Vidu Text To Video Q2

Vidu Text To Video Q2

Playground

ViduQ2 Text to Video generates high-quality videos with exceptional visual quality and motion diversity

Features

Vidu Text-to-Video Q2 — Prompt-to-Clip (Preview)

Vidu Q2 turns your text prompts into short cinematic clips with coherent motion, balanced lighting, and reliable scene composition. It supports style presets, multiple aspect ratios, motion intensity control, and optional background music. Ideal for ads, social posts, explainers, and quick concept reels. Very suitable for animation creation.

✨ Highlights

• Fast, stable motion with clear details and smooth camera paths.
• Style presets + aspect ratios for platform-ready framing.
• Motion amplitude to dial in subtle vs. energetic movement.
• Optional BGM for instant, shareable clips.

🧩 Parameters

• prompt* (text) — Describe subject, setting, lighting, camera, and action.
• style (dropdown) — general and animate .
• resolution (dropdown) — 360p, 540p, 720p, 1080p.
• duration (seconds slider) — up to 8s.
• aspect_ratio (dropdown) - 4:3 or 3:4
• movement_amplitude (dropdown) — low, medium, high.
• bgm (checkbox) — enable background music.

🚀 How to Use

1. **Write the prompt — subject + camera + lighting + motion.
2. Pick a style (general or animate).
3. Choose resolution and aspect_ratio for your target platform.
4. Set duration (seconds).
5. Adjust movement_amplitude (low for subtle, high for dynamic).
6. Toggle bgm if you want background music baked in.
7. Click Run to generate and download your clip.

💰 Pricing

🧠 Prompting Tips

• Start with subject + action + camera (“tracking shot of…”, “handheld close-up…”) and add lighting (“neon backlight”, “golden-hour sun”).
• Use movement_amplitude instead of stuffing the prompt with motion words—cleaner results.
• Keep style words minimal; let style preset and resolution do the heavy lifting.

Note

• The style means the model has been specifically optimized for the particular scenario. It does not represent the final generated result. The final effect still needs to be specified in the prompt (general or anime).

# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/vidu/text-to-video-q2" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "style": "general",
    "resolution": "720p",
    "duration": 5,
    "aspect_ratio": "4:3",
    "movement_amplitude": "auto",
    "bgm": true
}'

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