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

> Generéiert en neie Video no enger Referenz, mat optional ersatem Audio an éischtem a leschte Frame

Hëlt e `prompt` an eng Referenz-`video_url`. Eng optional `audio_url` ersetzt den Audio; wann se feelt, gëtt den Audio vum Input-Video benotzt. `image_url` an `end_image_url` kënnen den éischten an de leschte Frame fixéieren. Wann `match_video_length` aktiv ass, follegt d'Framezuel der Referenz; soss gëllt `num_frames` (9 bis 481).

- Model id: `ltx-2.3-22b/reference-video-to-video`
- Made by: Lightricks
- Category: Video to Video
- Output: video
- Price per megapixel of your output video: $0.00161 / megapixel of output video (cheapest run $0.002 (2 API credits))
- Run: `POST https://api.doitong.com/v1/run/ltx-2.3-22b/reference-video-to-video`
- Quote: `POST https://api.doitong.com/v1/quote/ltx-2.3-22b/reference-video-to-video`
- Docs page: https://doitong.com/lb/developers/models/ltx-2.3-22b/reference-video-to-video

## Pricing

Price: **$0.00161 / 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 $0.453 = 453 API credits (282 MP output video × $0.001605).

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/ltx-2.3-22b/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, deen als Grondlag fir d'Videogeneratioun benotzt gëtt. |
| `video_url` | `video` | string (video URL) | yes |  |  | URL, déi de Referenzvideo identifizéiert. |
| `audio_url` | `audio` | string (audio URL) \| null | no |  |  | Optional Audio-URL fir d'Audiospur vum Video. Wann e feelt, gëtt vorhandenen Audio aus dem Quellvideo benotzt. |
| `image_url` | `image` | string (image URL) \| null | no |  |  | Optional Bild-URL, déi den éischte Frame vum Video definéiert. |
| `end_image_url` | `end_image` | string (image URL) \| null | no |  |  | Bild-URL, déi de leschte Frame vum Video definéiert. |
| `match_video_length` |  | boolean | no | `true` |  | Modus fir d'Frame-Zuel: deaktivéiert benotzt `num_frames`, aktivéiert berechent d'Zuel mat FPS an der Videodauer. |
| `num_frames` |  | integer | no | `121` | 9 – 481 | Frame-Zuel vum generéierten Output. |
| `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` | Dimensioune vum generéierte Video. |
| `generate_audio` |  | boolean | no | `true` |  | Steiert, ob de Video generéierten Audio enthält. |
| `use_multiscale` |  | boolean | no | `true` |  | Toggle fir Multi-Scale-Generatioun fir besser Kohärenz an Detailer. Mat True féiert e méi klenge virleefege Video eng zweet Generatioun un, där hir Gréisst déi ugefrote Dimensiounen erreecht oder iwwerschreit. |
| `match_input_fps` |  | boolean | no | `true` |  | Iwwerschreiwung vun der Output-Frame-Rate, déi bei Aktivéierung den Standard-FPS duerch de FPS vum Quellvideo ersetzt. |
| `fps` |  | number | no | `24` | 1 – 60 | Frame-Rate vum Output-Video, gemooss a Frames pro Sekonn. |
| `num_inference_steps` |  | integer | no | `40` | 8 – 50 | Zuel vun den ausgeféierten Inferenzschrëtt. |
| `video_cfg_scale` |  | number | no | `3` | 1 – 20 | Video-Guidance-Astellung: erhéicht se fir méi Konsistenz a Fokus am generéierten Inhalt. Benotzt classifier-free guidance (CFG). |
| `video_stg_scale` |  | number | no | `0` | 0 – 20 | Kontroll vu Konsistenz a Fokus vum Video duerch d'Skala vu Spatiotemporal Guidance (STG); erhéicht d'Astellung, fir béid Eegeschafte ze verstäerken. |
| `video_rescaling_scale` |  | number | no | `0.7` | 0 – 1 | Video-Rescaling-Astellung, déi classifier-free a spatiotemporal guidance als Verhältnis ausbalancéiert. |
| `video_modality_scale` |  | number | no | `3` | 0 – 10 | Video-Modalitéits-Astellung, déi d'Bäiträg vu Video an Audio als Verhältnis ausbalancéiert. |
| `audio_cfg_scale` |  | number | no | `7` | 1 – 20 | Audio-Guidance-Astellung: erhéicht se fir méi Konsistenz a Fokus am generéierten Inhalt. Benotzt classifier-free guidance (CFG). |
| `audio_stg_scale` |  | number | no | `0` | 0 – 20 | Kontroll vu Konsistenz a Fokus vum Audio duerch d'Skala vu Spatiotemporal Guidance (STG); erhéicht d'Astellung, fir béid Eegeschafte ze verstäerken. |
| `audio_rescaling_scale` |  | number | no | `0.7` | 0 – 1 | Audio-Rescaling-Astellung, déi classifier-free a spatiotemporal guidance als Verhältnis ausbalancéiert. |
| `audio_modality_scale` |  | number | no | `3` | 0 – 10 | Audio-Modalitéits-Astellung, déi d'Bäiträg vu Video an Audio als Verhältnis ausbalancéiert. |
| `gradient_estimation_gamma` |  | number | no | `2` | 0 – 10 | Astellung fir d'Estimatioun vum Denoising-Gradient: 0 deaktivéiert d'Estimatioun; soss spezifizéiert de Wäert gamma. |
| `use_restart_sampling` |  | boolean | no | `false` |  | Toggle fir Restart-Sampling mat méiglecherweis besserer Videoqualitéit: d'Aktivéierung füügt bei all Denoising-Schrëtt e bëssen Rausche bäi. |
| `scheduler` |  | enum (string) | no | `ltx2` | `ltx2`, `linear_quadratic`, `beta` | Auswiel vum Scheduler. |
| `acceleration` |  | enum (string) | no | `regular` | `none`, `regular`, `high`, `full` | Beschleunigungsniveau, deen op d'Veraarbechtung applizéiert gëtt. |
| `camera_lora` |  | enum (string) | no | `none` | `dolly_in`, `dolly_out`, `dolly_left`, `dolly_right`, `jib_up`, `jib_down`, `static`, `none` | Auswiel vun der Kamera-LoRA fir d'Beweegung am generéierte Video méi präzis ze steiere wéi nëmme mat Kamera-Beweegungs-Prompts. |
| `camera_lora_scale` |  | number | no | `1` | 0 – 1 | Stäerkt vun der Kamera-LoRA fir d'Beweegung am generéierte Video méi präzis ze steiere wéi nëmme mat Kamera-Beweegungs-Prompts. |
| `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` |  | Negativen Prompt, dee bei der Videogeneratioun benotzt gëtt. |
| `seed` |  | integer \| null | no |  |  | Seed-Wäert, deen d'Generatioun vun Zoufallszuelen initialiséiert. |
| `enable_prompt_expansion` |  | boolean | no | `true` |  | Steiert, ob d'Prompt-Erweiderung aktivéiert ass. |
| `enable_safety_checker` |  | boolean | no | `true` |  | Steiert, ob d'Sécherheetskontroll aktivéiert ass. |
| `video_output_type` |  | enum (string) | no | `X264 (.mp4)` | `X264 (.mp4)`, `VP9 (.webm)`, `PRORES4444 (.mov)`, `GIF (.gif)` | Output-Typ vum resultéierende Video. |
| `video_quality` |  | enum (string) | no | `high` | `low`, `medium`, `high`, `maximum` | Qualitéitsniveau vum resultéierende Video. |
| `video_write_mode` |  | enum (string) | no | `balanced` | `fast`, `balanced`, `small` | Schreifmodus vum resultéierende Video. |
| `distill_lora_first_pass_scale` |  | number | no | `0.2` | 0 – 1 | Steiert d'Skaléierung vun der Distill-LoRA am éischte Pass; 0 deaktivéiert se. |
| `distill_lora_second_pass_scale` |  | number | no | `0.5` | 0 – 1 | Steiert d'Skaléierung vun der Distill-LoRA fir all Pass nom éischten. |
| `video_strength` |  | number | no | `1` | 0 – 1 | D'Fräiheet, de Videoinhalt z'änneren, gëtt duerch dës Conditioning-Stäerkt gesteiert: méi kleng Astellunge ginn dem Modell méi Spillraum. |
| `audio_strength` |  | number | no | `1` | 0 – 1 | D'Fräiheet, den Audioinhalt z'änneren, gëtt duerch dës Conditioning-Stäerkt gesteiert: méi kleng Astellunge ginn dem Modell méi Spillraum. |
| `preprocessor` |  | enum (string) | no | `none` | `depth`, `canny`, `pose`, `none` | Virveraarbechter, deen wärend der Generatioun applizéiert gëtt. |
| `ic_lora_type` |  | enum (string) | no | `union` | `match_preprocessor`, `union`, `detailer`, `none` | IC-LoRA-Variant, déi wärend der Generatioun applizéiert gëtt. |

