# LTX-2.3 22B Video Trainer API

> Trèanaichidh e LoRA LTX-2.3 22B airson stoidhlichean agus buaidhean bhidio gnàthaichte, le fuaim roghainneil

Trèanaichidh e LoRA air a’ mhodail LTX-2.3 22B airson stoidhlichean agus buaidhean gnàthaichte bho zip de bhidiothan no ìomhaighean, le 10 no barrachd fhaidhlichean mas fheàrr. Tha `number_of_steps` eadar 100 agus 6000 (àbhaisteach 2000), ’s e 25 an àbhaist airson `frame_rate`, agus ’s e 0.5 an àbhaist airson `first_frame_conditioning_p`. Bidh `with_audio` a’ sparradh no a’ cur à comas trèanadh fuaime, agus bidh `generate_audio_in_validation` a’ riaghladh fuaim ann an ro-sheallaidhean.

- 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/gd/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 tasglann ZIP airson seata-dàta anns a bheil ìomhaighean a-mhàin no bhideothan a-mhàin; chan eil seataichean-dàta le meadhanan measgaichte a’ faighinn taic. Feuch ri 10 faidhlichean no barrachd a chleachdadh, agus cruinneachadh nas motha mas fheàrr. Is iad na leudachain ris an gabhar .png, .jpg, .jpeg airson ìomhaighean agus .mp4, .mov, .avi, .mkv airson bhideothan. Faodaidh faidhlichean teacsa caption roghainneil a bhith còmhla ris na meadhanan, le gach faidhle caption air ainmeachadh gus a bhith a’ maidseadh an fhaidhle mheadhanan co-cheangailte ris. |
| `rank` |  | enum (integer) | no | `32` | `8`, `16`, `32`, `64`, `128` | Rang atharrachaidh LoRA, ag iomlaid barrachd caitheamh cuimhne airson comas nas motha mar a dh’èireas an suidheachadh. |
| `number_of_steps` |  | integer | no | `2000` | 100 – 6,000 | Àireamh iomlan de cheumannan trèanaidh. |
| `learning_rate` |  | number | no | `0.0002` | 0.000001 – 1 | Ìre ionnsachaidh optimization, a’ cothromachadh luathachadh comasach san trèanadh an aghaidh cunnart cus-fhreagarrachd nuair a thèid a mheudachadh. |
| `number_of_frames` |  | integer | no | `89` | 9 – 121 | Àireamh frèam airson gach sampall trèanaidh. Feumaidh roinneadh na h-àireimh le 8 còrr de 1 fhàgail; tha eisimpleirean a’ gabhail a-steach 1, 9, 17, 25, 33, 41, 49, 57, 65, 73, 81, 89, 97. |
| `frame_rate` |  | integer | no | `25` | 8 – 60 | Ìre frèama targaid a’ bhidio, air a thomhas ann am frèaman gach diog. |
| `resolution` |  | enum (string) | no | `medium` | `low`, `medium`, `high` | Dùmhlachd-bhreacaidh trèanaidh. Le bhith ag àrdachadh na dùmhlachd-bhreacaidh àrdaichear riatanasan cuimhne. |
| `aspect_ratio` |  | enum (string) | no | `1:1` | `16:9`, `1:1`, `9:16` | Co-mheas-taobhan trèanaidh. |
| `trigger_phrase` |  | string | no | `` |  | Abairt gnìomhachaidh stoidhle LoRA, air a cur aig toiseach nan captions rè trèanaidh. |
| `auto_scale_input` |  | boolean | no | `false` |  | Atharrachadh bhidio fèin-obrachail gus a bhith a rèir an FPS agus àireamh frèam a chaidh iarraidh nuair a tha e air; bidh seataichean-dàta ìomhaighe gun atharrachadh. |
| `split_input_into_scenes` |  | boolean | no | `true` |  | Sgaradh sheallaidhean airson bhidiothan a tha nas fhaide na stairsneach faid, air a chur an comas nuair a tha e fìor. |
| `split_input_duration_threshold` |  | number | no | `30` | 1 – 60 | Trigger sgaradh sheallaidhean air a chur an cèill mar fhad ann an diogan: cha tèid ach bhidiothan nas fhaide na an stairsneach a sgaradh. |
| `debug_dataset` |  | boolean | no | `false` |  | Modh sgrùdaidh ro-ghiullachd airson bhidiothan, ìomhaighean agus captions a dhearbhadh ro ruith trèanaidh iomlan. Le bhith ga chur an comas tillidh an trèanair an seata-dàta trèanaidh giullaichte ann an tasglann a ghabhas luchdadh a-nuas airson sgrùdadh làimhe. |
