Seedance 2.5 Now Live | Try in Video Generator →
Home/Explore/Alibaba/Wan 3.0/Reference To Video

alibaba/

Wan 3.0 Reference to Video creates coherent videos from prompts and multimodal references, including images, videos, and audio, with flexible 2-30 second duration and aspect ratio control for subject consistency, motion guidance, timing control, and scene continuity. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

image-to-video
Input

Idle

$0.6per run·~16 / $10

Next:

ExamplesView all

A steam train races across an endless desert at sunset while a masked female outlaw rides beside it on a black horse. She leaps onto the moving train, fights her way across the roof, and reaches a guarded carriage carrying a frightened young prisoner. As soldiers surround them, she cuts the carriage loose, sending it down a different track toward a distant canyon. Epic western action film, fast-paced camera movement, dynamic horseback tracking shots, dramatic close combat, sweeping aerial views, flying dust, golden sunset, practical stunt realism, anamorphic lens flares, cinematic scale.

Related Models

README

Wan 3.0 Reference-to-Video

Wan 3.0 Reference-to-Video combines reference images, videos, and audio with a prompt to create coherent video scenes. It supports multimodal reference guidance for character consistency, object control, motion direction, audio style, and scene composition.

Parameters

ParameterRequiredDescription
promptYesText prompt describing the desired scene, subject, motion, camera movement, lighting, and style.
reference_imagesConditionalUp to 10 reference images. At least one reference media array is required.
reference_videosConditionalUp to 5 reference video inputs. Each video must be MP4 or MOV, 1–15 seconds, 240–4096 pixels on each side, no more than 8:1 aspect ratio, and no more than 100 MB. Total reference video duration must not exceed 15 seconds.
reference_audiosConditionalUp to 5 reference audio files. Total reference audio duration must not exceed 15 seconds.
resolutionNoOutput resolution: 480p, 720p, or 1080p. Default: 720p.
aspect_ratioNoOutput aspect ratio. Default: 16:9.
durationNoOutput duration in seconds. Range: 2–30. Default: 5.
thinking_modeNoEnable deep-thinking mode for more deliberate prompt interpretation. Default: false.
enable_audioNoInclude audio in the output. Default: true.
seedNoRandom seed from 0 to 2147483647.

At least one of reference_images, reference_videos, or reference_audios is required.

How to Use

  1. Add reference media — Provide reference images, videos, audio, or a combination of them.
  2. Write your prompt — Describe the target scene, action, camera movement, lighting, style, and how the references should be used.
  3. Choose resolution — Use 480p for lower-cost drafts, 720p for balanced output, or 1080p for higher quality.
  4. Set aspect ratio — Select the output format that matches your target platform or creative direction.
  5. Set duration — Choose a duration from 2 to 30 seconds.
  6. Configure audio optional — Keep enable_audio enabled when audio is needed.
  7. Enable thinking mode optional — Use thinking_mode for complex prompts with multiple reference requirements.
  8. Submit — Generate the final reference-guided video.

Pricing

Pricing is based on output resolution and billed duration.

Billed duration is rounded up to the next whole second and clamped to the 2–30s range.

ResolutionPer 5sPer second
480p$0.35$0.07
720p$0.65$0.13
1080p$1.40$0.28

Example Costs

Resolution2s5s10s30s
480p$0.14$0.35$0.70$2.10
720p$0.26$0.65$1.30$3.90
1080p$0.56$1.40$2.80$8.40

Best Use Cases

  • Character-consistent storytelling — Generate scenes guided by character, face, outfit, or style references.
  • Multi-reference video generation — Combine people, objects, environments, motion, and audio references in one workflow.
  • Product and brand videos — Use reference assets to preserve product appearance or campaign style.
  • Audio-guided scenes — Use reference audio to guide mood, rhythm, ambience, or sound direction.
  • Social media content — Create short-form videos from multimodal references.
  • Creative prototyping — Test different scene directions while keeping reference-guided consistency.

Pro Tips

  • Use clear reference images when identity, product detail, or visual style matters.
  • Use reference videos when motion, pacing, gesture, or camera behavior matters.
  • Use reference audio when ambience, rhythm, voice style, or soundtrack direction matters.
  • Explain how each reference should influence the final video in the prompt.
  • Use 480p for quick drafts and 1080p for higher-quality output.
  • Enable thinking_mode for prompts that combine multiple references or detailed scene requirements.
  • Set a fixed seed when you want more reproducible results.

Related Models

Note:This website uses AI models provided by third parties. Documentation prices are for reference and may be outdated. The Generate button shows an estimate; the final task charge prevails.

Wan 3.0 Reference To Video API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/alibaba/wan-3.0/reference-to-video with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Wan 3.0 Reference To Video below.

