# Wan-2.2 Text-to-Video A14B with LoRAs API

> A14B text-to-video с поддержкой LoRA и необязательным обратным воспроизведением

Создаёт видео из текстового `prompt`, применяя веса LoRA, перечисленные в `loras`. `reverse_video` воспроизводит клип в обратном направлении. `num_frames` принимает значения от 17 до 161, `resolution` — 480p, 580p или 720p, а соотношение сторон — 16:9, 9:16 или 1:1. Доступны интерполяция film или rife и две шкалы guidance.

- Model id: `wan/v2.2-a14b/text-to-video/lora`
- Made by: Alibaba
- Category: Text to Video
- Output: video
- Estimated price per run: from $0.507 / run (cheapest run $0.507 (507 API credits))
- Run: `POST https://api.doitong.ru/v1/run/wan/v2.2-a14b/text-to-video/lora`
- Quote: `POST https://api.doitong.ru/v1/quote/wan/v2.2-a14b/text-to-video/lora`
- Docs page: https://doitong.com/developers/models/wan/v2.2-a14b/text-to-video/lora

## Pricing

Price: **from $0.507 / run** (the lowest tier; the quote prices your exact input). Estimated from the typical cost of one run. The quote is exactly what the run charges.

Price rules (the first rule that matches the input wins; a parameter you leave out counts as its default):

- When `num_frames` > 81 and `resolution` = 480p: base price × 2
- When `num_frames` > 81 and `resolution` = 580p: base price × 2
- When `num_frames` > 81 and `resolution` = 720p: base price × 2

The full example input below costs $0.507 = 507 API credits (1 request × 507 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/wan/v2.2-a14b/text-to-video/lora` 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 |  |  | Text instructions that guide video generation. |
| `negative_prompt` |  | string | no | `` |  | Negative prompt applied when generating a video. |
| `num_frames` |  | integer | no | `81` | 17 – 161 | Frame count for generation, with an inclusive range of 17–161. |
| `frames_per_second` |  | integer \| null | no | `16` | 4 – 60 | Generated video frame rate, accepting values from 4 to 60; setting `adjust_fps_for_interpolation` to false preserves this rate unchanged. With interpolation in use and `adjust_fps_for_interpolation` true (its default), multiply this rate by one plus the interpolated frame count to obtain the final FPS. For example, 16 FPS with 1 interpolated frame becomes 32 FPS. |
| `seed` |  | integer \| null | no |  |  | Seed that makes generation reproducible. Setting it to None selects a seed randomly. |
| `resolution` |  | enum (string) | no | `720p` | `480p`, `580p`, `720p` | Output video resolution: 480p, 580p, or 720p. |
| `aspect_ratio` |  | enum (string) | no | `16:9` | `16:9`, `9:16`, `1:1` | Output video's aspect ratio, either 16:9 or 9:16. |
| `num_inference_steps` |  | integer | no | `27` | 2 – 40 | Sampling step count, trading longer processing time for better quality as the count increases. |
| `enable_safety_checker` |  | boolean | no | `false` |  | Input safety screening before processing, which only authorized accounts may turn off. Requests lacking authorization are always screened; otherwise, true enables screening. |
| `enable_output_safety_checker` |  | boolean | no | `false` |  | Controls safety screening of the generated video; setting true enables a check after generation. |
| `enable_prompt_expansion` |  | boolean | no | `false` |  | Allow a large language model to enrich the prompt with details. Enabling this expansion leaves the prompt's meaning unchanged. |
| `acceleration` |  | enum (string) | no | `regular` | `none`, `regular` | Acceleration setting, with 'regular' as the recommended choice. Increasing acceleration sacrifices quality to shorten generation time. |
| `guidance_scale` |  | number | no | `3.5` | 1 – 10 | Classifier-free guidance strength, trading possible quality loss for closer prompt matching as the scale increases. |
| `guidance_scale_2` |  | number | no | `4` | 1 – 10 | Guidance scale controlling how closely the model follows the prompt during its second stage. |
| `shift` |  | number | no | `5` | 1 – 10 | Video shift setting, with an allowed range of 1.0–10.0. |
| `interpolator_model` |  | enum (string) | no | `film` | `none`, `film`, `rife` | Frame interpolation setting: choose None to skip interpolation, or specify the model to perform it. |
| `num_interpolated_frames` |  | integer | no | `1` | 0 – 4 | Insert 0–4 interpolated frames into every gap between two generated frames. |
| `adjust_fps_for_interpolation` |  | boolean | no | `true` |  | Frame-rate adjustment toggle: false preserves the supplied FPS, whereas true scales it by one plus the interpolated frame count. Thus, 16 FPS becomes 32 FPS when 1 frame is interpolated and adjustment is enabled. |
| `video_quality` |  | enum (string) | no | `high` | `low`, `medium`, `high`, `maximum` | Output video quality setting that trades larger files for improved visuals as the setting increases. |
| `video_write_mode` |  | enum (string) | no | `balanced` | `fast`, `balanced`, `small` | Video writing mode, with balanced offering a compromise between speed and quality. Choose small for the smallest files and slowest writing; faster writing returns results sooner but creates larger files. |
| `loras` |  | array of object {path, weight_name, scale, transformer} | no | `[]` |  | LoRA weights applied during inference. |
| `loras[].path` |  | string | yes |  |  | Location of the LoRA weights, specified as a URL or path. |
| `loras[].weight_name` |  | string \| null | no |  |  | LoRA weight name, required only when a Hugging Face repository contains more than 1 safetensors file. This name is used only when `path` identifies such a repository. |
| `loras[].scale` |  | number | no | `1` | 0 – 4 | Multiplier applied to the LoRA weight before it is merged into the base model. |
| `loras[].transformer` |  | enum (string) | no | `high` | `high`, `low`, `both` | Transformer destination for the LoRA weight. Select 'high' for the high-noise transformer, 'low' for the low-noise transformer, or 'both' to load the weight into both transformers. |
| `reverse_video` |  | boolean | no | `false` |  | Video reversal toggle; true reverses playback. |

