Wan 2.2 Image to Video

POST /v3/async/wan-2.2-i2v

Wan 2.2 Image to Video

cURL

curl --request POST \
  --url https://api.myrouter.ai/v3/async/wan-2.2-i2v \
  --header 'Authorization: <authorization>' \
  --header 'Content-Type: <content-type>' \
  --data '
{
  "input": {
    "prompt": "<string>",
    "img_url": "<string>",
    "template": "<string>",
    "audio_url": "<string>",
    "last_image": "<string>",
    "negative_prompt": "<string>"
  },
  "parameters": {
    "seed": 123,
    "audio": true,
    "loras": [
      {}
    ],
    "duration": 123,
    "watermark": true,
    "resolution": "<string>",
    "prompt_extend": true
  }
}
'

200

{
  "task_id": "<string>"
}

Wan 2.2 Image-to-Video API that converts static images into dynamic videos.

This is an async API that only returns the task_id of the async task. Use the task_id to call the Get Async Task Result API to retrieve the generated result.

Request Headers

Content-Type · string · required

Enum: application/json

Authorization · string · required

Bearer authentication format: Bearer {{API Key}}.

Request Body

input · object · required

Input parameters, including the source image and text prompt.

Hide properties

prompt · string

Text describing the desired video motion. Supports Chinese and English, up to 800 characters.

img_url · string · required

URL of the input image. Supported formats: JPEG, JPG, PNG, BMP, WEBP. Resolution: 360-2000px. Max: 10MB.

template · string

Predefined motion template name.

audio_url · string

URL of the audio file. Formats: WAV, MP3. Duration: 3-30 seconds. Max: 15MB.

last_image · string

URL of the end frame image, used for start-end frame video generation.

negative_prompt · string

Describes content to avoid in the generated video. Up to 500 characters.

parameters · object

Optional parameters for controlling video generation.

Hide properties

seed · integer

Random seed for reproducible generation.

audio · boolean

Whether to generate video with audio.

loras · array

List of LoRA models to apply.

LoRA model configuration.

duration · integer · default: 5

Duration of the generated video (seconds).

Possible values: 5, 8, 10

watermark · boolean

Whether to add a watermark. Default: false.

resolution · string · default: "480P"

Output video resolution.

Possible values: 480P, 720P, 1080P

prompt_extend · boolean

Whether to enable automatic prompt enhancement. Default: true.

Response

task_id · string

Use the task_id to call the Get Async Task Result API to retrieve the generated output.