Vidu Start End To Video

Vidu Start End To Video

Playground

Vidu Start-End to Video generates smooth transition videos between specified start and end images.

Features

🌌 Vidu Start-End to Video

Vidu Start-End to Video generates smooth cinematic transitions between two specified images — turning a start and end frame into a 5-second, coherent video. Ideal for storyboarding, scene linking, and concept animation, it combines motion interpolation with prompt-guided realism for visually stunning results.

🌟 Why it stands out

• 🎞️ Bi-Frame Guided Generation Creates natural motion between the start and end image while maintaining subject integrity.

• ⚡ Temporal Coherence Ensures stable transitions with no flicker or frame artifacts.

• 🧠 Context-Aware Motion Uses the text prompt to guide the transformation direction and emotional tone.

• 🎬 Cinematic Realism Simulates real camera motion—zoom, pan, fade, or morph—matching your creative intent.

⚙️ Input Parameters

• prompt — Describe the transition or narrative.

• image — Upload the starting frame (JPEG/PNG).

• last_image — Upload the ending frame (JPEG/PNG).

• movement_amplitude — Controls the motion intensity within the transition:

  • auto – Automatically adjusts based on content.
  • small – Subtle, gentle motion for static or emotional scenes.
  • medium – Balanced camera and object movement.
  • large – Dynamic, cinematic transitions with stronger visual motion.

💰 Pricing

🚀 How to Use

1. 🖼️ Upload your start and end images.
2. ✍️ Write a prompt describing the desired motion.
3. 🎚️ Select movement_amplitude (auto, small, medium, or large).
4. ▶️ Click Run ($0.20) to generate your transition.
5. 💾 Preview and download your cinematic result.

💡 Pro Tips

• Keep both input images aligned in composition and perspective for best transitions.
• Use “medium” for natural storytelling and “large” for action or dramatic shifts.
• Describe visual elements like lighting, direction, or camera movement for finer control.

# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/vidu/start-end-to-video" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "movement_amplitude": "auto",
    "seed": -1
}'

# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"