Vidu Reference To Video Q1

Vidu Reference To Video Q1

Playground

Generate videos from reference images while keeping characters, objects, and scene identity consistent using Multi-Entity Consistency. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Vidu Reference-to-Video Q1

Vidu Reference-to-Video Q1 generates high-quality 5-second videos guided by multiple reference images. It combines advanced appearance preservation and motion synthesis, allowing creators to animate characters, products, or scenes while maintaining their original identity and style.

🌟 Key Features

🔁 Multi-Entity Consistency

• Preserves the visual identity, color tone, and texture of all reference subjects.
• Supports consistent appearance across dynamic motion sequences.
• Ideal for animating characters, fashion items, or branded products.

🧩 Flexible Input Options

• Accepts 1–7 reference images to define the subject, outfit, or style.
• Supports aspect ratios 16:9, 9:16, and 1:1.
• Adjustable movement amplitude (auto, small, medium, large) for customized motion intensity.

🎥 Cinematic Motion Generation

• Adds smooth camera motion and ambient scene transitions.
• Creates realistic parallax effects and subject movement.
• Works well with both portraits and product shots.

⚙️ Requirements

Images

• Count: 1–7 reference images
• Formats: PNG, JPEG, JPG
• Aspect ratio: Between 1:4 and 4:1
• Max file size: 50 MB per image

Prompt

• Max length: 1500 characters

• Describe desired motion, scene, or style.

  Example: “The girl in image 2 wears the glasses from image 1 and walks through a sunny street, soft natural light, cinematic color tone.”

💰 Price

💡 Best Practices

1. Use clear, high-resolution reference images for optimal appearance consistency.
2. Describe the desired motion and scene context in detail.
3. Experiment with movement amplitude to adjust animation style.
4. Include multiple reference images for complex scenes or multi-object compositions.
5. Keep visual themes consistent (lighting, color palette, resolution).

⚠️ Effect Boundaries

• Works best with realistic, well-lit images.
• Overly stylized or low-quality inputs may cause flickering or distortion.
• Movement amplitude directly affects scene dynamics and smoothness.
• Complex multi-character prompts may require more references for stability.

📝 Notes

• Make sure each uploaded image is accessible and properly formatted.
• Check that the prompt and image order correspond correctly (e.g., “image 1,” “image 2”).
• If outputs look inconsistent, simplify the scene or reduce reference count.
• Simple, focused prompts yield the best alignment and motion results.

# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/vidu/reference-to-video-q1" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "aspect_ratio": "16:9",
    "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}"