Vidu Text To Video Q1

Vidu Text To Video Q1

Playground

Vidu Text to Video generates high-quality videos with exceptional visual quality and motion diversity

Features

Vidu text-to-video-q1

Vidu Q1 Text-to-Video is a high-end video generation model built on Shengshu Technology’s Vidu Q-series architecture. It transforms natural language prompts into cinematic 720p videos with exceptional realism, diverse motion, and consistent visual fidelity — optimized for creative professionals and production use.

Key Features

• High-Fidelity Generation Produces visually rich, detailed videos with natural lighting, textures, and depth.

• Motion Diversity Captures a wide range of subject and camera motion — from subtle gestures to complex dynamic scenes.

• Temporal Consistency Ensures frame-to-frame coherence and smooth motion transitions without flicker or distortion.

• Prompt-Driven Storytelling Understands complex prompts, generating coherent narrative flow and visual alignment with text.

• Cinematic Quality (720p) Designed for high-quality visual outputs suitable for editing, marketing, and storytelling.

Parameters

• prompt — Describe your desired scene, action, or atmosphere.

• movement_amplitude — Control the motion intensity:

  • auto – Adaptive movement based on scene content.
  • small – Subtle or static scenes.
  • medium – Balanced motion.
  • large – Dramatic or action-focused motion.

• style - choose general or anime.

• duration — 5 seconds per generation.

• seed — Optional; set a fixed number for reproducible results.

Pricing

How to Use

1. Write a clear and descriptive prompt explaining the scene.
2. Adjust movement_amplitude to match the desired motion level, and style of your video.
3. (Optional) Set a seed for consistent output.
4. Run the model to generate your 5-second 720p video.

Tips

• Keep prompts concise but descriptive — specify lighting, camera direction, and atmosphere.
• Use medium or large amplitude for cinematic movement.
• Suitable for short-form content, concept visualization, or creative production workflows.

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

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