Vidu Image To Video Q2 Turbo API Documentation

Vidu Image To Video Q2 Turbo API Documentation

Playground

Vidu Q2 Turbo Image-to-Video turns a single image into smooth, cinematic motion with fast, high-quality output. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Vidu Q2 Turbo Image-to-Video turns a single reference image into a smooth, cinematic video. Turbo accelerates generation for faster turnaround while keeping motion clean and stable — great for transitions, product demos, and quick storytelling.

Why Choose This?

• Turbo-optimized pipeline Faster generation than Pro at the same settings, perfect for quick iteration.

• Temporal smoothing Cuts flicker and popping while keeping faces, hands, hair, and thin details intact.

• Depth-aware motion Respects occlusion and parallax for natural foreground/background separation.

• Cinematic camera paths Subtle pans, push-ins, and dollies without rubbery warps.

• Optional background music Auto-generate BGM for social-ready clips.

Parameters

How to Use

1. Upload your image — ensure the URL is accessible for preview.
2. Write a prompt — describe desired motion, mood, and camera movement.
3. Set duration — choose video length from 1 to 10 seconds.
4. Select resolution — 540p, 720p, or 1080p based on quality needs.
5. Adjust movement amplitude (optional) — control motion intensity.
6. Enable BGM (optional) — add background music automatically.
7. Set seed (optional) — use for reproducible results.
8. Run — submit and download your video.

Pricing

Pricing depends on the selected resolution and duration.

Billing Rules

• 540p: $0.03 for the first second, plus $0.01 per additional second.
• 720p: $0.04 for 1 second, $0.05 for 2 seconds, then $0.05 per additional second.
• 1080p: $0.175 for the first second, plus $0.05 per additional second.
• Supported duration: 1–10 seconds, in whole-second increments.
• Background music is not available for 9- or 10-second videos.

Best Use Cases

• Quick Iterations — Faster than Pro for rapid creative exploration.
• Social Media Content — Create engaging video clips from photos.
• Product Demos — Animate product images with cinematic motion.
• Transitions — Generate smooth video transitions from key frames.
• Storytelling — Transform story moments into dynamic video.

Pro Tips

• Use high-quality, well-lit images for best results.
• Be specific in your prompt about camera movement (pan, zoom, dolly).
• Start with “auto” amplitude, then adjust if motion is too subtle or strong.
• Turbo is generally faster than Pro at the same settings.
• Use smaller amplitude for portraits to avoid unnatural distortion.

Notes

• Maximum duration is 10 seconds per generation.
• Actual runtime depends on resolution, duration, movement amplitude, and queue load.
• Ensure you have the right to use the uploaded image in your project.
• Image URL must be accessible for preview to display correctly.

Related Models

• Vidu Q2 Pro Image-to-Video — Higher quality at slightly higher cost.
• Vidu Q2 Text-to-Video — Generate videos from text prompts only.
• LTX-2 19B Image-to-Video — Alternative I2V with audio support.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result

set -euo pipefail

export WAVESPEED_API_KEY="your-api-key"

REQUEST_BODY=$(cat <<'JSON'
{
  "prompt": "A cinematic ocean wave at sunrise, highly detailed",
  "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
  "duration": 5,
  "resolution": "720p",
  "bgm": true,
  "movement_amplitude": "auto"
}
JSON
)

# 1. Submit the prediction once. Never retry this request automatically:
# a retry after an unclear failure can create a second, billed task.
CHECK='The task may already exist. Check History or the predictions list before submitting again.'
if ! SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  --connect-timeout 10 --max-time 60 \
  -X POST "https://api.wavespeed.ai/api/v3/vidu/image-to-video-q2-turbo" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}"); then
  printf 'Submit failed. %s\n' "${CHECK}" >&2
  exit 1
fi

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

# 2. Poll until the prediction reaches a final status.
BODY_FILE=$(mktemp)
trap 'rm -f "${BODY_FILE}"' EXIT
while true; do
  # Transient errors (429, 5xx) are retried, honoring Retry-After.
  HTTP_CODE=$(curl --silent --show-error --fail-with-body \
    --connect-timeout 10 --max-time 60 --retry 5 --retry-delay 2 \
    --output "${BODY_FILE}" --write-out '%{http_code}' \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}" || true)
  case "${HTTP_CODE}" in
    2??) ;;
    000|429|5??)  # dropped connection or temporary error: keep polling
      printf 'Task %s: HTTP %s, polling again in 10s\n' "${PREDICTION_ID}" "${HTTP_CODE}" >&2
      sleep 10; continue ;;
    *) printf 'Task %s: HTTP %s\n' "${PREDICTION_ID}" "${HTTP_CODE}" >&2
      cat "${BODY_FILE}" >&2; exit 1 ;;
  esac
  RESULT=$(jq 'if type == "object" and has("data") then .data else . end' "${BODY_FILE}")
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  case "${STATUS}" in
    completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
    failed|cancelled|timeout|deleted)
      printf 'Task %s ended with status %s\n' "${PREDICTION_ID}" "${STATUS}" >&2
      printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    *) sleep 2 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Every model also accepts the global request options enable_sync_mode and enable_base64_output; see their pages for details.

Response Parameters

Result Request Parameters

Result Response Parameters