# LTX-2.3 22B Video Trainer API

> Hufunza LoRA ya LTX-2.3 22B kwa mitindo na athari maalum za video, ikiwa na sauti ya hiari

Hufunza LoRA kwenye modeli ya LTX-2.3 22B kwa mitindo na athari maalum kutoka zip ya video au picha, ikiwezekana ikiwa na faili 10 au zaidi. `number_of_steps` ni 100 hadi 6000 (chaguomsingi 2000), `frame_rate` ni 25 kwa chaguomsingi, na `first_frame_conditioning_p` ni 0.5 kwa chaguomsingi. `with_audio` hulazimisha au kuzima mafunzo ya sauti, na `generate_audio_in_validation` hudhibiti sauti kwenye hakiki.

- Model id: `ltx23-video-trainer`
- Made by: Lightricks
- Category: Training
- Output: file
- Price: $0.0048 / step (cheapest run $9.60 (9600 API credits))
- Run: `POST https://api.doitong.com/v1/run/ltx23-video-trainer`
- Quote: `POST https://api.doitong.com/v1/quote/ltx23-video-trainer`
- Docs page: https://doitong.com/sw/developers/models/ltx23-video-trainer

## Pricing

Price: **$0.0048 / step**. Billed per training step (`number_of_steps`).

The full example input below costs $9.60 = 9600 API credits (2000 steps × 4.8 API credits).

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/ltx23-video-trainer` 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

