Skip to main content
Video models

Wan 2.6 — Image to video API

Image to video with Wan 2.6: request parameters, examples and response handling.

← Wan 2.6

Endpoint: POST https://api.higgsfield.ai/wan/v2.6/image-to-video

Endpoint ID: wan/v2.6/image-to-video

▶Open API PlaygroundWan 2.6 · Image to video↗

#Usage notes

  • Setting multi_shots=true also enables prompt_extend, even if prompt_extend was false.
  • Input images may be resized to fit a 1,440-pixel maximum dimension before generation. A last-frame input is unsupported.

#Quick start

Replace the example media URLs with publicly accessible URLs for your own files before submitting.

cURL
curl --request POST \
  --url https://api.higgsfield.ai/wan/v2.6/image-to-video \
  --header "Authorization: Key ${HF_API_KEY_ID}:${HF_API_KEY_SECRET}" \
  --header "Content-Type: application/json" \
  --header "Idempotency-Key: ${IDEMPOTENCY_KEY}" \
  --data '{
  "prompt": "A cinematic wide shot of ocean waves at sunset, with gentle camera movement.",
  "image_url": "https://example.com/input.jpg"
}'

#Input schema

seed integer

Seed used to control generation randomness. Minimum: -1. Maximum: 10000000.

prompt string required

Write your prompt here

duration integer (default: 5)

Requested output duration in seconds. Allowed values: 5, 10, 15.

audio_url string

Public URL of the audio reference. Format: uri.

image_url string required

Public URL of the input image. Format: uri.

resolution string (default: 720p)

Output resolution tier. Allowed values: "480p", "720p", "1080p".

multi_shots boolean (default: false)

See the complete JSON schema below.

prompt_extend boolean (default: false)

Enable prompt expansion.

negative_prompt string

Content or visual features to avoid.

Complete JSON schema
json
{
  "type": "object",
  "title": "Wan 2.6 Playground",
  "required": [
    "prompt",
    "image_url"
  ],
  "properties": {
    "seed": {
      "type": "integer",
      "maximum": 10000000,
      "minimum": -1
    },
    "prompt": {
      "type": "string",
      "title": "Prompt",
      "description": "Write your prompt here"
    },
    "duration": {
      "enum": [
        5,
        10,
        15
      ],
      "type": "integer",
      "title": "Duration",
      "default": 5
    },
    "audio_url": {
      "type": "string",
      "title": "Audio URL",
      "format": "uri"
    },
    "image_url": {
      "type": "string",
      "title": "Image URL",
      "format": "uri"
    },
    "resolution": {
      "enum": [
        "480p",
        "720p",
        "1080p"
      ],
      "type": "string",
      "default": "720p"
    },
    "multi_shots": {
      "type": "boolean",
      "default": false
    },
    "prompt_extend": {
      "type": "boolean",
      "default": false
    },
    "negative_prompt": {
      "type": "string",
      "title": "Negative prompt",
      "default": ""
    }
  }
}

#Response

Submission returns a request handle. Poll status_url until status is completed, or use webhooks.

Accepted
{
  "status": "queued",
  "request_id": "REQUEST_ID",
  "status_url": "https://api.higgsfield.ai/requests/REQUEST_ID/status",
  "cancel_url": "https://api.higgsfield.ai/requests/REQUEST_ID/cancel"
}

A completed response includes the following output fields:

json
{
  "status": "completed",
  "request_id": "REQUEST_ID",
  "video": {
    "url": "https://example.com/output.mp4"
  }
}

See idempotent requests, polling, request errors and authentication for shared request handling.

Was this page helpful?
Navigation