## 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/wan/v2.2-a14b/text-to-video/lora?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/wan/v2.2-a14b/text-to-video/lora?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/wan/v2.2-a14b/text-to-video/lora", 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": "wan/v2.2-a14b/text-to-video/lora",
      "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": "wan/v2.2-a14b/text-to-video/lora",
  "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": 507,
    "usd": "0.507",
    "charged": 507,
    "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 close-up of a young woman smiling gently in the rain, raindrops glistening on her face and eyelashes. The video captures the delicate details of her expression and the water droplets, with soft light reflecting off her skin in the rainy atmosphere.",
    "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} | Video file produced by generation. |
| `prompt` | string | Text prompt used to generate the video. |
| `seed` | integer | Seed value applied during generation. |

## Related models

- [Wan v2.2 A14B Text-to-Image A14B with LoRAs](https://doitong.com/developers/models/wan/v2.2-a14b/text-to-image/lora.md) (`wan/v2.2-a14b/text-to-image/lora`): $0.05 / image
- [Wan v2.2 A14B Image-to-Video A14B with LoRAs](https://doitong.com/developers/models/wan/v2.2-a14b/image-to-video/lora.md) (`wan/v2.2-a14b/image-to-video/lora`): from $1.006 / run
- [Wan 3.0 Text to Video](https://doitong.com/developers/models/alibaba/wan-3.0/text-to-video.md) (`alibaba/wan-3.0/text-to-video`): from $0.05 / second
- [FLUX 3 Max Text to Video](https://doitong.com/developers/models/blackforestlabs/flux-3-max/text-to-video.md) (`blackforestlabs/flux-3-max/text-to-video`): from $0.0425 / second of output video
- [Grok Imagine Video 1.5 Text to Video](https://doitong.com/developers/models/xai/grok-imagine-video/v1.5/text-to-video.md) (`xai/grok-imagine-video/v1.5/text-to-video`): from $0.08 / second
- [Kling 3.0 Pro Text to Video](https://doitong.com/developers/models/kling-video/v3/pro/text-to-video.md) (`kling-video/v3/pro/text-to-video`): from $0.112 / second
- [LTX 2.5 Pro Text to Video](https://doitong.com/developers/models/lightricks/ltx-2.5/text-to-video/pro.md) (`lightricks/ltx-2.5/text-to-video/pro`): from $0.12 / second
- [MiniMax H3 Text to Video](https://doitong.com/developers/models/minimax/h3/text-to-video.md) (`minimax/h3/text-to-video`): from $0.05 / second

## Links

- HTML page: https://doitong.com/developers/models/wan/v2.2-a14b/text-to-video/lora
- 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=wan/v2.2-a14b/text-to-video/lora
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.ru/v1/models/wan/v2.2-a14b/text-to-video/lora