| Parameter | Canonical name | Type | Required | Default | Allowed values / range | Description |
|---|---|---|---|---|---|---|
| `training_data_url` |  | string | yes |  |  | URL ya kumbukumbu ya ZIP ya seti ya data iliyo na picha pekee au video pekee; seti za data zenye midia mchanganyiko hazitumiki. Lenga faili 10 au zaidi, ikiwezekana mkusanyo mkubwa zaidi. Viendelezi vinavyokubalika ni .png, .jpg, .jpeg kwa picha na .mp4, .mov, .avi, .mkv kwa video. Faili za hiari za maandishi ya maelezo zinaweza kuambatana na midia, kila faili ikiwa na jina linalolingana na faili yake ya midia. |
| `rank` |  | enum (integer) | no | `32` | `8`, `16`, `32`, `64`, `128` | Daraja la urekebishaji la LoRA, linalobadilisha matumizi makubwa ya kumbukumbu kwa uwezo mkubwa zaidi kadiri mpangilio unavyoongezeka. |
| `number_of_steps` |  | integer | no | `2000` | 100 – 6,000 | Jumla ya idadi ya hatua za mafunzo. |
| `learning_rate` |  | number | no | `0.0002` | 0.000001 – 1 | Kiwango cha kujifunza cha uboreshaji, kinachosawazisha ongezeko linalowezekana la kasi ya mafunzo dhidi ya hatari ya overfitting kinapoongezwa. |
| `number_of_frames` |  | integer | no | `89` | 9 – 121 | Idadi ya fremu kwa kila sampuli ya mafunzo. Kugawa idadi hiyo kwa 8 lazima kuache salio la 1; mifano ni 1, 9, 17, 25, 33, 41, 49, 57, 65, 73, 81, 89, 97. |
| `frame_rate` |  | integer | no | `25` | 8 – 60 | Kasi lengwa ya fremu ya video, inayopimwa kwa fremu kwa sekunde. |
| `resolution` |  | enum (string) | no | `medium` | `low`, `medium`, `high` | Mwonekano wa mafunzo. Kuongeza mwonekano huongeza mahitaji ya kumbukumbu. |
| `aspect_ratio` |  | enum (string) | no | `1:1` | `16:9`, `1:1`, `9:16` | Uwiano wa mafunzo. |
| `trigger_phrase` |  | string | no | `` |  | Kauli ya uanzishaji wa mtindo wa LoRA, inayowekwa mwanzoni mwa manukuu wakati wa mafunzo. |
| `auto_scale_input` |  | boolean | no | `false` |  | Marekebisho ya video kiotomatiki ili yalingane na FPS na idadi ya fremu iliyoombwa yanapowashwa; seti za data za picha hazibadilishwi. |
| `split_input_into_scenes` |  | boolean | no | `true` |  | Ugawaji wa mandhari kwa video zinazozidi kizingiti cha muda, ukiwashwa wakati true. |
| `split_input_duration_threshold` |  | number | no | `30` | 1 – 60 | Kichocheo cha kugawa mandhari kinachoonyeshwa kama muda kwa sekunde: video ndefu kuliko kizingiti pekee ndizo hugawanywa. |
| `debug_dataset` |  | boolean | no | `false` |  | Hali ya ukaguzi wa uchakataji awali kwa kuangalia video, picha na manukuu kabla ya uendeshaji kamili wa mafunzo. Kuiwasha humfanya mkufunzi arudishe seti ya data ya mafunzo iliyochakatwa katika jalada linaloweza kupakuliwa kwa ukaguzi wa mikono. |
| `with_audio` |  | boolean \| null | no |  |  | Chagua True ili kulazimisha mafunzo ya sauti pamoja na mafunzo ya video, au False kuondoa sauti. Kuacha mpangilio kwenye chaguo lake chaguomsingi, None, hufanya chaguo liwe la kiotomatiki kulingana na kama video zilizotolewa zina sauti. |
| `audio_normalize` |  | boolean | no | `true` |  | Urekebishaji wa amplitude ya kilele, unaopendekezwa ili kufanya viwango vya sauti vilingane katika seti yote ya data kwa kuleta vilele kwenye kiwango cha pamoja. |
| `audio_preserve_pitch` |  | boolean | no | `true` |  | Uhifadhi wa toni wakati urefu wa sauti na video unatofautiana: ukiwashwa hutumia kunyoosha au kubana muda; ukiwa umezimwa hutumia kukata au kujaza ukimya. |
| `first_frame_conditioning_p` |  | number | no | `0.5` | 0 – 1 | Boresha utendaji wa image-to-video kwa kuongeza mara ambazo mafunzo hutumia masharti ya fremu ya kwanza; thamani hii huweka uwezekano huo. |
| `validation` |  | array of object {prompt, image_url} | no | `[]` | ≤ 2 items | Orodha ya vidokezo vya uthibitishaji wa mafunzo, ambayo maingizo yake lazima yote yawe na picha au yote yasiwe nazo. |
| `validation[].prompt` |  | string | yes |  |  | Kidokezo kinachotumiwa wakati wa uthibitishaji. |
| `validation[].image_url` |  | string (image URL) \| null | no |  |  | Picha ya uthibitishaji wa image-to-video, inayoruhusiwa tu ikiwa kila ingizo jingine la uthibitishaji pia lina picha. |
| `validation_negative_prompt` |  | string | no | `worst quality, inconsistent motion, blurry, jittery, distorted` |  | Kidokezo hasi kinachotumika wakati wa uthibitishaji. |
| `validation_number_of_frames` |  | integer | no | `89` | 9 – 121 | Idadi ya fremu kwa kila video ya uthibitishaji. |
| `validation_frame_rate` |  | integer | no | `25` | 8 – 60 | Kasi lengwa ya fremu ya video ya uthibitishaji, inayopimwa kwa fremu kwa sekunde. |
| `validation_resolution` |  | enum (string) | no | `high` | `low`, `medium`, `high` | Mwonekano unaotumiwa wakati wa uthibitishaji. |
| `validation_aspect_ratio` |  | enum (string) | no | `1:1` | `16:9`, `1:1`, `9:16` | Uwiano unaotumiwa wakati wa uthibitishaji. |
| `stg_scale` |  | number | no | `1` | 0 – 3 | Kipimo cha Mwongozo wa Anga na Muda (STG), ambapo 1.0 inapendekezwa na 0.0 huzima STG. |
| `generate_audio_in_validation` |  | boolean | no | `true` |  | Hudhibiti ikiwa sampuli za uthibitishaji zinajumuisha sauti iliyozalishwa. |

## Example input

Required parameters only:

```json
{
  "training_data_url": "https://example.com/your-file.zip"
}
```

