# LTX 2.3 22B API

> Uzalishaji wa video ya marejeo wenye LoRA maalum kupitia orodha inayohitajika ya `loras`

Hutumia `video_url` ya marejeo na `prompt`, pamoja na orodha inayohitajika ya `loras` za LoRA maalum. `audio_url` ya hiari hubadilisha sauti, na `image_url` na `end_image_url` huweka fremu za kwanza na za mwisho. Urefu hufuata video ya marejeo `match_video_length` ikiwa imewashwa, au `num_frames` (9 hadi 481) vinginevyo.

- Model id: `ltx-2.3-22b/reference-video-to-video/lora`
- Made by: Lightricks
- Category: Video to Video
- Output: video
- Price per megapixel of your output video: $0.00181 / megapixel of output video (cheapest run $0.002 (2 API credits))
- Run: `POST https://api.doitong.ru/v1/run/ltx-2.3-22b/reference-video-to-video/lora`
- Quote: `POST https://api.doitong.ru/v1/quote/ltx-2.3-22b/reference-video-to-video/lora`
- Docs page: https://doitong.com/sw/developers/models/ltx-2.3-22b/reference-video-to-video/lora

## Pricing

Price: **$0.00181 / 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 $0.51 = 510 API credits (282 MP output video × $0.001805).

