> ## Documentation Index
> Fetch the complete documentation index at: https://docs.anyfast.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Wan2.2 I2V A14B

> Wan2.2 I2V A14B video generation model via Alibaba via Anyfast API.

Wan2.2 I2V A14B is an image-to-video generation model available through Anyfast. Video generation is **asynchronous** — submit a task and poll `GET /v1/video/generations/{task_id}` until `status` is `succeeded`.

## Key capabilities

* **Image-to-video** — Generate videos from an image + text prompt
* **Image-to-video** — Provide a reference image URL via `image`
* **Duration control** — 3–5 seconds
* **Custom resolution** — Set `width` × `height`

## Quick example

<CodeGroup>
  ```bash cURL theme={null}
  # Step 1 — create task
  curl https://www.anyfast.ai/v1/video/generations \
    -H "Authorization: Bearer YOUR_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "model": "wan2.2-i2v-a14b",
      "prompt": "a cat playing piano",
      "duration": 5,
      "image": "https://example.com/cat.jpg"
    }'

  # Step 2 — poll until succeeded
  curl https://www.anyfast.ai/v1/video/generations/{TASK_ID} \
    -H "Authorization: Bearer YOUR_API_KEY"
  ```

  ```python Python theme={null}
  import requests, time

  headers = {"Authorization": "Bearer YOUR_API_KEY"}

  # Step 1 — create task
  resp = requests.post(
      "https://www.anyfast.ai/v1/video/generations",
      headers=headers,
      json={
          "model": "wan2.2-i2v-a14b",
          "prompt": "a cat playing piano",
          "duration": 5,
          "image": "https://example.com/cat.jpg",
      }
  )
  task_id = resp.json()["task_id"]

  # Step 2 — poll until done
  while True:
      result = requests.get(
          f"https://www.anyfast.ai/v1/video/generations/{task_id}",
          headers=headers
      ).json()
      status = result["data"]["status"]
      if status == "succeeded":
          print(result["data"]["url"])
          break
      elif status == "failed":
          print("Failed:", result["data"]["error"])
          break
      time.sleep(3)
  ```
</CodeGroup>

## Parameters

| Parameter  | Type    | Required  | Description                         |
| ---------- | ------- | --------- | ----------------------------------- |
| `model`    | string  | Yes       | Must be `wan2.2-i2v-a14b`           |
| `prompt`   | string  | Yes       | Text description of the video       |
| `image`    | string  | Yes (i2v) | Reference image URL                 |
| `duration` | number  | No        | 3–5 seconds. Default: `5`           |
| `width`    | integer | No        | Output video width in pixels        |
| `height`   | integer | No        | Output video height in pixels       |
| `seed`     | integer | No        | Random seed for reproducibility     |
| `metadata` | object  | No        | Extra parameters passed to upstream |

## Task status values

| Status       | Description                                             |
| ------------ | ------------------------------------------------------- |
| `queued`     | Task is waiting in queue                                |
| `processing` | Video is being generated                                |
| `succeeded`  | Done — `data.url` contains the video link (valid \~24h) |
| `failed`     | Failed — `data.error` contains the error message        |

<Card title="API Reference" icon="code" href="/api-reference/model-api/alibaba/wan2.2-i2v-a14b">
  View the interactive API playground for Wan2.2 I2V A14B.
</Card>

<script src="/feedback.js" />