Vidu Q3 Reference To Video API Documentation

Vidu Q3 Reference To Video API Documentation

Playground

Vidu Q3 Reference-to-Video Mix generates multi-entity consistent videos from 1-4 reference images with text prompt guidance. Supports 360p to 1080p resolutions, up to 16 seconds duration, multiple aspect ratios, and optional audio generation. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Vidu Q3 Reference-to-Video generates cinematic video guided by multiple reference images and a text prompt. Upload one or more reference images to establish character identity, style, or scene elements — the model produces a cohesive, motion-consistent video that blends all provided references into a new scene.

Why Choose This?

• Multi-image reference generation Upload multiple reference images to combine characters, styles, or visual elements from different sources into a single coherent video.

• Character-consistent output The model preserves the identity, appearance, and style of subjects from your reference images throughout the generated clip.

• Optional audio generation Enable generate_audio to produce synchronized ambient sound and atmosphere alongside the video.

• Flexible resolution options Generate at 480p, 720p, or 1080p to match your quality and budget requirements.

• Reproducible results Use the seed parameter to lock in a specific output for exact reproduction.

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

Parameters

How to Use

1. Write your prompt — describe the scene, characters, camera movement, and atmosphere. Use the Prompt Enhancer for better results.
2. Upload your reference images — provide one or more images via URL or drag-and-drop. Click Add Item to add more.
3. Select aspect ratio — choose the format that fits your target platform.
4. Select resolution — 480p for lower cost, 720p or 1080p for higher quality.
5. Set duration — choose your desired clip length in seconds.
6. Enable audio (optional) — generate_audio is enabled by default; disable it if you only need video.
7. Set seed (optional) — fix the seed to reproduce a specific result in future runs.
8. Submit — generate, preview, and download your video.

Pricing

Billing Rules

• 480p: $0.07 per second
• 720p / 1080p: $0.154 per second (2.2× base rate)

Best Use Cases

• Character-Driven Storytelling — Place consistent characters from reference images into entirely new scenes.
• Social Media Content — Produce short-form video clips with consistent visual identity from reference photos.
• Marketing & Brand Video — Generate new scenes featuring consistent brand characters or products from reference imagery.
• Creative Concepting — Rapidly prototype multi-character or multi-element scenes for pitching and storyboarding.
• Style-Consistent Series — Maintain a unified visual style across multiple video generations using the same reference set.

Pro Tips

• Use clear, well-lit reference images with distinct subjects for the most accurate identity preservation.
• The more reference images you provide, the richer the model’s understanding of your intended style and characters.
• Disable generate_audio if you plan to add your own soundtrack in post-production.
• Fix the seed once you find a result you like to iterate consistently across resolution and duration changes.
• Use 480p to rapidly test your prompt and reference combination before committing to a higher-resolution render.

Notes

• Both prompt and images are required fields; all other parameters are optional.
• generate_audio is enabled by default — disable it explicitly if you do not need audio.
• Ensure image URLs are publicly accessible if using links rather than direct uploads.
• Please ensure your content complies with Vidu’s usage policies.

Related Models

• Vidu Q3 Image-to-Video Pro — Animate a single reference image into a cinematic video clip with Q3 Pro quality.
• Vidu Image-to-Video Q2 Pro — Previous generation Vidu Pro image-to-video model.
• Vidu One-Click V2 MV — One-click music video generation with Vidu.

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",
  "images": [
    "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
  ],
  "aspect_ratio": "16:9",
  "resolution": "720p",
  "duration": 5,
  "generate_audio": true
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/vidu/q3/reference-to-video" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}")

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 "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL=$(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' "${RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  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

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters