# Ltx 2.3 Quality · Reference Video to Video API

> Generaziun guidada d'in prompt cun in video da referenza, cun maletgs opziunals dal prim, mesaun e davos keyframe

Crea in nov video dad in `prompt` obligatoric ed in `video_url` da referenza che furnescha moviment e structura. `image_url`, `mid_image_url` ed `end_image_url` facultativs fixeschan l'apparientscha a l'entschatta, amez e la fin. `video_strength` e `strength` (omadus 0 fin 1) controllan quant bain ch'il model suonda u mantegna la funtauna, e `control_video_url` po furnir in signal da controlla precalculà. `resolution` porscha auto u preselecziuns fixas sco square e 16:9 vertical u orizontal.

- Model id: `ltx-2.3-quality/reference-video-to-video`
- Made by: Lightricks
- Category: Video to Video
- Output: video
- Price per megapixel of your output video: $0.00241 / 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`
- Quote: `POST https://api.doitong.ru/v1/quote/ltx-2.3-quality/reference-video-to-video`
- Docs page: https://doitong.com/rm/developers/models/ltx-2.3-quality/reference-video-to-video

## Pricing

Price: **$0.00241 / 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 $0.27 = 270 API credits (112 MP output video × $0.002408).

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` 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 utilisà per dirigir la generaziun. |
| `video_url` | `video` | string (video URL) | yes |  |  | URL che mussa ad in video da referenza utilisà per guidar il moviment e la structura. |
| `control_video_url` |  | string (video URL) \| null | no |  |  | Video da controlla precalculà facultativ, utilisà empè da l'estimaziun da controlla integrada sch'el vegn furnì ensemen cun `skip_control_preprocess`. El daventa il signal direct da controlla suenter il resampling per adattar las dimensiuns da l'output e la quantitad da frames. Il video po cuntegnair, per exempel, in composite da profunditad, urs u posa gia renderisà. |
| `skip_control_preprocess` |  | boolean | no | `false` |  | Modus da controlla direct cun `control_video_url` empè d'estimar internamain profunditad, urs u posa; senza questa URL vegn la configuraziun ignorada. Il dimensionament da l'output respecta en quest modus dimensiuns explicitas cun alignament 64, per mantegnair RGB e videos da controlla concordants, entant che `auto` prenda las dimensiuns e la proporziun da l'origin entaifer ils limits da LTX. |
| `preserve_original_video` |  | boolean | no | `false` |  | Modus per mantegnair il video original, disponibel mo cun `skip_control_preprocess`, `video_url` e `control_video_url`. Disactivà per standard, el lascha intact il process da controlla standard; activà, el cumenza la generaziun da `video_url` mantegnend la guida structurala da `control_video_url`. Il denoising tras `strength` fixescha la quantitad mantegnida; valurs pli bassas mantegnan dapli pixels originals. |
| `image_url` | `image` | string (image URL) \| null | no |  |  | Stil d'ancra da maletg facultativ u identitad dal caracter sco keyframe dal prim frame. |
| `mid_image_url` |  | string (image URL) \| null | no |  |  | Aspect d'ancra da maletg facultativ enturn il center dal clip, che cumplettescha il keyframe inizial `image_url`. El gida l'aspect a suandar il moviment da la camera empè da derivar; dovra `image_url`. |
| `end_image_url` | `end_image` | string (image URL) \| null | no |  |  | Aspect d'ancra da maletg facultativ al davos frame dal clip. Util sch'il moviment da la camera finescha en in lieu different da l'immagine da partenza; dovra `image_url`. |
| `video_strength` |  | number | no | `0.6` | 0 – 1 | La libertad da midar moviment e structura dal video da referenza vegn controllada da questa forza da conditioning: valurs pli pitschnas permettan dapli midadas. |
| `strength` |  | number | no | `1` | 0 – 1 | Controlla il denoising per il sampling da video-a-video da referenza; l'effect dependa da `preserve_original_video`. Sche il modus è disactivà, el scurzescha mo il program da denoising; sche activà, controlla la transformaziun dals pixels d'origin, cun 1.0 regenerond tut e valurs pli bassas mantegnend dapli, per exempel 0.5 mantegn circa 50%. |
| `num_frames` |  | integer | no | `121` | 9 – 481 | Dumber da frame da l'output, limità tras in budget da stabilitad IC-LoRA basà sin la resoluziun multiplitgada cun il dumber da frame. Ina resposta 422 signifitga che quest budget è vegnì surpassà: reduci la resoluziun u `num_frames`. Il budget permetta circa 150 frame cun dimensiuns da la classa 720p e dapli cun dimensiuns pli pitschnas. |
| `resolution` |  | object {width, height} \| enum (string) | no | `auto` | `auto`, `square_hd`, `square`, `portrait_4_3`, `portrait_16_9`, `landscape_4_3`, `landscape_16_9` | Dimensiuns dal video d'output, che influenzeschan era la durada stabila: dimensiuns pli pitschnas permettan dapli frames, pli grondas reduceschan il maximum. L'estimaziun da controlla integrada mantegna la dimensiun datiers dal workflow da controlla uffizial; la controlla directa tras `skip_control_preprocess` e `control_video_url` respecta dimensiuns explicitas cun alignament 64px. En il modus da controlla direct prenda `auto` las dimensiuns e la proporziun da l'origin entaifer ils limits da LTX. |
| `frames_per_second` |  | number | no | `24` | 1 – 60 | Frame rate dal video d’output, mesirà en frames per secunda. |
| `num_inference_steps` |  | integer | no | `15` | 8 – 30 | Definir quants pass d’inferenza da far, fin a 30; senza midada vegnan utilisads 15. |
| `guidance_scale` |  | number | no | `1` | 1 – 20 | Ajustar la classifier-free guidance cun questa scala; la configuraziun standard mira a qualitad auta e generaziun svelta. |
| `generate_audio` |  | boolean | no | `true` |  | Interrupziun da la pista audio per l’MP4 restituì: deactivada producescha ina datoteca mo cun video, activada includa 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 negativ che specifiescha da tge che la generaziun duai evitar. |
| `seed` |  | integer \| null | no |  |  | Seed che renda la generaziun reproducibla. Cun definir None vegn tschernì in seed casualmain. |
| `enable_prompt_expansion` |  | boolean | no | `true` |  | Controlla sche l'expansiun dal prompt è activada. |
| `enable_safety_checker` |  | boolean | no | `true` |  | Controllescha sche la verificaziun da segirezza è activada. |
| `video_quality` |  | enum (string) | no | `high` | `low`, `medium`, `high`, `maximum` | Preset da qualitad applitgà al video d’output. |
| `video_write_mode` |  | enum (string) | no | `balanced` | `fast`, `balanced`, `small` | Modus da scriver per il video resultà. |

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
{
  "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
{
  "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?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "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?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "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 = {
    "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", 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",
      "input": {
        "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",
  "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": 270,
    "usd": "0.27",
    "charged": 270,
    "refunded": 0
  },
  "input": {
    "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 producì dal model. |
| `seed` | integer | Seed effectiv applitgà durant la generaziun. |
| `prompt` | string | Prompt da generaziun, inclusiv eventuala expansiun applitgada avant l’utilisaziun. |

## 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
- 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
- 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