Wan first-frame image-to-video compatibility view

Compatibility view for Wan first-frame image-to-video requests. This document keeps the legacy single-image public shape under /v1/videos.

Public fields: model, image, prompt, seconds, size, prompt_extend, watermark, seed, and negative_prompt. For channel-specific latest capabilities, use the dedicated capability document.

POST /v1/videos

Wan First-Frame to Video

cURL

curl --request POST \
  --url https://api.powertokens.ai/v1/videos \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "first-frame-video-model",
  "image": "https://example.com/first-frame.jpg",
  "prompt": "Realistic style, a black kitten curiously looking at the sky, camera moving up from eye level to top-down",
  "seconds": "5",
  "size": "720P",
  "prompt_extend": true
}
'

200

{
  "id": "<string>",
  "task_id": "<string>",
  "object": "video",
  "model": "<string>",
  "status": "pending",
  "progress": 123,
  "created_at": 123
}

Authorizations

Authorization · string · header · required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json

model · string · required

First-frame image-to-video model identifier for this compatibility view.

image · string · required

First frame image URL. Supports HTTP/HTTPS publicly accessible addresses.

prompt · string

Text prompt describing desired video content. Supports Chinese and English, max 800 characters.

seconds · string · default: 5

String form of the video duration in seconds. Currently fixed at "5".

size · enum<string> · default: 1080P

Video resolution for the compatibility view. Options: 480P, 720P, 1080P.

Available options: 480P, 720P, 1080P

prompt_extend · boolean · default: true

Whether to enable prompt intelligent rewriting.

watermark · boolean · default: false

Whether to add watermark to video.

seed · integer

Random seed, range [0, 2147483647].

negative_prompt · string

Negative prompt describing content to avoid. Max 500 characters.

Response

200

application/json

Submission successful, returns video task object.

id · string

Task unique identifier.

task_id · string

Task ID (same as id).

object · string

Example:

"video"

model · string

Model name used.

status · enum<string>

Task status.

Available options: pending, queued, running, succeeded, failed, cancelled

progress · integer

Task progress (percentage).

created_at · integer<int64>

Unix timestamp of creation time (seconds).