| `with_audio` |  | boolean \| null | no |  |  | Tagh True gus trèanadh claisneachd a sparradh còmhla ri trèanadh bhidio, no False gus claisneachd a chur às. Ma dh’fhàgas tu an suidheachadh aig a’ bhun-roghainn aige, None, thèid an roghainn a dhèanamh gu fèin-obrachail a rèir a bheil claisneachd anns na bhideothan a chaidh a sholarachadh. |
| `audio_normalize` |  | boolean | no | `true` |  | Normalachadh amplitude stùca, air a mholadh gus ìrean claisneachd a dhèanamh cunbhalach air feadh an t-seata-dàta le bhith a’ toirt nan stùcan gu ìre chumanta. |
| `audio_preserve_pitch` |  | boolean | no | `true` |  | Glèidheadh pitch nuair a tha faid claisneachd is bhidio eadar-dhealaichte: bidh comasachadh a’ cleachdadh sìneadh no teannachadh ùine; bidh cur à comas a’ cleachdadh bearradh no pleadhag sàmhach na àite. |
| `first_frame_conditioning_p` |  | number | no | `0.5` | 0 – 1 | Leasaich coileanadh image-to-video le bhith a’ meudachadh cho tric ’s a chleachdas trèanadh suidheachadh a’ chiad fhrèam; tha an luach seo a’ suidheachadh na coltachd sin. |
| `validation` |  | array of object {prompt, image_url} | no | `[]` | ≤ 2 items | Liosta de phromptaichean dearbhaidh trèanaidh; feumaidh ìomhaighean a bhith an cois gach in-chuir no gun a bhith an cois gin dhiubh. |
| `validation[].prompt` |  | string | yes |  |  | Prompt a thèid a chleachdadh rè dearbhaidh. |
| `validation[].image_url` |  | string (image URL) \| null | no |  |  | Ìomhaigh airson dearbhadh image-to-video, ceadaichte a-mhàin ma tha ìomhaigh anns gach in-chur dearbhaidh eile cuideachd. |
| `validation_negative_prompt` |  | string | no | `worst quality, inconsistent motion, blurry, jittery, distorted` |  | Prompt àicheil air a chur an sàs rè dearbhaidh. |
| `validation_number_of_frames` |  | integer | no | `89` | 9 – 121 | Àireamh frèam airson gach bhidio dearbhaidh. |
| `validation_frame_rate` |  | integer | no | `25` | 8 – 60 | Ìre frèama targaid a’ bhidio dearbhaidh, air a thomhas ann am frèaman gach diog. |
| `validation_resolution` |  | enum (string) | no | `high` | `low`, `medium`, `high` | Dùmhlachd-bhreacaidh a thèid a chleachdadh rè dearbhaidh. |
| `validation_aspect_ratio` |  | enum (string) | no | `1:1` | `16:9`, `1:1`, `9:16` | Co-mheas-taobhan a thèid a chleachdadh rè dearbhaidh. |
| `stg_scale` |  | number | no | `1` | 0 – 3 | Sgèile Spatio-Temporal Guidance (STG), le 1.0 air a mholadh agus 0.0 a’ cur STG dheth. |
| `generate_audio_in_validation` |  | boolean | no | `true` |  | A’ cumail smachd air co-dhiù a tha claisneachd ghinte anns na sampallan dearbhaidh. |

## 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 airson bhideothan dearbhaidh sam bith a tha rim faighinn. |
| `lora_file` | object {url, content_type, file_name, file_size} | URL airson cuideaman LoRA trèanaichte ann an cruth .safetensors. |
| `config_file` | object {url, content_type, file_name, file_size} | Rèiteachadh airson suidheachadh puing-crìche inference. |
| `debug_dataset` | object {url, content_type, file_name, file_size} \| null | Tasglann debug a ghabhas luchdadh a-nuas, air a thilleadh a-mhàin airson in-churan le `debug_dataset` air a chomasachadh; tha an seata-dàta trèanaidh ro-ghiullachd ann, a’ gabhail a-steach claisneachd agus bhidio dì-chòdaichte. |

## 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