Vidu Start End To Video Q1 API Documentation

Vidu Start End To Video Q1 API Documentation

Playground

Vidu Q1 Start-End To Video turns specified start and end images into smooth image-to-video transitions for morphs and scene fades. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Vidu Q1 Start-End to Video generates smooth, coherent motion sequences between a specified start frame and end frame, transforming static images into cinematic 5-second transitions. Built on the Vidu Q-series architecture, it delivers high-quality motion interpolation, making it ideal for professional storytelling, editing, and scene development.

Key Features

• Bi-frame Guided Synthesis Generates realistic motion by interpreting both start and end frames, ensuring a seamless visual flow.

• Strong Narrative Continuity Preserves scene logic and emotional tone across frames, maintaining coherent storytelling through motion.

• Object- and Human-Aware Motion Handles complex transitions involving people, objects, and environments with spatial consistency and natural dynamics.

• Adaptive Camera Behavior Simulates camera pans, zooms, or layout changes to achieve cinematic motion depth.

• High-Fidelity Quality (720p) Provides production-ready visuals with accurate textures, lighting, and temporal consistency.

Use Cases

• Storyboarding and concept animation
• Scene interpolation for long-form content or cinematic projects
• Instructional or educational visual transitions
• Film previsualization and creative prototyping

Pricing

How to Use

1. Upload your start frame and end frame (JPEG/PNG).
2. Optionally include a prompt describing the desired motion or transition style. 3.4. Click Run to generate your cinematic transition video and download it.

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",
  "last_image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
}
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-q1" \
  -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 "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"

# 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|deleted) printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    *) sleep 2 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters