MiniMax H3 Open Weights | Try in Video Generator →

Vidu Start End to Video Q2 Turbo | Fast Image-to-Video API

vidu/

Vidu Q2 Turbo Start-End to Video creates smooth Image-to-Video transitions between start and end images with fast high-quality results. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

image-to-video
Input

Idle

$0.1per run·~10 / $1

Next:

ExamplesView all

Camera spins, fabrics swirl, colors morph into a new outfit.

A time-lapse sequence showing the sun arcing across the sky, shadows moving dynamically across the mountain face, and the fog in the valley slowly dissipating to reveal a lush green landscape.

Her expression slowly and subtly transforms. The sadness in her eyes begins to fade, replaced by a growing spark of determination. A faint, hopeful smile begins to form on her lips as she lifts her gaze, looking directly into the camera.

Gentle wind blows, petals swirl, the temperature drops as the scene gradually turns cold.

Lights flicker as the music builds, her reflection in the window begins to change.

The camera zooms into the painting as her reflection merges with the artwork.

The character is running, and eventually, they slowly grow up.

The dream collapses, clouds dissolve into dust, fading into a real bedroom.

Seasons whirl — the ice melts, green life bursts forth.

Related Models

README

Vidu Q2 Start-End to Video Turbo

Vidu Q2 Start-End to Video Turbo creates a coherent video from just two images: a start frame and an end frame. Turbo accelerates bi-frame interpolation with optimized inference for faster turnaround and smoother motion — ideal for scene transitions, bridging shots, and rapid storytelling.

Why Choose This?

  • Bi-frame guidance Anchors identity, layout, and lighting from both start and end frames.

  • Turbo temporal smoothing Reduces flicker and popping while preserving subject integrity at higher throughput.

  • Object and human-aware motion Protects faces, hands, hair, and thin structures while animating garments and props.

  • Layout-smart interpolation Respects depth, occlusion, and parallax for clean foreground/background motion.

  • Adaptive camera pathing Natural pans, push-ins, and dolly moves without warping.

  • Speed-optimized pipeline Faster than Pro at the same settings, perfect for rapid iteration.

Parameters

ParameterRequiredDescription
start_frameYesStarting image for the video
end_frameYesEnding image for the video
promptNoDescribe motion style, mood, or camera movement
durationNoVideo length in seconds (1–10)
resolutionNoOutput resolution: 540p, 720p, or 1080p
movement_amplitudeNoMotion intensity: auto, small, medium, or large
bgmNoEnable background music generation
seedNoRandom seed for reproducibility (-1 for random)

How to Use

  1. Upload start frame — the beginning image of your video.
  2. Upload end frame — the ending image of your video.
  3. Write a prompt (optional) — describe motion style, mood, or camera movement.
  4. Set duration — choose video length from 1 to 10 seconds.
  5. Select resolution — 540p, 720p, or 1080p based on quality needs.
  6. Enable BGM (optional) — add background music automatically.
  7. Set seed (optional) — use for reproducible results.
  8. Run — submit and download your video.

Pricing

ResolutionDurationPrice
540p1s$0.03
540p2s$0.04
540p3s$0.05
540p4s$0.06
540p5s$0.07
540p6s$0.08
540p7s$0.09
540p8s$0.10
540p9s$0.20
540p10s$0.30
720p1s$0.04
720p2s$0.05
720p3s$0.10
720p4s$0.15
720p5s$0.20
720p6s$0.25
720p7s$0.30
720p8s$0.35
720p9s$0.45
720p10s$0.50
1080p1s$0.175
1080p2s$0.225
1080p3s$0.275
1080p4s$0.325
1080p5s$0.375
1080p6s$0.425
1080p7s$0.475
1080p8s$0.525
1080p9s$0.625
1080p10s$0.725

Billing Rules

540p: $0.03 for 1s, +$0.01/s up to 8s, then $0.20 for 9s, $0.30 for 10s

720p: $0.04 for 1s, $0.05 for 2s, then +$0.05/s from 3s

1080p: $0.175 for 1s, then +$0.05/s up to 8s, then +$0.10/s for 9s-10s

Best Use Cases

  • Storyboarding and Concept Animation — Animate between keyframes to preview beats in seconds.
  • Scene Interpolation — Seamless bridges between shots with consistent style.
  • Before/After Visualization — Visualize transformations with smooth, controlled motion.
  • Film Pre-visualization — Explore blocking and camera moves early and often.
  • Transitions — Create smooth video transitions between key moments.

Pro Tips

  • For large pose or layout jumps, try shorter durations or insert intermediate keyframes.
  • Use consistent lighting and style between start and end frames for smoother interpolation.
  • Turbo generally returns faster than Pro at the same settings.
  • Add a prompt to guide the motion style and camera movement between frames.

Notes

  • Maximum duration is 10 seconds per generation.
  • Actual processing time depends on resolution, duration, and current queue load.
  • Ensure you have rights to all uploaded images.
  • For complex transformations, consider using intermediate keyframes.

Related Models

Note:This website uses AI models provided by third parties.

Start End To Video Q2 Turbo API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/vidu/start-end-to-video-q2-turbo 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 Start End To Video Q2 Turbo 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,
    "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/start-end-to-video-q2-turbo" \
  -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/start-end-to-video-q2-turbo";
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 ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
        "prompt": "A cinematic shot of a city at sunset, soft golden light",
        "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
        "last_image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
        "duration": 5,
        "resolution": "720p",
        "bgm": true,
        "movement_amplitude": "auto",
        "seed": -1
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
  `https://api.wavespeed.ai/api/v3/predictions/${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,
    "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/start-end-to-video-q2-turbo", 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)

Start End To Video Q2 Turbo API — Frequently asked questions

What is the Start End To Video Q2 Turbo API?

Start End To Video Q2 Turbo is a Vidu model for video generation from images, exposed as a REST API on WaveSpeedAI. Vidu Q2 Turbo Start-End to Video creates smooth Image-to-Video transitions between start and end images with fast high-quality results. 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 Start End To Video Q2 Turbo 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-start-end-to-video-q2-turbo.

How much does Start End To Video Q2 Turbo cost per run?

Start End To Video Q2 Turbo starts at $0.10 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 Start End To Video Q2 Turbo 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-start-end-to-video-q2-turbo.

How do I get started with the Start End To Video Q2 Turbo API?

Sign up for a free WaveSpeedAI account to claim starter credits, copy your API key from /accesskey, then call the endpoint shown in the API tab of the playground. The playground also auto-generates a code sample in Python, JavaScript, or cURL for the parameters you've set.

Can I use Start End To Video Q2 Turbo 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 Start End to Video Q2 Turbo | Fast Image-to-Video API on WaveSpeedAI