# LTX-Video 13B 0.9.8 Distilled · Multiconditioning API

> 使用 0.9.8 distilled 13B 模型，同时根据多张图像和视频以及提示词进行生成

将必填的 `prompt` 与条件 `images` 和 `videos` 列表结合生成视频，使多个参考共同影响一个结果。输出为 480p 或 720p，`aspect_ratio` 可为 auto、9:16、1:1 或 16:9。`num_frames` 范围为 9 到 1441，`loras` 用于添加自定义权重。

- Model id: `ltxv-13b-098-distilled/multiconditioning`
- Made by: Lightricks
- Category: Video to Video
- Output: video
- Price per second of your output video: from $0.02 / second of output video (cheapest run $0.02 (20 API credits))
- Run: `POST https://api.doitong.ru/v1/run/ltxv-13b-098-distilled/multiconditioning`
- Quote: `POST https://api.doitong.ru/v1/quote/ltxv-13b-098-distilled/multiconditioning`
- Docs page: https://doitong.com/zh-CN/developers/models/ltxv-13b-098-distilled/multiconditioning

## Pricing

Price: **from $0.02 / second of output video** (the lowest tier; the quote prices your exact input). Price per second of your output video: the input files are measured before the run (length, resolution, frame rate). The quote measures the same files and is exactly what the run charges.

The full example input below costs $0.101 = 101 API credits (5.0417 s output video × $0.02).

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/ltxv-13b-098-distilled/multiconditioning` 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 |
|---|---|---|---|---|---|---|
| `prompt` |  | string | yes |  |  | 引导生成的文本指令。 |
| `negative_prompt` |  | string | no | `worst quality, inconsistent motion, blurry, jittery, distorted` |  | 用于生成的负面文本指令。 |
| `loras` |  | array of object {path, weight_name, scale} | no | `[]` |  | 生成过程中应用的 LoRA 权重。 |
| `loras[].path` |  | string | yes |  |  | LoRA 权重的位置，可以是 URL 或路径。 |
| `loras[].weight_name` |  | string \| null | no |  |  | 用于在 HuggingFace 仓库的多个权重中进行选择的 LoRA 权重名称；仅包含多个权重的仓库需要此项。除非 `path` 指向 HuggingFace 仓库，否则此设置无效。 |
| `loras[].scale` |  | number | no | `1` | 0 – 4 | 加载 LoRA 权重时对其进行缩放的乘数。 |
| `resolution` |  | enum (string) | no | `720p` | `480p`, `720p` | 输出视频的分辨率。 |
| `aspect_ratio` |  | enum (string) | no | `auto` | `9:16`, `1:1`, `16:9`, `auto` | 视频宽高比。 |
| `seed` |  | integer \| null | no |  |  | 控制生成过程中随机性的种子。 |
| `num_frames` |  | integer | no | `121` | 9 – 1,441 | 视频的总帧数。 |
| `first_pass_num_inference_steps` |  | integer | no | `8` | 2 – 12 | 第一遍的推理步数。 |
| `second_pass_num_inference_steps` |  | integer | no | `8` | 2 – 12 | 第二遍的推理步数。 |
| `second_pass_skip_initial_steps` |  | integer | no | `5` | 1 – 11 | 第二遍要省略的初始推理步数，使该遍处理更偏向细节优化，而不是大范围变化。 |
| `frame_rate` |  | integer | no | `24` | 1 – 60 | 视频的帧率。 |
| `expand_prompt` |  | boolean | no | `false` |  | 通过语言模型扩展提示词。 |
| `reverse_video` |  | boolean | no | `false` |  | 反转视频的播放顺序。 |
| `enable_safety_checker` |  | boolean | no | `true` |  | 安全检查开关；关闭设置仅对已授权账户生效。所有未经授权的请求都会进行安全检查。 |
| `enable_detail_pass` |  | boolean | no | `false` |  | 可选的第二次细化处理，启用后可改善视频细节。 |
| `temporal_adain_factor` |  | number | no | `0.5` | 0 – 1 | 自适应实例归一化（AdaIN）强度：较高设置更注重颜色一致性，较低设置允许更大的颜色变化。它会处理除第一段以外的生成片段，对整个视频中的颜色分布进行归一化，以帮助抑制饱和度或对比度逐步升高。 |
| `tone_map_compression_ratio` |  | number | no | `0` | 0 – 1 | 色调映射压缩级别，从 0.0 时不压缩到 1.0 时最大压缩。以这种方式压缩视频的动态范围可改善视觉质量。 |
| `constant_rate_factor` |  | integer | no | `29` | 0 – 51 | 用于输入压缩的恒定码率因子（CRF），通过使提供的媒体更接近模型训练数据，可能改善运动质量。 |
| `images` |  | array of object {image_url, start_frame_num, strength} | no | `[]` |  | 通过 URL 提供的条件图像。 |
| `images[].image_url` |  | string (image URL) | yes |  |  | 通过 URL 提供的条件图像。 |
| `images[].start_frame_num` |  | integer | no | `0` | 0 – 1,440 | 图像条件起始位置，以可被 8 整除的帧号指定。 |
| `images[].strength` |  | number | no | `1` | 0 – 1 | 条件强度：0.0 禁用条件控制，1.0 完全应用条件控制。 |
| `videos` |  | array of object {video_url, conditioning_type, preprocess, start_frame_num, strength, limit_num_frames, max_num_frames, resample_fps, target_fps, reverse_video} | no | `[]` |  | 用于条件控制的视频。 |
| `videos[].video_url` |  | string (video URL) | yes |  |  | 通过 URL 提供的条件视频。 |
| `videos[].conditioning_type` |  | enum (string) \| null | no | `rgb` | `rgb`, `depth`, `pose`, `canny` | 视频条件类别，用于在启用预处理时选择预处理管线，并正确应用上下文 LoRA 权重。 |
| `videos[].preprocess` |  | boolean | no | `false` |  | 启用预处理以匹配视频的条件类型。对于 RGB 条件，启用此项不会进行任何更改。 |
| `videos[].start_frame_num` |  | integer | no | `0` | 0 – 1,440 | 视频中的条件起始位置，以可被 8 整除的帧号指定。 |
| `videos[].strength` |  | number | no | `1` | 0 – 1 | 条件强度：0.0 禁用条件控制，1.0 完全应用条件控制。 |
| `videos[].limit_num_frames` |  | boolean | no | `false` |  | 视频帧数限制开关：启用后，`max_num_frames` 会限制从视频中获取的帧数。 |
| `videos[].max_num_frames` |  | integer | no | `1441` | 1 – 1,441 | 视频帧数上限，None 表示选择整个视频，而不是限制帧数。 |
| `videos[].resample_fps` |  | boolean | no | `false` |  | 视频帧率转换开关：启用后，会以 `target_fps` 指定的帧率重新采样视频。 |
| `videos[].target_fps` |  | integer | no | `24` | 1 – 60 | 重新采样帧率（以 FPS 计），仅在启用 `resample_fps` 时适用。 |
| `videos[].reverse_video` |  | boolean | no | `false` |  | 视频顺序反转，用于需要条件控制按反向帧顺序进行的任务。 |