HTTP example
set -euo pipefail

: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"

REQUEST_BODY=$(cat <<'JSON'
{
    "prompt": "A cinematic shot of a city at sunset, soft golden light",
    "resolution": "720p",
    "aspect_ratio": "16:9",
    "duration": 5,
    "thinking_mode": false,
    "enable_audio": true
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/alibaba/wan-3.0/reference-to-video" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY" \
  -d "$REQUEST_BODY")

TASK=$(printf '%s' "$SUBMIT_RESPONSE" | jq 'if has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "$TASK" | jq -r '.id')
if [ -z "$PREDICTION_ID" ] || [ "$PREDICTION_ID" = "null" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL=$(printf '%s' "$TASK" | jq -r '.urls.get // empty')
if [ -z "$RESULT_URL" ]; then
  RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/$PREDICTION_ID/result"
fi

# 2. Poll until the prediction finishes.
while true; do
  RESPONSE=$(curl --silent --show-error --fail-with-body "$RESULT_URL" \
    -H "Authorization: Bearer $WAVESPEED_API_KEY")
  RESULT=$(printf '%s' "$RESPONSE" | jq 'if has("data") then .data else . end')
  STATUS=$(printf '%s' "$RESULT" | jq -r '.status')
  case "$STATUS" in
    completed) printf '%s\n' "$RESULT" | jq '.outputs'; break ;;
    failed|cancelled|timeout) printf '%s\n' "$RESULT" | jq . >&2; exit 1 ;;
    created|processing) sleep 2 ;;
    *) printf 'Unexpected status: %s
' "$STATUS" >&2; exit 1 ;;
  esac
done
Node.js example
const submitUrl = "https://api.wavespeed.ai/api/v3/alibaba/wan-3.0/reference-to-video";
const apiKey = process.env.WAVESPEED_API_KEY;
if (!apiKey) throw new Error('Set WAVESPEED_API_KEY');

async function requestJson(url, options = {}) {
  const response = await fetch(url, options);
  if (!response.ok) throw new Error(await response.text());
  return response.json();
}

// 1. Submit the prediction.
const body = await requestJson(submitUrl, {
  method: "POST",
  headers: {
    "Authorization": `Bearer ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
        "prompt": "A cinematic shot of a city at sunset, soft golden light",
        "resolution": "720p",
        "aspect_ratio": "16:9",
        "duration": 5,
        "thinking_mode": false,
        "enable_audio": true
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
  `https://api.wavespeed.ai/api/v3/predictions/${task.id}/result`;

// 2. Poll until the prediction finishes.
while (true) {
  const resultBody = await requestJson(resultUrl, {
    headers: { "Authorization": `Bearer ${apiKey}` },
  });
  const result = resultBody.data ?? resultBody;
  if (result.status === "completed") {
    console.log(result.outputs);
    break;
  }
  if (["failed", "cancelled", "timeout"].includes(result.status)) throw new Error(JSON.stringify(result));
  if (!["created", "processing"].includes(result.status)) throw new Error("Unexpected status: " + result.status);
  await new Promise(resolve => setTimeout(resolve, 2000));
}
Python example
import json
import os
import time
from urllib.request import Request, urlopen

api_key = os.environ["WAVESPEED_API_KEY"]
headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
payload = {
    "prompt": "A cinematic shot of a city at sunset, soft golden light",
    "resolution": "720p",
    "aspect_ratio": "16:9",
    "duration": 5,
    "thinking_mode": False,
    "enable_audio": True
}

def request_json(url, data=None):
    request = Request(url, data=data, headers=headers, method="POST" if data else "GET")
    with urlopen(request) as response:
        return json.load(response)

# 1. Submit the prediction.
body = request_json("https://api.wavespeed.ai/api/v3/alibaba/wan-3.0/reference-to-video", json.dumps(payload).encode())
task = body.get("data", body)
if not task.get("id"):
    raise RuntimeError("Submission response did not contain a prediction id")
result_url = task.get("urls", {}).get("get") or f"https://api.wavespeed.ai/api/v3/predictions/{task['id']}/result"

# 2. Poll until the prediction finishes.
while True:
    result_body = request_json(result_url)
    result = result_body.get("data", result_body)
    status = result.get("status")
    if status == "completed":
        print(result.get("outputs", []))
        break
    if status in {"failed", "cancelled", "timeout"}:
        raise RuntimeError(result)
    if status not in {"created", "processing"}:
        raise RuntimeError(f"Unexpected status: {status}")
    time.sleep(2)

Wan 3.0 Reference To Video API — Frequently asked questions

What is the Wan 3.0 Reference To Video API?

Wan 3.0 Reference To Video is a Alibaba model for video generation from images, exposed as a REST API on WaveSpeedAI. Wan 3.0 Reference to Video creates coherent videos from prompts and multimodal references, including images, videos, and audio, with flexible 2-30 second duration and aspect ratio control for subject consistency, motion guidance, timing control, and scene continuity. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.

How do I call the Wan 3.0 Reference To Video API?

POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID. Poll the result endpoint starting around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. The playground generates production-oriented Python, JavaScript, and cURL examples with timeouts, transient-error handling, and safe GET retries. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/alibaba/alibaba-wan-3.0-reference-to-video.

How much does Wan 3.0 Reference To Video cost per run?

Wan 3.0 Reference To Video starts at $0.60 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.

What inputs does Wan 3.0 Reference To Video accept?

Key inputs: `prompt`, `aspect_ratio`, `resolution`, `duration`, `seed`, `reference_images`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/alibaba/alibaba-wan-3.0-reference-to-video.

How long does Wan 3.0 Reference To Video take to generate?

Median end-to-end generation time on WaveSpeedAI is around 731 seconds per request, based on recent successful runs. Queue time varies with global demand; live status is visible in the prediction record.

Can I use Wan 3.0 Reference To Video outputs commercially?

Commercial usage rights depend on the model's license, set by its provider (Alibaba). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.

Wan 3.0 Reference to Video API on WaveSpeedAI