A fuller example:

```json
{
  "training_data_url": "https://example.com/your-file.zip"
}
```

## 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/ltx23-video-trainer?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "training_data_url": "https://example.com/your-file.zip"
  }'

# 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/ltx23-video-trainer?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "training_data_url": "https://example.com/your-file.zip"
  }),
});
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 = {
    "training_data_url": "https://example.com/your-file.zip",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/ltx23-video-trainer", 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": "ltx23-video-trainer",
      "input": {
        "training_data_url": "https://example.com/your-file.zip"
      },
      "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": "ltx23-video-trainer",
  "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": 9600,
    "usd": "9.60",
    "charged": 9600,
    "refunded": 0
  },
  "input": {
    "training_data_url": "https://example.com/your-file.zip"
  },
  "output": {
    "video": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_name": "0-output.jpeg",
      "file_size": 1843200
    },
    "lora_file": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_name": "0-output.jpeg",
      "file_size": 1843200
    },
    "config_file": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_name": "0-output.jpeg",
      "file_size": 1843200
    },
    "debug_dataset": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_name": "0-output.jpeg",
      "file_size": 1843200
    }
  },
  "outputs": [
    {
      "type": "file",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_size": 1843200,
      "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} \| null | URL ya video zozote za uthibitishaji zinazopatikana. |
| `lora_file` | object {url, content_type, file_name, file_size} | URL ya uzito wa LoRA uliofunzwa katika umbizo la .safetensors. |
| `config_file` | object {url, content_type, file_name, file_size} | Usanidi wa kuweka endpoint ya uelekezaji. |
| `debug_dataset` | object {url, content_type, file_name, file_size} \| null | Kumbukumbu ya utatuzi inayoweza kupakuliwa, inayorejeshwa tu kwa maingizo yenye `debug_dataset` iliyowashwa; ina seti ya data ya mafunzo iliyochakatwa awali, ikijumuisha sauti na video zilizofasiriwa. |

## Related models

- [LTX 2.3 Trainer (V2) - Audio Inpainting](https://doitong.com/developers/models/ltx23-trainer-v2/audio-inpaint.md) (`ltx23-trainer-v2/audio-inpaint`): $0.0023 / step
- [LTX 2.3 Trainer (V2) - Audio+Video Reference IC-LoRA](https://doitong.com/developers/models/ltx23-trainer-v2/ic-lora/av2av.md) (`ltx23-trainer-v2/ic-lora/av2av`): $0.0068 / step
- [LTX 2.3 Trainer (V2) - Audio+Video Reference Transformation](https://doitong.com/developers/models/ltx23-trainer-v2/av2av.md) (`ltx23-trainer-v2/av2av`): $0.0068 / step
- [LTX 2.3 Trainer (V2) - Audio-to-Audio](https://doitong.com/developers/models/ltx23-trainer-v2/a2a.md) (`ltx23-trainer-v2/a2a`): $0.0023 / step
- [LTX 2.3 Trainer (V2) - Audio-to-Audio IC-LoRA](https://doitong.com/developers/models/ltx23-trainer-v2/ic-lora/a2a.md) (`ltx23-trainer-v2/ic-lora/a2a`): $0.0023 / step
- [LTX 2.3 Trainer (V2) - Audio-to-Video](https://doitong.com/developers/models/ltx23-trainer-v2/a2v.md) (`ltx23-trainer-v2/a2v`): $0.006 / step
- [LTX 2.3 Trainer (V2) - Backward Audio Extension](https://doitong.com/developers/models/ltx23-trainer-v2/audio-extend-suffix.md) (`ltx23-trainer-v2/audio-extend-suffix`): $0.0023 / step
- [LTX 2.3 Trainer (V2) - Backward Video Extension](https://doitong.com/developers/models/ltx23-trainer-v2/extend-suffix.md) (`ltx23-trainer-v2/extend-suffix`): $0.0061 / step

## Links

- HTML page: https://doitong.com/developers/models/ltx23-video-trainer
- 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=ltx23-video-trainer
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.com/v1/models/ltx23-video-trainer