## Example input

Required parameters only:

```json
{
  "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
}
```

A fuller example:

```json
{
  "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
}
```

## 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/ltxv-13b-098-distilled/multiconditioning?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  }'

# 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/ltxv-13b-098-distilled/multiconditioning?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  }),
});
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 = {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/ltxv-13b-098-distilled/multiconditioning", 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": "ltxv-13b-098-distilled/multiconditioning",
      "input": {
        "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
      },
      "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": "ltxv-13b-098-distilled/multiconditioning",
  "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": 101,
    "usd": "0.101",
    "charged": 101,
    "refunded": 0
  },
  "input": {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  },
  "output": {
    "video": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp4",
      "content_type": "video/mp4",
      "file_name": "0-output.mp4",
      "file_size": 1843200
    },
    "prompt": "A vibrant, abstract composition featuring a person with outstretched arms, rendered in a kaleidoscope of colors against a deep, dark background. The figure is composed of intricate, swirling patterns reminiscent of a mosaic, with hues of orange, yellow, blue, and green that evoke the style of artists such as Wassily Kandinsky or Bridget Riley. The camera zooms into the face striking portrait of a man, reimagined through the lens of old-school video-game graphics. The subject's face is rendered in a kaleidoscope of colors, with bold blues and reds set against a vibrant yellow backdrop. His dark hair is pulled back, framing his profile in a dramatic pose.",
    "seed": 42
  },
  "outputs": [
    {
      "type": "video",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp4",
      "content_type": "video/mp4",
      "file_size": 1843200,
      "width": 1280,
      "height": 720,
      "duration": 5,
      "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} | 生成生成的视频文件。 |
| `prompt` | string | 用于生成输出的提示词。 |
| `seed` | integer | 生成期间应用的种子值。 |

## Related models

- [LTX-Video 13B 0.9.8 Distilled](https://doitong.com/developers/models/ltxv-13b-098-distilled.md) (`ltxv-13b-098-distilled`): from $0.02 / second of output video
- [LTX-Video 13B 0.9.8 Distilled · Image to Video](https://doitong.com/developers/models/ltxv-13b-098-distilled/image-to-video.md) (`ltxv-13b-098-distilled/image-to-video`): from $0.02 / second of output video
- [LTX-Video 13B 0.9.8 Distilled · Extend](https://doitong.com/developers/models/ltxv-13b-098-distilled/extend.md) (`ltxv-13b-098-distilled/extend`): from $0.02 / second of output video
- [Ltx 2.3](https://doitong.com/developers/models/ltx-2.3/reframe.md) (`ltx-2.3/reframe`): from $0.10 / second of input video
- [LTX 2.3 22B](https://doitong.com/developers/models/ltx-2.3-22b/reference-video-to-video/lora.md) (`ltx-2.3-22b/reference-video-to-video/lora`): $0.00181 / megapixel of output video
- [Ltx 2.3 Quality · Clean Plate](https://doitong.com/developers/models/ltx-2.3-quality/clean-plate.md) (`ltx-2.3-quality/clean-plate`): $0.00241 / megapixel of output video
- [Ltx 2.3 Quality · Colorization](https://doitong.com/developers/models/ltx-2.3-quality/colorization.md) (`ltx-2.3-quality/colorization`): $0.00241 / megapixel of output video
- [Ltx 2.3 Quality · Cross Eyed](https://doitong.com/developers/models/ltx-2.3-quality/cross-eyed.md) (`ltx-2.3-quality/cross-eyed`): $0.00241 / megapixel of output video

## Links

- HTML page: https://doitong.com/developers/models/ltxv-13b-098-distilled/multiconditioning
- 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=ltxv-13b-098-distilled/multiconditioning
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.ru/v1/models/ltxv-13b-098-distilled/multiconditioning