# LTX-2.3 22B Video Trainer API

> Træner en LTX-2.3 22B-LoRA til brugerdefinerede videostile og effekter med valgfri lyd

Træner en LoRA på LTX-2.3 22B-modellen til brugerdefinerede stilarter og effekter fra et zip-arkiv med videoer eller billeder, helst 10 eller flere filer. `number_of_steps` går fra 100 til 6000 (standard 2000), `frame_rate` er som standard 25, og `first_frame_conditioning_p` er som standard 0.5. `with_audio` gennemtvinger eller deaktiverer lydtræning, og `generate_audio_in_validation` styrer lyd i forhåndsvisninger.

- 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/da/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 til et ZIP-arkiv med et datasæt, der udelukkende indeholder billeder eller udelukkende videoer; datasæt med blandede medier understøttes ikke. Sigt efter 10 filer eller flere, helst en større samling. Accepterede filtypenavne er .png, .jpg, .jpeg for billeder og .mp4, .mov, .avi, .mkv for videoer. Valgfrie billedteksts-filer kan ledsage medierne, hvor hver billedtekstfil navngives, så den matcher den tilknyttede mediefil. |
| `rank` |  | enum (integer) | no | `32` | `8`, `16`, `32`, `64`, `128` | LoRA-tilpasningsrang, der bytter øget hukommelsesforbrug for større kapacitet, når indstillingen øges. |
| `number_of_steps` |  | integer | no | `2000` | 100 – 6,000 | Samlet antal træningstrin. |
| `learning_rate` |  | number | no | `0.0002` | 0.000001 – 1 | Optimeringens læringsrate, der afvejer en mulig hastighedsforøgelse i træningen mod risikoen for overtilpasning, når den øges. |
| `number_of_frames` |  | integer | no | `89` | 9 – 121 | Antal frames i hver træningsprøve. Når antallet divideres med 8, skal resten være 1; eksempler er 1, 9, 17, 25, 33, 41, 49, 57, 65, 73, 81, 89, 97. |
| `frame_rate` |  | integer | no | `25` | 8 – 60 | Målvideoframefrekvens målt i frames per sekund. |
| `resolution` |  | enum (string) | no | `medium` | `low`, `medium`, `high` | Træningsopløsning. En højere opløsning øger hukommelseskravene. |
| `aspect_ratio` |  | enum (string) | no | `1:1` | `16:9`, `1:1`, `9:16` | Træningens størrelsesforhold. |
| `trigger_phrase` |  | string | no | `` |  | Aktiveringsudtryk for LoRA-stilen, indsat i begyndelsen af beskrivelserne under træning. |
| `auto_scale_input` |  | boolean | no | `false` |  | Automatisk videojustering, så den matcher den anmodede FPS og frameantal, når den aktiveres; billeddatasæt forbliver uændrede. |
| `split_input_into_scenes` |  | boolean | no | `true` |  | Scenedeling for videoer, der overskrider en varighedstærskel, aktiveret når værdien er true. |
| `split_input_duration_threshold` |  | number | no | `30` | 1 – 60 | Trigger for scenedeling angivet som en varighed i sekunder: kun videoer, der er længere end tærsklen, opdeles. |
| `debug_dataset` |  | boolean | no | `false` |  | Inspektionstilstand for præprocessering, der bruges til at kontrollere videoer, billeder og beskrivelser før en fuld træningskørsel. Aktivering får træneren til at returnere det behandlede træningsdatasæt i et arkiv, der kan downloades til manuel gennemgang. |
| `with_audio` |  | boolean \| null | no |  |  | Vælg True for at gennemtvinge lydtræning sammen med videotræning, eller False for at udelade lyd. Hvis indstillingen bevares på standardværdien None, vælges automatisk baseret på, om de leverede videoer indeholder lyd. |
| `audio_normalize` |  | boolean | no | `true` |  | Normalisering af spidsamplitude, anbefalet for at gøre lydniveauerne ensartede i hele datasættet ved at bringe spidserne til et fælles niveau. |
| `audio_preserve_pitch` |  | boolean | no | `true` |  | Bevarelse af tonehøjde, når lyd- og videolængder er forskellige: aktiveret bruger tidsstrækning eller -komprimering; deaktiveret bruger i stedet trimning eller udfyldning med stilhed. |
| `first_frame_conditioning_p` |  | number | no | `0.5` | 0 – 1 | Forbedr image-to-video-ydeevnen ved at øge, hvor ofte træningen bruger betingelse på første frame; denne værdi angiver sandsynligheden. |
| `validation` |  | array of object {prompt, image_url} | no | `[]` | ≤ 2 items | Træningsvalideringspromptliste, hvis input enten alle skal indeholde billeder eller alle skal udelade dem. |
| `validation[].prompt` |  | string | yes |  |  | Prompt, der bruges under validering. |
| `validation[].image_url` |  | string (image URL) \| null | no |  |  | Billede til image-to-video-validering, kun tilladt hvis alle andre valideringsinput også indeholder et billede. |
| `validation_negative_prompt` |  | string | no | `worst quality, inconsistent motion, blurry, jittery, distorted` |  | Negativ prompt, der anvendes under validering. |
| `validation_number_of_frames` |  | integer | no | `89` | 9 – 121 | Frameantal for hver valideringsvideo. |
| `validation_frame_rate` |  | integer | no | `25` | 8 – 60 | Målvideoframefrekvens under validering målt i frames per sekund. |
| `validation_resolution` |  | enum (string) | no | `high` | `low`, `medium`, `high` | Opløsning, der bruges under validering. |
| `validation_aspect_ratio` |  | enum (string) | no | `1:1` | `16:9`, `1:1`, `9:16` | Størrelsesforhold, der bruges under validering. |
| `stg_scale` |  | number | no | `1` | 0 – 3 | Skala for Spatio-Temporal Guidance (STG), hvor 1.0 anbefales, og 0.0 deaktiverer STG. |
| `generate_audio_in_validation` |  | boolean | no | `true` |  | Styrer, om valideringseksempler indeholder genereret lyd. |

## 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 til eventuelle tilgængelige valideringsvideoer. |
| `lora_file` | object {url, content_type, file_name, file_size} | URL til trænede LoRA-vægte i .safetensors-format. |
| `config_file` | object {url, content_type, file_name, file_size} | Konfiguration til opsætning af inferens-endpointet. |
| `debug_dataset` | object {url, content_type, file_name, file_size} \| null | Downloadbart fejlfindingsarkiv, der kun returneres for input med aktiveret `debug_dataset`; det indeholder det forbehandlede træningsdatasæt, inklusive afkodet lyd og 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