_lora_type` |  | enum (string) | no | `union` | `match_preprocessor`, `union`, `detailer`, `none` | Variante do IC LoRA aplicada durante a geração. |

File parameters (`video`, `audio`, `image`, `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-2.3-22b/distilled/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-2.3-22b/distilled/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-2.3-22b/distilled/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-2.3-22b/distilled/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-2.3-22b/distilled/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": 397,
    "usd": "0.397",
    "charged": 397,
    "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,
      "width": 1024,
      "height": 768,
      "fps": 1.0,
      "duration": 5,
      "num_frames": 1
    },
    "seed": 42,
    "prompt": "black-and-white video, a cowboy walks through a dusty town, film grain"
  },
  "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, width, height, fps, duration, num_frames} | Vídeo produzido pelo modelo. |
| `seed` | integer | Valor da seed usado para inicializar a geração de números aleatórios. |
| `prompt` | string | Prompt usado para orientar a geração. |

## Related models

- [LTX-2.3 22B Distilled · Text to Video](https://doitong.com/developers/models/ltx-2.3-22b/distilled/text-to-video.md) (`ltx-2.3-22b/distilled/text-to-video`): $0.00121 / megapixel of output video
- [LTX-2.3 22B Distilled · Text to Video · LoRA](https://doitong.com/developers/models/ltx-2.3-22b/distilled/text-to-video/lora.md) (`ltx-2.3-22b/distilled/text-to-video/lora`): $0.00141 / megapixel of output video
- [LTX-2.3 22B Distilled · Image to Video](https://doitong.com/developers/models/ltx-2.3-22b/distilled/image-to-video.md) (`ltx-2.3-22b/distilled/image-to-video`): $0.00121 / megapixel of output video
- [LTX-2.3 22B Distilled · Image to Video · LoRA](https://doitong.com/developers/models/ltx-2.3-22b/distilled/image-to-video/lora.md) (`ltx-2.3-22b/distilled/image-to-video/lora`): $0.00141 / megapixel of output video
- [LTX-2.3 22B Distilled · Reference Video to Video](https://doitong.com/developers/models/ltx-2.3-22b/distilled/reference-video-to-video.md) (`ltx-2.3-22b/distilled/reference-video-to-video`): $0.00121 / megapixel of output video
- [LTX-2.3 22B Distilled · Video to Video](https://doitong.com/developers/models/ltx-2.3-22b/distilled/video-to-video.md) (`ltx-2.3-22b/distilled/video-to-video`): $0.00121 / megapixel of output video
- [LTX-2.3 22B Distilled · Video to Video · LoRA](https://doitong.com/developers/models/ltx-2.3-22b/distilled/video-to-video/lora.md) (`ltx-2.3-22b/distilled/video-to-video/lora`): $0.00141 / megapixel of output video
- [LTX-2.3 22B Distilled · Audio to Video](https://doitong.com/developers/models/ltx-2.3-22b/distilled/audio-to-video.md) (`ltx-2.3-22b/distilled/audio-to-video`): $0.00121 / megapixel of output video

## Links

- HTML page: https://doitong.com/developers/models/ltx-2.3-22b/distilled/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-2.3-22b/distilled/reference-video-to-video/lora
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.ru/v1/models/ltx-2.3-22b/distilled/reference-video-to-video/lora