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

> Nagsasanay ng video-to-video LoRA mula sa magkapares na before/after clip, na ginagabayan ng reference control video

Nagtetrain ng LoRA na natututo ng transformation mula sa magkapares na before at after clip at ginagabayan sa inference ng reference video. Ang default ay 3000 hakbang at `first_frame_conditioning_p` na 0.1. Pinahihintulutan ng `reference_downscale_factor` at `reference_temporal_scale_factor` (1 hanggang 8) ang coarse o low-fps na reference proxy.

- 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/fil/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 |  |  | URL ng `.zip` na naglalaman ng training data, na inayos ayon sa napiling training mode. Maaaring may katumbas na `.txt` caption na may parehong base name ang bawat 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 | `3000` | 100 – 10,000 | Kabuuang bilang ng training step. |
| `learning_rate` |  | number | no | `0.0002` | 0.000001 – 1 | Learning rate ng optimization. |
| `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 | `24` | 8 – 60 | Target frame rate ng training video sa frames per segundo. Ang native rate para sa LTX-2.3 ay 24. |
| `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. |
| `first_frame_conditioning_p` |  | number | no | `0.1` | 0 – 1 | Paboran ang video-to-video transformation sa pamamagitan ng pagbawas sa dalas ng paggamit ng training sa first-frame conditioning; itinatakda ng value na ito ang probability na iyon. |
| `validation` |  | array of object {prompt, reference_video_url} | no | `[]` | ≤ 2 items | Listahan ng input para sa validation na naglalaman ng mga prompt na ipinapares sa reference videos. |
| `validation[].prompt` |  | string | yes |  |  | Prompt na ginagamit habang nagva-validation. |
| `validation[].reference_video_url` |  | string (video URL) | yes |  | ≥ 1 characters | Ibigay ang video na ita-transform sa panahon ng IC-LoRA validation sa pamamagitan ng URL nito. |
| `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.` |  | Negative prompt na inilalapat habang nagva-validation, na gumagamit ng single-stage preview process. Dahil tinatantiya ng prosesong iyon ang distilled production inference na may dalawang stage, naiiba ang guidance at preview quality nito sa mga final result. |
| `validation_number_of_frames` |  | integer | no | `89` | 9 – 121 | Bilang ng frame para sa bawat validation video. |
| `validation_frame_rate` |  | integer | no | `24` | 8 – 60 | Target frame rate para sa validation video, sa frames per segundo; native na tumatakbo ang LTX-2.3 sa 24. |
| `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. |
| `reference_downscale_factor` |  | integer | no | `1` | 1 – 8 | Spatial reduction factor para sa IC-LoRA control reference video; 1 ang default at pinananatili ang resolution at behavior. Bago ang encoding, dini-downscale ang reference ayon sa factor na ito upang turuan ang LoRA na gumawa ng full-resolution output mula sa coarse, low-resolution input, gaya ng maliit na pose, depth, o sketch proxy. Kinakailangan ang divisibility by 32 para sa width at height, bago at pagkatapos hatiin ang mga ito sa factor. |
| `reference_temporal_scale_factor` |  | integer | no | `1` | 1 – 8 | Reference frame-rate reduction factor para sa IC-LoRA control, na default sa 1 upang mapanatili ang fps at behavior. Sumasailalim ang reference video sa temporal downsampling ayon sa factor na ito bago ang encoding, kaya maaaring gamitin ng LoRA ang reference na may mababang fps. |

## 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 | Pinagsamang video preview mula sa validation, kapag available para sa mga endpoint na gumagawa ng video. |
| `audio` | object {url, content_type, file_name, file_size} \| null | Pinagsamang audio mula sa validation, ibinibigay bilang preview kapag available para sa mga audio-only route na ito: /audio-inpaint, /audio-extend-suffix, /audio-extend-prefix, /t2a, /a2a, at /v2a. |
| `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 | Debug output na available kapag naka-enable ang `debug_dataset`: isang archive na maaaring i-download at naglalaman ng training data pagkatapos ng preprocessing. |

## 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