# LTX 2.3 Trainer (V2) - Audio+Video Reference Transformation API

> 训练 LoRA，将参考片段的视频和音频映射到配对目标片段，并同时生成两条轨道

在配对片段上训练 LoRA，其中每个带音频的参考视频都与目标片段对应。通过 `training_data_url` 提供压缩包，可选添加 .txt 字幕。默认关闭场景切分，因为这会使起止配对失去同步，因此请提供已剪切的片段。`rank` 可为 8 到 128，步数为 100 到 10000，最多允许 2 个验证条目。

- Model id: `ltx23-trainer-v2/av2av`
- Made by: Lightricks
- Category: Training
- Output: file
- Price: $0.0068 / step (cheapest run $13.60 (13600 API credits))
- Run: `POST https://api.doitong.ru/v1/run/ltx23-trainer-v2/av2av`
- Quote: `POST https://api.doitong.ru/v1/quote/ltx23-trainer-v2/av2av`
- Docs page: https://doitong.com/zh-CN/developers/models/ltx23-trainer-v2/av2av

## Pricing

Price: **$0.0068 / step**. Billed per training step (`number_of_steps`).

The full example input below costs $13.60 = 13600 API credits (2000 steps × 6.8 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.ru/v1/quote/ltx23-trainer-v2/av2av` 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 |  |  | 包含训练数据的 `.zip` URL，数据按所选训练模式组织。每个媒体文件可以附带一个名称匹配的 `.txt` 字幕文件。 |
| `rank` |  | enum (integer) | no | `32` | `8`, `16`, `32`, `64`, `128` | LoRA 适配秩；该设置越高，内存消耗越大，但容量也越高。 |
| `number_of_steps` |  | integer | no | `2000` | 100 – 10,000 | 训练步数总数。 |
| `learning_rate` |  | number | no | `0.0002` | 0.000001 – 1 | 优化学习率。 |
| `number_of_frames` |  | integer | no | `89` | 9 – 121 | 每个训练样本的帧数。将该数量除以 8 后余数必须为 1；示例包括 1、9、17、25、33、41、49、57、65、73、81、89、97。 |
| `frame_rate` |  | integer | no | `24` | 8 – 60 | 训练视频的目标帧率，以每秒帧数计。LTX-2.3 的原生帧率为 24。 |
| `resolution` |  | enum (string) | no | `medium` | `low`, `medium`, `high` | 训练分辨率。提高分辨率会增加内存需求。 |
| `aspect_ratio` |  | enum (string) | no | `1:1` | `16:9`, `1:1`, `9:16` | 训练宽高比。 |
| `trigger_phrase` |  | string | no | `` |  | LoRA 样式激活短语，在训练期间插入字幕开头。 |
| `auto_scale_input` |  | boolean | no | `false` |  | 启用后自动调整视频，使其匹配请求的 FPS 和帧数；图像数据集保持不变。 |
| `split_input_into_scenes` |  | boolean | no | `false` |  | av2av 中禁用场景切分，以保持 _start/_end 对同步。必须预先切分片段；目标/参考配对准备会忽略场景切分设置。 |
| `split_input_duration_threshold` |  | number | no | `30` | 1 – 60 | 以秒为单位的场景切分触发时长：只有超过该阈值的视频才会被切分。 |
| `debug_dataset` |  | boolean | no | `false` |  | 预处理检查模式，用于在完整训练运行前检查视频、图像和字幕。启用后，训练器会在可下载的归档中返回处理后的训练数据集，以便手动检查。 |
| `audio_normalize` |  | boolean | no | `true` |  | 音频峰值归一化，以保持整个数据集中的音量一致。 |
| `audio_preserve_pitch` |  | boolean | no | `true` |  | 调整音频以匹配视频长度时保留音高，而不是裁剪音频。 |
| `validation` |  | array of object {prompt, reference_video_url, reference_audio_url} | no | `[]` | ≤ 2 items | 验证提示词列表，每个提示词与一个参考视频和音频配对。 |
| `validation[].prompt` |  | string | yes |  |  | 验证期间使用的提示词。 |
| `validation[].reference_video_url` |  | string (video URL) | yes |  | ≥ 1 characters | 用于条件音频和视频生成的参考视频 URL。视频的音频轨道也会作为音频参考。 |
| `validation[].reference_audio_url` |  | string (audio URL) \| null | no |  |  | 可选地覆盖 `reference_video_url` 中的音频轨道，方法是提供单独参考音频文件的 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.` |  | 验证期间应用的负面提示词，验证使用单阶段预览流程。由于该流程近似于两阶段的蒸馏生产推理，其引导方式和预览质量与最终结果不同。 |
| `validation_number_of_frames` |  | integer | no | `89` | 9 – 121 | 每个验证视频的帧数。 |
| `validation_frame_rate` |  | integer | no | `24` | 8 – 60 | 验证视频的目标帧率，以每秒帧数计；LTX-2.3 的原生帧率为 24。 |
| `validation_resolution` |  | enum (string) | no | `high` | `low`, `medium`, `high` | 验证期间使用的分辨率。 |
| `validation_aspect_ratio` |  | enum (string) | no | `1:1` | `16:9`, `1:1`, `9:16` | 验证期间使用的宽高比。 |
| `stg_scale` |  | number | no | `1` | 0 – 3 | 时空引导（STG）比例，建议使用 1.0，使用 0.0 可关闭 STG。 |
| `reference_downscale_factor` |  | integer | no | `1` | 1 – 8 | 用于在编码前创建粗略低分辨率参考视频控制代理的缩小因子，同时保持输出为完整分辨率。缩小前后两个参考尺寸都必须能被 32 整除；默认值 1 会保留原始分辨率。 |
| `reference_temporal_scale_factor` |  | integer | no | `1` | 1 – 8 | 参考视频帧率降低因子，默认值为 1，以保留 fps。按此因子进行时间下采样会在视频编码前降低 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.ru/v1/run/ltx23-trainer-v2/av2av?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.ru/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"
```

### JavaScript

```javascript
const API = "https://api.doitong.ru/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/av2av?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.ru/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/av2av", 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.ru/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/av2av",
      "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/av2av",
  "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": 13600,
    "usd": "13.60",
    "charged": 13600,
    "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.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
```

### Output fields (`output`)

| Field | Type | Description |
|---|---|---|
| `video` | object {url, content_type, file_name, file_size} \| null | 验证生成的合并视频预览（适用于可用且会生成视频的端点）。 |
| `audio` | object {url, content_type, file_name, file_size} \| null | 验证生成的合并音频；对于以下仅音频路由，在可用时作为预览提供：/audio-inpaint、/audio-extend-suffix、/audio-extend-prefix、/t2a、/a2a 和 /v2a。 |
| `lora_file` | object {url, content_type, file_name, file_size} | 采用 .safetensors 格式的已训练 LoRA 权重 URL。 |
| `config_file` | object {url, content_type, file_name, file_size} | 推理端点设置的配置。 |
| `debug_dataset` | object {url, content_type, file_name, file_size} \| null | 启用 `debug_dataset` 时可用的调试输出：一个可下载的归档，其中包含预处理后的训练数据。 |

## 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-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
- [LTX 2.3 Trainer (V2) - Forward Audio Extension](https://doitong.com/developers/models/ltx23-trainer-v2/audio-extend-prefix.md) (`ltx23-trainer-v2/audio-extend-prefix`): $0.0022 / step

## Links

- HTML page: https://doitong.com/developers/models/ltx23-trainer-v2/av2av
- 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/av2av
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.ru/v1/models/ltx23-trainer-v2/av2av