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/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 |  |  | Kidokezo kinachotumika kama msingi wa uzalishaji wa video. |
| `video_url` | `video` | string (video URL) | yes |  |  | URL inayotambua video ya marejeleo. |
| `audio_url` | `audio` | string (audio URL) \| null | no |  |  | URL ya hiari ya sauti inayotoa wimbo wa sauti wa video. Isipotolewa, sauti kutoka video chanzo hutumika ikiwa ipo. |
| `image_url` | `image` | string (image URL) \| null | no |  |  | URL ya hiari ya picha inayobainisha fremu ya mwanzo ya video. |
| `end_image_url` | `end_image` | string (image URL) \| null | no |  |  | URL ya picha inayobainisha fremu ya mwisho ya video. |
| `match_video_length` |  | boolean | no | `true` |  | Hali ya uteuzi wa idadi ya fremu: ikiwa imezimwa hutumia `num_frames`, huku ikiwa imewashwa ikikokotoa idadi kwa kutumia FPS na muda wa video. |
| `num_frames` |  | integer | no | `121` | 9 – 481 | Idadi ya fremu za tokeo lililozalishwa. |
| `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` | Vipimo vya video iliyozalishwa. |
| `generate_audio` |  | boolean | no | `true` |  | Hudhibiti ikiwa video itajumuisha sauti iliyozalishwa. |
| `use_multiscale` |  | boolean | no | `true` |  | Kigeuzi cha uzalishaji wa mizani mingi kwa mshikamano na maelezo bora. Kwa True, video ndogo ya awali huongoza uzalishaji wa pili ambao ukubwa wake unafikia au kuzidi vipimo vilivyoombwa. |
| `match_input_fps` |  | boolean | no | `true` |  | Ubadilishaji wa kiwango cha fremu za tokeo unaobadilisha FPS lengwa chaguomsingi na FPS ya video chanzo unapowashwa. |
| `fps` |  | number | no | `24` | 1 – 60 | Kasi ya fremu ya video ya tokeo, iliyopimwa kwa fremu kwa sekunde. |
| `num_inference_steps` |  | integer | no | `40` | 8 – 50 | Idadi ya hatua za uelekezaji zilizotekelezwa. |
| `video_cfg_scale` |  | number | no | `3` | 1 – 20 | Mpangilio wa mwongozo wa video: uinue kwa mshikamano na umakini zaidi katika maudhui yaliyozalishwa. Hutumia mwongozo usio na classifier (CFG). |
| `video_stg_scale` |  | number | no | `0` | 0 – 20 | Hudhibiti mshikamano na umakini wa video kupitia kipimo cha Spatiotemporal Guidance (STG); ongeza mpangilio huu ili kuimarisha sifa zote mbili. |
| `video_rescaling_scale` |  | number | no | `0.7` | 0 – 1 | Marekebisho ya kuongeza au kupunguza video kwa kusawazisha mwongozo usio na classifier na mwongozo wa spatiotemporal kama uwiano. |
| `video_modality_scale` |  | number | no | `3` | 0 – 10 | Marekebisho ya modality ya video kwa kusawazisha michango ya video na sauti kama uwiano. |
| `audio_cfg_scale` |  | number | no | `7` | 1 – 20 | Mpangilio wa mwongozo wa sauti: uinue kwa mshikamano na umakini zaidi katika maudhui yaliyozalishwa. Hutumia mwongozo usio na classifier (CFG). |
| `audio_stg_scale` |  | number | no | `0` | 0 – 20 | Hudhibiti mshikamano na umakini wa sauti kupitia kipimo cha Spatiotemporal Guidance (STG); ongeza mpangilio huu ili kuimarisha sifa zote mbili. |
| `audio_rescaling_scale` |  | number | no | `0.7` | 0 – 1 | Marekebisho ya kuongeza au kupunguza sauti kwa kusawazisha mwongozo usio na classifier na mwongozo wa spatiotemporal kama uwiano. |
| `audio_modality_scale` |  | number | no | `3` | 0 – 10 | Marekebisho ya modality ya sauti kwa kusawazisha michango ya video na sauti kama uwiano. |
| `gradient_estimation_gamma` |  | number | no | `2` | 0 – 10 | Mpangilio wa makadirio ya gradient ya kuondoa kelele: 0 huzima makadirio; vinginevyo, thamani hubainisha gamma. |
| `use_restart_sampling` |  | boolean | no | `false` |  | Kigeuzi cha kuanza upya sampuli kwa ubora bora wa video: kukiwasha huongeza kelele kidogo katika kila hatua ya kuondoa kelele. |
| `scheduler` |  | enum (string) | no | `ltx2` | `ltx2`, `linear_quadratic`, `beta` | Uteuzi wa scheduler. |
| `acceleration` |  | enum (string) | no | `regular` | `none`, `regular`, `high`, `full` | Kiwango cha kuongeza kasi kinachotumika kwenye uchakataji. |
| `camera_lora` |  | enum (string) | no | `none` | `dolly_in`, `dolly_out`, `dolly_left`, `dolly_right`, `jib_up`, `jib_down`, `static`, `none` | Uteuzi wa Camera LoRA kwa kudhibiti mwendo katika video iliyozalishwa kwa usahihi zaidi kuliko vidokezo vya mwendo wa kamera pekee. |
| `camera_lora_scale` |  | number | no | `1` | 0 – 1 | Nguvu ya Camera LoRA kwa kudhibiti mwendo katika video iliyozalishwa kwa usahihi zaidi kuliko vidokezo vya mwendo wa kamera pekee. |
| `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` |  | Kidokezo hasi kinachotumika wakati wa uzalishaji wa video. |
| `seed` |  | integer \| null | no |  |  | Thamani ya mbegu inayoanzisha uzalishaji wa nambari nasibu. |
| `enable_prompt_expansion` |  | boolean | no | `true` |  | Hudhibiti ikiwa upanuzi wa kidokezo umewashwa. |
| `enable_safety_checker` |  | boolean | no | `true` |  | Hudhibiti ikiwa ukaguzi wa usalama umewashwa. |
| `video_output_type` |  | enum (string) | no | `X264 (.mp4)` | `X264 (.mp4)`, `VP9 (.webm)`, `PRORES4444 (.mov)`, `GIF (.gif)` | Aina ya tokeo la video inayotokana. |
| `video_quality` |  | enum (string) | no | `high` | `low`, `medium`, `high`, `maximum` | Kiwango cha ubora wa video inayotokana. |
| `video_write_mode` |  | enum (string) | no | `balanced` | `fast`, `balanced`, `small` | Hali ya kuandika ya video inayotokana. |
| `loras` |  | array of object {path, weight_name, scale} | yes |  |  | Uteuzi wa LoRA kwa uzalishaji. |
| `loras[].path` |  | string | yes |  |  | Mahali pa uzani wa LoRA, palipotolewa kama URL au kitambulisho cha hazina ya HuggingFace katika muundo wa owner/repo. |
| `loras[].weight_name` |  | string \| null | no |  |  | Jina la uzani wa LoRA kwa kuchagua kati ya uzani wengi katika hazina ya HuggingFace; ni hazina zilizo na uzani wengi pekee zinahitaji hii. Mpangilio huu hauna athari isipokuwa `path` itambue hazina ya HuggingFace. |
| `loras[].scale` |  | number | no | `1` | 0 – 4 | Kipengele cha kuongeza/kupunguza ukubwa kinachotumika kwenye LoRA, kuanzia 0.0 hadi 4.0. |
| `distill_lora_first_pass_scale` |  | number | no | `0.2` | 0 – 1 | Dhibiti kuongeza au kupunguza kwa distill LoRA ya pass ya kwanza, ukitumia 0 kuizima. |
| `distill_lora_second_pass_scale` |  | number | no | `0.5` | 0 – 1 | Dhibiti kuongeza au kupunguza kwa distill LoRA kwa kila pass baada ya ya kwanza. |
| `video_strength` |  | number | no | `1` | 0 – 1 | Uhuru wa kubadilisha maudhui ya video hudhibitiwa na nguvu hii ya conditioning: mipangilio midogo huipa modeli uhuru zaidi. |
| `audio_strength` |  | number | no | `1` | 0 – 1 | Uhuru wa kubadilisha maudhui ya sauti hudhibitiwa na nguvu hii ya conditioning: mipangilio midogo huipa modeli uhuru zaidi. |
| `preprocessor` |  | enum (string) | no | `none` | `depth`, `canny`, `pose`, `none` | Preprocessor inayotumika wakati wa uzalishaji. |
| `ic_lora_type` |  | enum (string) | no | `union` | `match_preprocessor`, `union`, `detailer`, `none` | Tofauti ya IC LoRA inayotumika wakati wa uzalishaji. |

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/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/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/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/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/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": 510,
    "usd": "0.51",
    "charged": 510,
    "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} | Video iliyozalishwa na modeli. |
| `seed` | integer | Thamani ya seed inayotumika kuanzisha uzalishaji wa nambari nasibu. |
| `prompt` | string | Kidokezo kinachotumika kuongoza uzalishaji. |

## 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 · 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 · Reference Video to Video](https://doitong.com/developers/models/ltx-2.3-22b/reference-video-to-video.md) (`ltx-2.3-22b/reference-video-to-video`): $0.00161 / 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/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/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/reference-video-to-video/lora