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

> Ġenerazzjoni minn vidjo ta' referenza bħall-verżjoni bażi, iżda tapplika sa 3 LoRAs personalizzati

Jiġġenera vidjo minn `prompt` meħtieġ u `video_url` ta' referenza għall-moviment u l-istruttura, u jeħtieġ ukoll `loras`, sa 3 fajls LoRA ta' mhux aktar minn 3 GB kull wieħed. Immaġnijiet fakultattivi tal-ewwel, tan-nofs u tal-aħħar keyframe (`image_url`, `mid_image_url`, `end_image_url`) jiffissaw id-dehra. `video_strength` u `strength` ivarjaw minn 0 sa 1, u `num_frames` minn 9 sa 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/mt/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 użat biex jidderieġi l-ġenerazzjoni. |
| `video_url` | `video` | string (video URL) | yes |  |  | URL li jindika vidjo ta' referenza użat biex jiggwida l-moviment u l-istruttura. |
| `control_video_url` |  | string (video URL) \| null | no |  |  | Vidjo ta' kontroll ikkalkulat minn qabel u mhux obbligatorju, użat minflok l-istima integrata tal-kontroll meta jingħata flimkien ma' `skip_control_preprocess`. Isir is-sinjal ta' kontroll dirett wara li jiġi rratat mill-ġdid biex jaqbel mad-dimensjonijiet tal-output u mal-għadd ta' frejms. Il-vidjo jista', pereżempju, ikun fih kompożit ta' fond, truf jew poża diġà rrendert. |
| `skip_control_preprocess` |  | boolean | no | `false` |  | Modalità ta' kontroll dirett li tuża `control_video_url` minflok tistma l-fond, it-truf jew il-poża internament; mingħajr dak l-URL, dan l-issettjar jiġi injorat. Id-daqs tal-output f'din il-modalità jirrispetta dimensjonijiet espliċiti b'allinjament ta' 64 biex iżomm il-vidjos RGB u ta' kontroll allinjati, filwaqt li `auto` jieħu d-dimensjonijiet u l-proporzjon tal-aspett tas-sors fil-limiti ta' LTX. |
| `preserve_original_video` |  | boolean | no | `false` |  | Modalità taż-żamma tal-vidjo oriġinali, disponibbli biss ma' `skip_control_preprocess`, `video_url`, u `control_video_url`. Diżattivata b'mod prestabbilit, iżżomm l-ipproċessar standard tal-kontroll; meta tiġi attivata, tibda l-ġenerazzjoni minn `video_url` filwaqt li żżomm il-gwida strutturali minn `control_video_url`. It-tneħħija tal-istorbju permezz ta' `strength` tistabbilixxi l-ammont miżmum, b'issettjar aktar baxx iżomm aktar pixels oriġinali. |
| `image_url` | `image` | string (image URL) \| null | no |  |  | Stil mhux obbligatorju ta' ankrar tal-immaġni jew identità tal-karattru bħala l-keyframe tal-ewwel frejm. |
| `mid_image_url` |  | string (image URL) \| null | no |  |  | Dehra mhux obbligatorja għall-ankrar tal-immaġni qrib in-nofs tal-klipp, li tissupplimenta l-keyframe inizjali `image_url`. Tgħin biex id-dehra ssegwi l-moviment tal-kamera minflok tinbidel; teħtieġ `image_url`. |
| `end_image_url` | `end_image` | string (image URL) \| null | no |  |  | Dehra mhux obbligatorja għall-ankrar tal-immaġni fl-aħħar frejm tal-klipp. Utli meta l-moviment tal-kamera jispiċċa f'post differenti mill-immaġni tal-bidu; teħtieġ `image_url`. |
| `video_strength` |  | number | no | `0.6` | 0 – 1 | Il-libertà li jinbidel il-moviment u l-istruttura mill-vidjo ta' referenza hija kkontrollata minn din is-saħħa tal-kundizzjonament: issettjar iżgħar jippermetti bidliet akbar. |
| `strength` |  | number | no | `1` | 0 – 1 | Kontroll tat-tneħħija tal-istorbju għat-teħid ta' kampjuni vidjo għal vidjo b'referenza, li l-effett tiegħu jiddependi fuq `preserve_original_video`. Meta dik il-modalità tkun mitfija, sempliċement tqassar l-iskeda tat-tneħħija tal-istorbju; meta tkun mixgħula, tikkontrolla t-trasformazzjoni tal-pixels tas-sors, fejn 1.0 jerġa' jiġġenera kollox u settings aktar baxxi jżommu aktar (pereżempju, 0.5 iżomm madwar 50%). |
