Wan 2.6 Flash Image to Video API

POST Base URL: https://api.hiapi.ai /v1/tasks

Copy Page

Image, video, and audio models are called through theUnified Async API POST /v1/tasks endpoint; only the input fields differ (see input parameters below).

Model summary

Model	wan2.6-flash/image-to-video
Capability	Single-image video + optional audio
Resolution	720p / 1080p
Duration	5 / 10 / 15 seconds

Upload one image, describe the motion and get a 5, 10 or 15 second video at 720p or 1080p, with optional synchronized audio.

Production guidance

Calling the API

• Check the motion at 720p, 5 seconds and no audio first, then switch to 1080p, a longer clip or audio on.
• Upload a portrait image for portrait output; the frame follows the image.
• Use callback.url for task notifications; read the task object from data in query responses and directly from the callback body.
• Artifact URLs expire; copy files you need to keep into persistent storage.

Best suited for

Animate a still

Natural motion and camera moves for people, animals, products and scenery.

image_urlsprompt

Clips with sound

Turn audio on for synchronized ambience and effects.

audio

Longer shots

Up to 15 seconds for a complete action or mood.

duration

Request parameters

</> Generate example code

model string required

Model ID.

example wan2.6-flash/image-to-video

input object required

Image-to-video parameters.

prompt string required

Describe the motion, camera and atmosphere in Chinese or English, up to 1,500 characters.

image_urls string[] required

One public image URL (http:// or https://) used as the start of the video. JPG/PNG/WebP, at least 256×256, up to 10MB; the output follows the image's aspect ratio.

duration enum optional

Length in seconds: 5, 10 or 15. Billed per second.

default 5 enum: 51015

resolution enum optional

Output resolution.

default 720p enum: 720p1080p

audio boolean optional

Generate synchronized audio (ambience, effects). Audio-on clips are billed at the audio rate.

default false

callback object optional

Sends a notification when the task succeeds or fails; read the task object from data in query responses and directly from the callback body.

url string required

HTTPS URL that receives task success or failure notifications.

example https://your-domain.com/hiapi/callback

when enum optional

Triggers when the task succeeds or fails.

default final enum: final

Input requirements

• image_urls is required and takes exactly one image; JPG/PNG/WebP, at least 256×256, up to 10MB.
• duration accepts 5, 10 or 15; resolution accepts 720p or 1080p.
• prompt is required, up to 1,500 characters.

Example requests

Default, silent

720p, 5 seconds, no audio.

Request body⧉

{
  "model": "wan2.6-flash/image-to-video",
  "input": {
    "prompt": "The fox turns its head toward the camera, its ears twitch, golden leaves drift down through the misty light",
    "image_urls": [
      "https://example.com/start.jpg"
    ]
  }
}

1080p with audio

Audio on at 1080p.

Request body⧉

{
  "model": "wan2.6-flash/image-to-video",
  "input": {
    "prompt": "The vendor tosses the noodles in the wok, flames flare up, the crowd chatters",
    "image_urls": [
      "https://example.com/start.jpg"
    ],
    "resolution": "1080p",
    "audio": true
  }
}

Getting the result

1. Read data.taskId from the create-task response.
2. Wait for the callback or query GET /v1/tasks/:id; polling puts the task under data.
3. When status=success, read the video URL from output type=video; a callback reads output directly.

FAQ

Does audio change the price?

Yes. Audio-on clips are billed at the audio per-second rate; see the pricing page for current prices.

Can I set the output aspect ratio?

No need; the frame follows the input image.

Can I pass more than one image?

No. image_urls takes exactly one image.

Which lengths are supported?

5, 10 or 15 seconds; 5 by default.

Next steps

• Live pricing