Minimax Hailuo 2.3 T2V Pro

Minimax Hailuo 2.3 T2V Pro

Playground

Hailuo 2.3 Pro - MiniMax’s next-generation AI video model ranked #2 globally. Features 2.5x efficiency improvement, 85% complex instruction response rate, and extreme physics simulation capabilities for professional-grade 1080p video generation.

Features

MiniMax Hailuo 2.3 — Text-to-Video (T2V) Pro

Hailuo 2.3 Pro is the premium text-to-video model from MiniMax, engineered for creators who demand cinematic realism, dynamic motion, and superior visual coherence. It transforms text prompts into richly detailed 5-second 1080p videos — merging professional-grade quality with cutting-edge physical simulation.

🎬 Why It Looks Great

• Cinematic Fidelity – Generates ultra-smooth motion, realistic lighting, and lifelike shadows in every frame.
• Advanced Physics & Scene Logic – Accurately models object dynamics, reflections, and camera movement.
• High Prompt Accuracy – Faithfully interprets natural-language descriptions with exceptional semantic precision.
• Consistent Characters – Maintains subject identity and spatial layout throughout the clip.
• Refined Aesthetic – Tuned for film-like color grading, depth, and atmosphere.

⚙️ Limits and Performance

• Input: text prompt only
• Output duration: fixed — 5 seconds
• Resolution: up to 1080p
• Processing time: approximately 40–70 seconds per job (depending on complexity and queue load)

💰 Pricing

🚀 How to Use

1. Write a clear text prompt describing your scene, characters, lighting, and motion. Example: “A traveler walks through a neon-lit rainy street at night, reflections glowing on wet pavement.”
2. Submit your job — no reference image required.
3. Wait for processing (typically under 1 minute).
4. Download your completed 5-second cinematic video.

💡 Pro Tips

• Use film-style language — include camera direction (wide shot, slow zoom, tracking).
• Mention lighting type (sunset glow, neon reflections, soft cinematic light).
• Keep prompts concise (1–2 sentences) for best fidelity.
• For stable subjects, include descriptors like same person or consistent background.

# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/minimax/hailuo-2.3/t2v-pro" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "enable_prompt_expansion": true
}'

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