| `num_frames` |  | integer | no | `121` | 9 – 481 | Għadd ta' frejms tal-output, soġġett għal baġit ta' stabbiltà IC-LoRA bbażat fuq ir-riżoluzzjoni immultiplikata bil-frejms. Rispons 422 ifisser li nqabeż dak il-baġit: naqqas ir-riżoluzzjoni jew `num_frames`. Il-baġit jippermetti madwar 150 frejm f'dimensjonijiet tal-klassi 720p u aktar f'daqsijiet iżgħar. |
| `resolution` |  | object {width, height} \| enum (string) | no | `auto` | `auto`, `square_hd`, `square`, `portrait_4_3`, `portrait_16_9`, `landscape_4_3`, `landscape_16_9` | Dimensjonijiet tal-vidjo tal-output, li jaffettwaw ukoll it-tul stabbli: daqsijiet iżgħar jippermettu aktar frejms, filwaqt li daqsijiet akbar inaqqsu l-massimu. L-istima integrata tal-kontroll iżżomm id-daqs qrib il-fluss tax-xogħol uffiċjali tal-kontroll; il-kontroll dirett permezz ta' `skip_control_preprocess` u `control_video_url` minflok jirrispetta dimensjonijiet espliċiti b'allinjament ta' 64px. Fil-modalità ta' kontroll dirett, `auto` jiret id-dimensjonijiet u l-proporzjon tal-aspett tas-sors fil-limiti ta' LTX. |
| `frames_per_second` |  | number | no | `24` | 1 – 60 | Rata tal-frejms tal-vidjo tal-output, imkejla fi frejms kull sekonda. |
| `num_inference_steps` |  | integer | no | `15` | 8 – 30 | Issettja kemm passi ta' inference għandhom jitħaddmu, sa 30; jekk tħallih kif inhu jintużaw 15. |
| `guidance_scale` |  | number | no | `1` | 1 – 20 | Aġġusta classifier-free guidance billi tuża din l-iskala; l-irfinar prestabbilit tagħha jimmira għal kwalità għolja u ġenerazzjoni mgħaġġla. |
| `generate_audio` |  | boolean | no | `true` |  | Toggle tat-track tal-awdjo għall-MP4 ritornat: mitfi jipproduċi fajl tal-vidjo biss, u mixgħul jinkludi l-awdjo. |
| `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 negattiv li jispeċifika x'għandha tevita l-ġenerazzjoni. |
| `seed` |  | integer \| null | no |  |  | Seed li jagħmel il-ġenerazzjoni riproduċibbli. L-issettjar tiegħu għal None jagħżel seed b’mod każwali. |
| `enable_prompt_expansion` |  | boolean | no | `true` |  | Jikkontrolla jekk l-espansjoni tal-prompt hijiex attivata. |
| `enable_safety_checker` |  | boolean | no | `true` |  | Jikkontrolla jekk il-verifika tas-sikurezza hijiex attivata. |
| `video_quality` |  | enum (string) | no | `high` | `low`, `medium`, `high`, `maximum` | Preset tal-kwalità applikat għall-vidjo tal-output. |
| `video_write_mode` |  | enum (string) | no | `balanced` | `fast`, `balanced`, `small` | Modalità tal-kitba għall-vidjo li jirriżulta. |
| `loras` |  | array of object {path, scale, transformer} | yes |  | ≤ 3 items | Żidiet LoRA għal LTX-2.3, kull waħda limitata għal 3 GB, b'massimu ta' 3 entrati. It-tagħbija ssir biss wara li d-downloader tar-reġistru sikur kontra SSRF jirkupra kull path. |
| `loras[].path` |  | string | yes |  | ≤ 2048 characters | URL HTTP(S) dirett għal fajl LoRA .safetensors ta' mhux aktar minn 3 GB. It-tagħbija tkun preċeduta mill-irkupru permezz ta' downloader sikur kontra SSRF. |
| `loras[].scale` |  | number | no | `1` | 0 – 2 | L-influwenza tal-LoRA fuq il-vidjo iġġenerat tiżdied hekk kif tiżdied din is-saħħa fil-medda 0.0–2.0. |
| `loras[].transformer` |  | enum (string) | no | `both` | `high`, `low`, `both` | Flag tal-għażla tat-transformer: 'both' huwa adattat għal kważi kull min juża LTX-2.3 għax il-mudell għandu transformer wieħed biss. Il-flag jeżisti biex jappoġġja arkitetturi futuri b'diversi transformers. |

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} | Vidjo prodott mill-mudell. |
| `seed` | integer | Żerriegħa attwali applikata waqt il-ġenerazzjoni. |
| `prompt` | string | Prompt tal-ġenerazzjoni, inkluża kwalunkwe espansjoni applikata qabel l-użu. |

## 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