Wan 3.0 Reference to Video API

Text to video Image to video References

Endpoint: POST https://api.higgsfield.ai/alibaba/wan-3.0/reference-to-video Endpoint ID: alibaba/wan-3.0/reference-to-video ▶Try Wan 3.0 with ReferencesOpen this endpoint in the Higgsfield API Playground.↗

Quick Start

import higgsfield_client

result = higgsfield_client.subscribe(
    "alibaba/wan-3.0/reference-to-video",
    arguments={
        "prompt": "Use Image 1 for the character and Video 1 for the camera movement",
        "image_urls": ["https://cdn.example.com/character.jpg"],
        "video_urls": ["https://cdn.example.com/camera-reference.mp4"],
        "audio_urls": ["https://cdn.example.com/music-reference.mp3"],
        "resolution": "1080p",
        "aspect_ratio": "adaptive",
        "duration": 8,
        "generate_audio": True,
    },
)

print(result["video"]["url"])

import { config, higgsfield } from "@higgsfield/client/v2";

config({ credentials: process.env.HF_CREDENTIALS });

const result = await higgsfield.subscribe(
  "alibaba/wan-3.0/reference-to-video",
  {
    input: {
      prompt: "Use Image 1 for the character and Video 1 for the camera movement",
      image_urls: ["https://cdn.example.com/character.jpg"],
      video_urls: ["https://cdn.example.com/camera-reference.mp4"],
      audio_urls: ["https://cdn.example.com/music-reference.mp3"],
      resolution: "1080p",
      aspect_ratio: "adaptive",
      duration: 8,
      generate_audio: true,
    },
    withPolling: true,
  },
);

if (result.isCompleted) console.log(result.jobs[0].results?.raw.url);

curl --request POST \
  --url https://api.higgsfield.ai/alibaba/wan-3.0/reference-to-video \
  --header "Authorization: Key ${HF_API_KEY_ID}:${HF_API_KEY_SECRET}" \
  --header "Content-Type: application/json" \
  --data '{
    "prompt": "Use Image 1 for the character and Video 1 for the camera movement",
    "image_urls": ["https://cdn.example.com/character.jpg"],
    "video_urls": ["https://cdn.example.com/camera-reference.mp4"],
    "audio_urls": ["https://cdn.example.com/music-reference.mp3"],
    "resolution": "1080p",
    "aspect_ratio": "adaptive",
    "duration": 8,
    "generate_audio": true
  }'

Input Schema

string

required

Text instructions for the output. Refer to assets by order, such as Image 1, Video 1, or Audio 1.

array

Public reference image URLs. Accepts up to 10 items.

array

Public reference video URLs. Accepts up to 5 clips with a maximum combined duration of 30 seconds.

array

Public WAV or MP3 reference URLs. Accepts up to 5 files with a maximum combined duration of 30 seconds.

string

Public document URL used as context. Supported document types include PDF, DOCX, XLSX, PPTX, TXT, and Markdown. Cannot be combined with link_url.

string

Public web page URL used as context. Cannot be combined with file_url.

string

default:"1080p"

Supported values: 480p, 720p, 1080p.

string

default:"adaptive"

Supported values: adaptive, 16:9, 4:3, 1:1, 3:4, 9:16.

integer

default:"5"

Output duration in seconds. Supported range: 2–30; input video duration plus output duration cannot exceed 30 seconds.

boolean

default:"true"

Generate synchronized dialogue, ambience, sound effects, and music.

boolean

default:"false"

Enable additional reasoning. Automatically enabled when file_url or link_url is provided.

integer

Optional integer seed from 0 to 2147483647 for reproducibility.

Provide at least one reference input. file_url and link_url are mutually exclusive.

Output Schema

string

required

Request state. A newly accepted request returns queued.

string

required

Stable identifier used for polling, cancellation, and support.

string

required

URL to poll until the request reaches a terminal state.

string

required

URL used to cancel a request before processing starts.

object

Completed video output containing its download url.

Input Example

{
  "prompt": "Use Image 1 for the character and Video 1 for the camera movement",
  "image_urls": ["https://cdn.example.com/character.jpg"],
  "video_urls": ["https://cdn.example.com/camera-reference.mp4"],
  "audio_urls": ["https://cdn.example.com/music-reference.mp3"],
  "resolution": "1080p",
  "aspect_ratio": "adaptive",
  "duration": 8,
  "generate_audio": true
}

Output Example

{
  "status": "queued",
  "request_id": "d7e6c0f3-6699-4f6c-bb45-2ad7fd9158ff",
  "status_url": "https://api.higgsfield.ai/requests/d7e6c0f3-6699-4f6c-bb45-2ad7fd9158ff/status",
  "cancel_url": "https://api.higgsfield.ai/requests/d7e6c0f3-6699-4f6c-bb45-2ad7fd9158ff/cancel"
}

{
  "status": "completed",
  "request_id": "d7e6c0f3-6699-4f6c-bb45-2ad7fd9158ff",
  "video": { "url": "https://cdn.example.com/wan-3-reference-to-video.mp4" }
}

Use an SDK for automatic polling, or poll the returned status URL.

Get started

Model API reference

Core concepts

SDKs

Organizations

API reference

Resources

Quick Start

Input Schema

Output Schema

Input Example

Output Example

​Quick Start

​Input Schema

​Output Schema

​Input Example

​Output Example

Quick Start

Input Schema

Output Schema

Input Example

Output Example