# LTX 2.3 Trainer (V2) - Video-to-Video API

> Ka whakangungu i tētahi LoRA ataata-ki-te-ataata mai i ngā topenga i mua/i muri kua taurite, ka aratakina e tētahi ataata whakahaere tohutoro

Ka whakangungu i tētahi LoRA e ako ana i tētahi panoni mai i ngā topenga i mua me muri kua taurite, ā, ka aratakina i te inferensi e tētahi ataata tohutoro. Ko te taunoa he 3000 kaupae me `first_frame_conditioning_p` he 0.1. Mā `reference_downscale_factor` me `reference_temporal_scale_factor` (1 ki te 8) e taea ai ngā takawaenga tohutoro whānui, iti-auau-anga rānei.

- Model id: `ltx23-trainer-v2/v2v`
- Made by: Lightricks
- Category: Training
- Output: file
- Price: $0.0059 / step (cheapest run $17.70 (17700 API credits))
- Run: `POST https://api.doitong.com/v1/run/ltx23-trainer-v2/v2v`
- Quote: `POST https://api.doitong.com/v1/quote/ltx23-trainer-v2/v2v`
- Docs page: https://doitong.com/mi/developers/models/ltx23-trainer-v2/v2v

## Pricing

Price: **$0.0059 / step**. Billed per training step (`number_of_steps`).

The full example input below costs $17.70 = 17700 API credits (3000 steps × 5.9 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-trainer-v2/v2v` 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 |  |  | He URL mō tētahi `.zip` kei roto ngā raraunga whakangungu, kua whakaritea kia rite ki te aratau whakangungu kua kōwhiria. Ka taea e ia kōnae pāpāho he tapanga `.txt` whai ingoa pūtake ōrite. |
| `rank` |  | enum (integer) | no | `32` | `8`, `16`, `32`, `64`, `128` | Te taumata urutaunga LoRA, e whakawhiti ana i te nui ake o te whakamahinga mahara mō te kaha nui ake i te pikinga o te tautuhinga. |
| `number_of_steps` |  | integer | no | `3000` | 100 – 10,000 | Te tatau katoa o ngā hipanga whakangungu. |
| `learning_rate` |  | number | no | `0.0002` | 0.000001 – 1 | Te tere ako mō te arotautanga. |
| `number_of_frames` |  | integer | no | `89` | 9 – 121 | Te tatau anga mō ia tauira whakangungu. Me waiho he toenga 1 ina whakawehea te tatau ki te 8; ko ngā tauira 1, 9, 17, 25, 33, 41, 49, 57, 65, 73, 81, 89, 97. |
| `frame_rate` |  | integer | no | `24` | 8 – 60 | Te tere anga whāinga o te ataata whakangungu, i ngā anga ia hēkona. Ko te tere taketake mō LTX-2.3 he 24. |
| `resolution` |  | enum (string) | no | `medium` | `low`, `medium`, `high` | Te taumira whakangungu. Mā te whakapiki i te taumira ka piki ngā hiahia mahara. |
| `aspect_ratio` |  | enum (string) | no | `1:1` | `16:9`, `1:1`, `9:16` | Te ōwehenga-āhuatanga whakangungu. |
| `trigger_phrase` |  | string | no | `` |  | Te rerenga whakakā kāhua LoRA, ka whakaurua ki te tīmatanga o ngā tapanga i te wā whakangungu. |
| `auto_scale_input` |  | boolean | no | `false` |  | Te whakatikatika aunoa i te ataata kia ōrite ki te FPS me te tatau anga i tonoa ina whakakāhia; kāore ngā huinga raraunga atahanga e whakarerekē. |
| `split_input_into_scenes` |  | boolean | no | `true` |  | Te wehe whakaaturanga mō ngā ataata kua hipa i te paepae roanga, ka whakakā ina pono. |
| `split_input_duration_threshold` |  | number | no | `30` | 1 – 60 | Te keu wehe whakaaturanga kua whakaaturia hei roanga i roto i ngā hēkona: ko ngā ataata roa ake i te paepae anake ka wehewehea. |
| `debug_dataset` |  | boolean | no | `false` |  | Te aratau tirotiro tukatuka-mua mō te taki i ngā ataata, ngā atahanga me ngā tapanga i mua i te rerenga whakangungu katoa. Ina whakakāhia, ka whakahokia e te kaiwhakangungu te huinga raraunga whakangungu kua tukatukahia ki tētahi pūranga ka taea te tikiake mō te arotake ā-ringa. |
| `first_frame_conditioning_p` |  | number | no | `0.1` | 0 – 1 | Whakanuia te huringa video-to-video mā te whakaiti i te auautanga e whakamahi ai te whakangungu i te whakarite ki te anga tuatahi; mā tēnei uara taua tūponotanga e whakarite. |
| `validation` |  | array of object {prompt, reference_video_url} | no | `[]` | ≤ 2 items | Rārangi tāuru whakamana e whai ana i ngā tohutohu kua honoa ki ngā ataata tohutoro. |
| `validation[].prompt` |  | string | yes |  |  | Te tohutohu e whakamahia ana i te whakamana. |
| `validation[].reference_video_url` |  | string (video URL) | yes |  | ≥ 1 characters | Tukuna te ataata hei panoni i te wā o te whakamana IC-LoRA mā tōna URL. |
| `validation_negative_prompt` |  | string | no | `blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio, incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts.` |  | Te tohutohu tōraro ka whakamahia i te whakamana, mā tētahi tukanga arokite wāhanga-kotahi. Nā te mea ka whakatata taua tukanga ki te whakatau whakaputa kua whakarewaina, e rua ōna wāhanga, he rerekē tōna arataki me tōna kounga arokite i ngā putanga whakamutunga. |
| `validation_number_of_frames` |  | integer | no | `89` | 9 – 121 | Te tatau anga mō ia ataata whakamana. |
| `validation_frame_rate` |  | integer | no | `24` | 8 – 60 | Te tere anga whāinga mō ngā ataata whakamana, i ngā anga ia hēkona; ko te tere taketake o LTX-2.3 he 24. |
| `validation_resolution` |  | enum (string) | no | `high` | `low`, `medium`, `high` | Te taumira e whakamahia ana i te whakamana. |
| `validation_aspect_ratio` |  | enum (string) | no | `1:1` | `16:9`, `1:1`, `9:16` | Te ōwehenga-āhuatanga e whakamahia ana i te whakamana. |
| `stg_scale` |  | number | no | `1` | 0 – 3 | Te tauine Spatio-Temporal Guidance (STG), ko te 1.0 e taunakitia ana, ā, mā te 0.0 e whakaweto te STG. |
| `reference_downscale_factor` |  | integer | no | `1` | 1 – 8 | Tauwehe whakaiti mokowā mō te ataata tohutoro whakahaere IC-LoRA; ko 1 te taunoa, ka pupuri i te taumira me te whanonga. I mua i te whakawaehere, ka whakahekea te taumira o te tohutoro mā tēnei tauwehe hei whakaako i te LoRA kia whakaputa putanga taumira-katoa mai i te tāuru taratara, taumira-iti, pērā i tētahi takawaenga tū, hōhonu, tātuhi rānei. Me taea te wehe i te whānui me te teitei ki te 32 i mua, ā, i muri hoki i te wehe ki te tauwehe. |
| `reference_temporal_scale_factor` |  | integer | no | `1` | 1 – 8 | Tauwehe whakaiti auau-anga o te tohutoro mō te whakahaere IC-LoRA, ko 1 te taunoa hei pupuri i te fps me te whanonga. Ka whakahekea ā-wā te ataata tohutoro mā tēnei tauwehe i mua i te whakawaehere, kia āhei ai tētahi tohutoro fps-iti ki te ārahi i te LoRA. |

