# LTX-2.3 22B Video Trainer API

> Sikavel LTX-2.3 22B LoRA vaš custom video-stilura thaj efekta, opcionale audio-sa

Sikavel LoRA pe LTX-2.3 22B modelos vaš custom stilura thaj efekta andar zip videourendar vaj slikarendar, idealno 10 vaj buter fajlura. `number_of_steps` si 100 te 6000 (default 2000), `frame_rate` si defaultes 25, thaj `first_frame_conditioning_p` si defaultes 0.5. `with_audio` zorarel vaj phandel audio-trening, thaj `generate_audio_in_validation` kontrolirinel audio ande preview-ura.

- 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.ru/v1/run/ltx23-video-trainer`
- Quote: `POST https://api.doitong.ru/v1/quote/ltx23-video-trainer`
- Docs page: https://doitong.com/rom/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.ru/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 ZIP archive datasetosko savo si numa kipenca vaj numa videosar; mixed media datasets na si supportime. Cielos 10 fajlo vaj maj but, maj šukar baro kolekcia. Acceptime extensions si .png, .jpg, .jpeg kipenge thaj .mp4, .mov, .avi, .mkv videoske. Optional caption tekstoske fajlo šaj aven khetane mediaha, sako caption fajlo la navaha lake phandime media fajloske. |
| `rank` |  | enum (integer) | no | `32` | `8`, `16`, `32`, `64`, `128` | LoRA adaptation rank, savo lel maj-baro memory thaj del maj-bari capacity kana vazdel pes. |
| `number_of_steps` |  | integer | no | `2000` | 100 – 6,000 | Sa e training steps-enge gind. |
| `learning_rate` |  | number | no | `0.0002` | 0.000001 – 1 | Optimization learning rate, balancirinel jek possible speedup ande traininga riskoha overfittingesko kana bararel. |
| `number_of_frames` |  | integer | no | `89` | 9 – 121 | Kadro-gind sako training sample-oske. Te del o gind pe 8, o remainder si 1; exempelura si 1, 9, 17, 25, 33, 41, 49, 57, 65, 73, 81, 89, 97. |
| `frame_rate` |  | integer | no | `25` | 8 – 60 | Ciljno frekvencija e videokadrenge, merime ande kadra pe sekunda. |
| `resolution` |  | enum (string) | no | `medium` | `low`, `medium`, `high` | Training rezolucija. Maj-bari rezolucija mangel maj-baro memory. |
| `aspect_ratio` |  | enum (string) | no | `1:1` | `16:9`, `1:1`, `9:16` | Training aspect ratio. |
| `trigger_phrase` |  | string | no | `` |  | LoRA stiloski activation fraza, thovi pes andro captionsko starto andro training. |
| `auto_scale_input` |  | boolean | no | `false` |  | Automatikano video adjustment te jakharel e manglini FPS thaj kadro-gind kana si aktivno; kipo datasets ačhen bi paruvipen. |
| `split_input_into_scenes` |  | boolean | no | `true` |  | Scene splitting videoske save našen durata threshold, aktivno kana si true. |
| `split_input_duration_threshold` |  | number | no | `30` | 1 – 60 | Scene-splitting trigger, sikavdo durata andro sekunda: numa videona maj-bare sar threshold si split-ime. |
| `debug_dataset` |  | boolean | no | `false` |  | Preprocessing inspection modo vašo video, kipo thaj caption proveripen angleder full training run. Kana si aktivno, trainer del processed training dataset andro download-ime archive vašo manušikano dikhipen. |
| `with_audio` |  | boolean \| null | no |  |  | Alosar True vaj te zorarel audio training khetane video traininga, vaj False vaj te čhivel avri audio. Kana mukhes settinga standardno, None kerel o alosaripen automaticki pala oda te si audio ande dine videos. |
| `audio_normalize` |  | boolean | no | `true` |  | Peak-amplitude normalization, preporučime vaj audio levels te aven jekhajekh ande sasto dataset, anindoj o peaks ande common level. |
| `audio_preserve_pitch` |  | boolean | no | `true` |  | Pitch preservation kana audio thaj video si aver length: enabled kerel time stretching vaj compression; disabled kerel trimming vaj silence padding. |
| `first_frame_conditioning_p` |  | number | no | `0.5` | 0 – 1 | Šukararel image-to-video performance te bararel sar barvales training astarel first-frame conditioning; kadava value si oda probability. |
| `validation` |  | array of object {prompt, image_url} | no | `[]` | ≤ 2 items | Training validation promptoski lista, savi inputosa trubun te saven vaj savoro kipo inkludinel vaj savoro len na inkludinel. |
| `validation[].prompt` |  | string | yes |  |  | Prompto savo si lavdo andro validation. |
| `validation[].image_url` |  | string (image URL) \| null | no |  |  | Kipo vaši validacija kipo-ando-video, mukhlo numa te sako aver validacijako inputo vi astarel jekh kipo. |
| `validation_negative_prompt` |  | string | no | `worst quality, inconsistent motion, blurry, jittery, distorted` |  | Negative prompto dine ande validation. |
| `validation_number_of_frames` |  | integer | no | `89` | 9 – 121 | Kadro-gind sako validation videoske. |
| `validation_frame_rate` |  | integer | no | `25` | 8 – 60 | Ciljno frekvencija e validacijake videokadrenge, merime ande kadra pe sekunda. |
| `validation_resolution` |  | enum (string) | no | `high` | `low`, `medium`, `high` | Rezolucija savi si lavdi andro validation. |
| `validation_aspect_ratio` |  | enum (string) | no | `1:1` | `16:9`, `1:1`, `9:16` | Aspect ratio savo si lavdo andro validation. |
| `stg_scale` |  | number | no | `1` | 0 – 3 | Spatio-Temporal Guidance (STG) skala, rekomendime 1.0; 0.0 zaačharel STG. |
| `generate_audio_in_validation` |  | boolean | no | `true` |  | Kontrolinel te len li validation samples generated audio. |

## 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.ru/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.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/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.ru/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.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": "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.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} \| null | URL kon varesave validation videoske. |
| `lora_file` | object {url, content_type, file_name, file_size} | URL trained LoRA weights-enge andro .safetensors formato. |
| `config_file` | object {url, content_type, file_name, file_size} | Konfiguracija vašo inference endpoint setup. |
| `debug_dataset` | object {url, content_type, file_name, file_size} \| null | Downloadable debug archive sikavdo numa inputonge save `debug_dataset` si enabled; ande leste si o preprocessed training dataset, save decoded audio thaj video. |

## 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.ru/v1/models/ltx23-video-trainer