# LTX-2.3 22B Video Trainer API

> Nagsasanay ng LTX-2.3 22B LoRA para sa custom na estilo at effect ng video, na may opsyonal na audio

Nagsasanay ng LoRA sa LTX-2.3 22B modelo para sa mga custom na istilo at effect mula sa zip ng mga video o larawan, na pinakamainam kung 10 o higit pang file. Ang `number_of_steps` ay mula 100 hanggang 6000 (default 2000), default na 25 ang `frame_rate`, at default na 0.5 ang `first_frame_conditioning_p`. Pinipilit o dini-disable ng `with_audio` ang audio training, at kinokontrol ng `generate_audio_in_validation` ang audio sa mga preview.

- 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/fil/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 ng ZIP archive para sa dataset na eksklusibong naglalaman ng mga larawan o eksklusibong video; hindi sinusuportahan ang mixed media datasets. Layuning magkaroon ng 10 file o higit pa, mas mainam kung mas malaking koleksyon. Ang mga tinatanggap na extension ay .png, .jpg, .jpeg para sa mga larawan at .mp4, .mov, .avi, .mkv para sa mga video. Maaaring may kasamang opsyonal na caption text file ang media, na ang pangalan ng bawat caption file ay tumutugma sa kaugnay nitong media file. |
| `rank` |  | enum (integer) | no | `32` | `8`, `16`, `32`, `64`, `128` | LoRA adaptation rank, na ipinagpapalit ang mas mataas na memory consumption para sa mas malaking capacity habang tumataas ang setting. |
| `number_of_steps` |  | integer | no | `2000` | 100 – 6,000 | Kabuuang bilang ng training step. |
| `learning_rate` |  | number | no | `0.0002` | 0.000001 – 1 | Optimization learning rate, na nagbabalanse sa posibleng pagbilis ng training at panganib ng overfitting kapag tinaasan. |
| `number_of_frames` |  | integer | no | `89` | 9 – 121 | Bilang ng frame para sa bawat training sample. Kapag hinati ang bilang sa 8, dapat may remainder na 1; kabilang sa mga halimbawa ang 1, 9, 17, 25, 33, 41, 49, 57, 65, 73, 81, 89, 97. |
| `frame_rate` |  | integer | no | `25` | 8 – 60 | Target frame rate ng video, sinusukat sa frames per segundo. |
| `resolution` |  | enum (string) | no | `medium` | `low`, `medium`, `high` | Training resolution. Kapag tinaasan ang resolution, tumataas ang memory requirements. |
| `aspect_ratio` |  | enum (string) | no | `1:1` | `16:9`, `1:1`, `9:16` | Training aspect ratio. |
| `trigger_phrase` |  | string | no | `` |  | LoRA style activation phrase, na ipinapasok sa simula ng mga caption habang nagta-training. |
| `auto_scale_input` |  | boolean | no | `false` |  | Awtomatikong video adjustment upang tumugma sa hinihinging FPS at frame count kapag pinagana; hindi binabago ang larawan dataset. |
| `split_input_into_scenes` |  | boolean | no | `true` |  | Paghahati ng eksena para sa mga video na lumalagpas sa duration threshold, pinapagana kapag true. |
| `split_input_duration_threshold` |  | number | no | `30` | 1 – 60 | Trigger ng paghahati ng eksena na ipinapahayag bilang duration sa segundo: ang mga video lamang na mas mahaba sa threshold ang hinahati. |
| `debug_dataset` |  | boolean | no | `false` |  | Preprocessing inspection mode para suriin ang mga video, larawan, at caption bago ang buong training run. Kapag pinagana, ibinabalik ng trainer ang na-process na training dataset sa isang downloadable archive para sa manu-manong pagsusuri. |
| `with_audio` |  | boolean \| null | no |  |  | Piliin ang True upang pilitin ang audio training kasabay ng video training, o False upang ibukod ang audio. Kapag iniwan ang setting sa default nitong None, awtomatikong pinipili batay sa kung may audio ang mga ibinigay na video. |
| `audio_normalize` |  | boolean | no | `true` |  | Peak-amplitude normalization, inirerekomenda upang maging pare-pareho ang mga level ng audio sa buong dataset sa pamamagitan ng pagdadala ng mga peak sa iisang level. |
| `audio_preserve_pitch` |  | boolean | no | `true` |  | Pagpapanatili ng pitch kapag magkaiba ang haba ng audio at video: gumagamit ang enabled ng time stretching o compression; gumagamit naman ang disabled ng trimming o silence padding. |
| `first_frame_conditioning_p` |  | number | no | `0.5` | 0 – 1 | Pagbutihin ang image-to-video performance sa pamamagitan ng pagtaas ng dalas ng paggamit ng training sa first-frame conditioning; itinatakda ng value na ito ang probability na iyon. |
| `validation` |  | array of object {prompt, image_url} | no | `[]` | ≤ 2 items | Listahan ng training validation prompt, na ang mga input ay dapat lahat may kasamang mga larawan o lahat ay walang larawan. |
| `validation[].prompt` |  | string | yes |  |  | Prompt na ginagamit habang nagva-validation. |
| `validation[].image_url` |  | string (image URL) \| null | no |  |  | Larawan para sa image-to-video validation, pinapahintulutan lamang kung ang bawat iba pang validation input ay may kasama ring larawan. |
| `validation_negative_prompt` |  | string | no | `worst quality, inconsistent motion, blurry, jittery, distorted` |  | Negative prompt na ginagamit sa validation. |
| `validation_number_of_frames` |  | integer | no | `89` | 9 – 121 | Bilang ng frame para sa bawat validation video. |
| `validation_frame_rate` |  | integer | no | `25` | 8 – 60 | Target frame rate ng validation video, sinusukat sa frames per segundo. |
| `validation_resolution` |  | enum (string) | no | `high` | `low`, `medium`, `high` | Resolution na ginagamit habang nagva-validation. |
| `validation_aspect_ratio` |  | enum (string) | no | `1:1` | `16:9`, `1:1`, `9:16` | Aspect ratio na ginagamit habang nagva-validation. |
| `stg_scale` |  | number | no | `1` | 0 – 3 | Spatio-Temporal Guidance (STG) scale, kung saan inirerekomenda ang 1.0 at dini-disable ng 0.0 ang STG. |
| `generate_audio_in_validation` |  | boolean | no | `true` |  | Kinokontrol kung may kasamang nabuong audio ang validation samples. |

## 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 para sa anumang available na validation video. |
| `lora_file` | object {url, content_type, file_name, file_size} | URL para sa trained LoRA weights sa .safetensors format. |
| `config_file` | object {url, content_type, file_name, file_size} | Configuration para sa setup ng inference endpoint. |
| `debug_dataset` | object {url, content_type, file_name, file_size} \| null | Nada-download na debug archive na ibinabalik lamang para sa mga input na naka-enable ang `debug_dataset`; naglalaman ito ng na-preprocess na training dataset, kabilang ang decoded audio at 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.com/v1/models/ltx23-video-trainer