## 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-trainer-v2/v2v?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-trainer-v2/v2v?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-trainer-v2/v2v", 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-trainer-v2/v2v",
      "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-trainer-v2/v2v",
  "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": 17700,
    "usd": "17.70",
    "charged": 17700,
    "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
    },
    "audio": {
      "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 | He arokite ataata whakakotahi mai i te whakamana, ina wātea mō ngā pito API whakaputa ataata. |
| `audio` | object {url, content_type, file_name, file_size} \| null | He ororongo whakakotahi mai i te whakamana, ka tukuna hei arokite ina wātea mō ēnei ara ororongo-anake: /audio-inpaint, /audio-extend-suffix, /audio-extend-prefix, /t2a, /a2a, me /v2a. |
| `lora_file` | object {url, content_type, file_name, file_size} | He URL mō ngā taumahatanga LoRA kua whakangungua i te hōputu .safetensors. |
| `config_file` | object {url, content_type, file_name, file_size} | Te whirihoranga mō te tatūnga pito API whakatau. |
| `debug_dataset` | object {url, content_type, file_name, file_size} \| null | Putanga rapurongoā e wātea ana ina whakakāhia `debug_dataset`: he pūranga ka taea te tikiake, kei roto ngā raraunga whakangungu i muri i te tukatuka-mua. |

## 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-trainer-v2/v2v
- 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-trainer-v2/v2v
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.com/v1/models/ltx23-trainer-v2/v2v