Seedance 2.5 Now Live | Try in Video Generator →
Home/Explore/Vidu/Q3/Start End To Video

vidu/

Vidu Q3 Start End Image-to-Video turns text prompts into high-quality videos with exceptional visual fidelity and diverse motion. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

image-to-video
Input

Idle

$0.35per run·~28 / $10

Next:

ExamplesView all

A rugged, mid-30s man with short dark hair and a weathered face rides a vintage black motorcycle at high speed through a winding mountain road at dusk. He wears a leather jacket with visible wear, gloves, and goggles pushed up on his forehead, eyes focused ahead with determination. The motorcycle kicks up dust and gravel as it curves sharply, tires screaming against the asphalt. Behind him, the sky glows with orange and purple hues, trees blur past, and distant mountains loom in shadow. Shot in cinematic action style, wide-angle, dynamic motion blur, realistic lighting, high detail, 4K resolution.

Related Models

README

Vidu Q3 Start-End-to-Video

Vidu Q3 Start-End-to-Video generates videos with precise control over both the first and last frames. Provide a start image, an end image, and a text prompt — the model creates a smooth, coherent video transition between the two states. Supports multiple resolutions, motion control, and optional audio generation with background music.

Why Choose This?

  • Start and end frame control Define both the beginning and ending visuals for precise, predictable video transitions.

  • Smooth interpolation AI-powered motion generates natural, fluid movement between your two reference frames.

  • Multiple resolutions Choose from 540p, 720p, or 1080p to balance quality and cost.

  • Motion control Adjust movement_amplitude to control the intensity of motion in the transition.

  • Audio generation Optional synchronized audio and background music for complete video content.

  • Prompt Enhancer Built-in tool to automatically improve your scene descriptions.

Parameters

ParameterRequiredDescription
promptYesText description of the desired motion and action
imageYesStart frame image (URL or upload)
last_imageYesEnd frame image (URL or upload)
durationNoVideo length in seconds (default: 5)
resolutionNoOutput resolution: 540p, 720p, or 1080p (default: 720p)
bgmNoInclude background music (default: enabled)
generate_audioNoWhether to generate synchronized audio (default: enabled)
movement_amplitudeNoMotion intensity: auto or manual value (default: auto)
seedNoRandom seed for reproducible results (default: -1)

How to Use

  1. Upload your start image — provide the first frame of the video.
  2. Upload your end image — provide the last frame of the video.
  3. Write your prompt — describe the motion, action, and transition between the two frames.
  4. Set duration — specify how long you want the video to be.
  5. Set resolution — choose 540p for speed, 720p for balance, or 1080p for quality.
  6. Adjust motion (optional) — control movement intensity with movement_amplitude.
  7. Enable audio (optional) — toggle generate_audio and bgm for complete video with sound.
  8. Run — submit and download your video.

Pricing

ResolutionCost per Second
540p$0.07
720p$0.15
1080p$0.16

Billing Rules

  • Per-second billing based on duration and resolution
  • Total cost = duration × per-second rate

Examples

  • 5s @ 540p → 5 × $0.07 = $0.35
  • 5s @ 720p → 5 × $0.15 = $0.75
  • 5s @ 1080p → 5 × $0.16 = $0.80
  • 10s @ 720p → 10 × $0.15 = $1.50

Best Use Cases

  • Scene Transitions — Create smooth cinematic transitions between two visual states.
  • Product Morphing — Show product transformations, color changes, or feature variations.
  • Before/After Content — Generate engaging videos showing transformations or comparisons.
  • Character Animation — Animate a character moving from one pose to another.
  • Time-Lapse Effects — Create artificial time-lapse videos with controlled start and end points.

Pro Tips

  • Use images with similar composition for smoother transitions.
  • The prompt should describe the motion and action happening between frames, not just the static scenes.
  • Start with shorter durations (5s) to test transitions before generating longer clips.
  • Set a seed value to reproduce the same result or create consistent variations.
  • Lower movement_amplitude for subtle transitions, higher for dramatic transformations.

Notes

  • Prompt, image, and last_image are all required fields.
  • Higher resolution increases both quality and cost.
  • Audio generation (generate_audio and bgm) is included at no extra cost.
  • Seed value of -1 means random seed.

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.

Q3 Start End To Video API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/vidu/q3/start-end-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 Q3 Start End 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",
    "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
    "last_image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
    "duration": 5,
    "resolution": "720p",
    "bgm": true,
    "generate_audio": true,
    "movement_amplitude": "auto",
    "seed": -1
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/vidu/q3/start-end-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/vidu/q3/start-end-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 ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
        "prompt": "A cinematic shot of a city at sunset, soft golden light",
        "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
        "last_image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
        "duration": 5,
        "resolution": "720p",
        "bgm": true,
        "generate_audio": true,
        "movement_amplitude": "auto",
        "seed": -1
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
  `https://api.wavespeed.ai/api/v3/predictions/${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",
    "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
    "last_image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
    "duration": 5,
    "resolution": "720p",
    "bgm": True,
    "generate_audio": True,
    "movement_amplitude": "auto",
    "seed": -1
}

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/vidu/q3/start-end-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)

Q3 Start End To Video API — Frequently asked questions

What is the Q3 Start End To Video API?

Q3 Start End To Video is a Vidu model for video generation from images, exposed as a REST API on WaveSpeedAI. Vidu Q3 Start End Image-to-Video turns text prompts into high-quality videos with exceptional visual fidelity and diverse motion. 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 Q3 Start End 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/vidu/vidu-q3-start-end-to-video.

How much does Q3 Start End To Video cost per run?

Q3 Start End To Video starts at $0.35 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 Q3 Start End To Video accept?

Key inputs: `prompt`, `image`, `resolution`, `duration`, `seed`, `bgm`. 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/vidu/vidu-q3-start-end-to-video.

How long does Q3 Start End To Video take to generate?

Median end-to-end generation time on WaveSpeedAI is around 81 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 Q3 Start End To Video outputs commercially?

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

Vidu Q3 Start End to Video | Fast Image-to-Video API on WaveSpeedAI