Vidu Reference To Video Q2

Vidu Reference To Video Q2

Playground

Vidu Q2 is a new image-to-video (and reference-to-video) model that emphasizes subtle facial expressions, smooth push–pull camera moves.

Features

Vidu Q2 — Reference-to-Video Model

Vidu Q2 is Shengshu Technology’s new-generation reference-to-video model designed to transform one or multiple input images into expressive, cinematic videos. It excels at producing subtle facial motion, natural body dynamics, and camera-aware storytelling with a strong sense of realism.

🎬 What It Does

Vidu Q2 synthesizes short videos from one or several reference images guided by a text prompt. It’s ideal for turning still portraits or concept images into smooth motion clips — suitable for both creative storytelling and professional visual production.

✨ Key Features

• Smooth motion realism Subtle micro-expressions, eye movements, and breathing motions are reproduced authentically.
• Cinematic camera dynamics Built-in control of push/pull, pan, tilt, and zoom effects for scene depth and emotional tone.
• Multiple-image reference support Upload up to 6 reference images to guide pose, lighting, or perspective transitions.
• Flexible composition Choose from aspect ratios (16:9, 9:16, 4:3, 3:4, 1:1) for any platform.
• Motion amplitude control Select auto / small / medium / large to define the strength and style of movement.
• High fidelity output Consistent lighting, identity preservation, and accurate reference adherence even across complex motions.

🧩 Designed For

• Filmmakers & Storytellers: Bring still characters or concept art to life with controlled, cinematic motion.
• Advertising Creators: Generate short motion ads with precise control over composition and intensity.
• Artists & Illustrators: Animate hand-drawn or AI-generated portraits into dynamic living forms.
• Game & Animation Studios: Prototype visual narratives quickly using character or environment references.

⚙️ Parameters

💰 Pricing

🧠 Tips for Best Results

• Use consistent lighting and angles among reference images for smoother transitions.
• Write prompts that define camera motion, emotion, or scene tone clearly.
• “auto” movement amplitude works best for portrait-style animation; use “medium” or “large” for full-body or action scenes.
• For cinematic looks, pair 16:9 with 1080p and descriptive atmosphere prompts (e.g., “soft sunlight flickering through leaves”).

📎 Note

• If you didn’t upload images locally, ensure the image URLs are publicly accessible. Successfully loaded images will display as thumbnails in the interface.

# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/vidu/reference-to-video-q2" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "aspect_ratio": "16:9",
    "resolution": "720p",
    "duration": 5,
    "movement_amplitude": "auto",
    "seed": 0
}'

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