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
{
  "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.com/v1/run/ltx-2.3-22b/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.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/ltx-2.3-22b/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.com/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-2.3-22b/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.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": "ltx-2.3-22b/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-2.3-22b/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": 453,
    "usd": "0.453",
    "charged": 453,
    "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,
      "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.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, width, height, fps, duration, num_frames} | Video, dee vum Modell produzéiert gëtt. |
| `seed` | integer | Seed-Wäert, mat deem d'Generatioun vun Zoufallszuele initialiséiert gëtt. |
| `prompt` | string | Prompt, deen d'Generatioun leet. |

## Related models

- [LTX-2.3 22B · Text to Video](https://doitong.com/developers/models/ltx-2.3-22b/text-to-video.md) (`ltx-2.3-22b/text-to-video`): $0.00161 / megapixel of output video
- [LTX-2.3 22B · Text to Video · LoRA](https://doitong.com/developers/models/ltx-2.3-22b/text-to-video/lora.md) (`ltx-2.3-22b/text-to-video/lora`): $0.00181 / megapixel of output video
- [LTX-2.3 22B · Image to Video](https://doitong.com/developers/models/ltx-2.3-22b/image-to-video.md) (`ltx-2.3-22b/image-to-video`): $0.00161 / megapixel of output video
- [LTX-2.3 22B · Image to Video · LoRA](https://doitong.com/developers/models/ltx-2.3-22b/image-to-video/lora.md) (`ltx-2.3-22b/image-to-video/lora`): $0.00181 / megapixel of output video
- [LTX 2.3 22B](https://doitong.com/developers/models/ltx-2.3-22b/reference-video-to-video/lora.md) (`ltx-2.3-22b/reference-video-to-video/lora`): $0.00181 / megapixel of output video
- [LTX-2.3 22B · Extend Video](https://doitong.com/developers/models/ltx-2.3-22b/extend-video.md) (`ltx-2.3-22b/extend-video`): $0.00161 / megapixel of output video
- [LTX-2.3 22B · Extend Video · LoRA](https://doitong.com/developers/models/ltx-2.3-22b/extend-video/lora.md) (`ltx-2.3-22b/extend-video/lora`): $0.00181 / megapixel of output video
- [LTX-2.3 22B · Video to Video](https://doitong.com/developers/models/ltx-2.3-22b/video-to-video.md) (`ltx-2.3-22b/video-to-video`): $0.00161 / megapixel of output video

## Links

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