Kandinsky 5 Pro

Kandinsky 5 Pro Text-to-Video

Kandinsky 5 Pro Text-to-Video is a production-ready text-to-video model that generates dynamic 5-second MP4 clips from a single prompt. It’s optimized for fast iteration and clean, prompt-faithful motion, with simple controls for resolution and aspect ratio.

Why it stands out

• 5-second text-to-video generation Turn a prompt into a complete short clip—ideal for rapid concept testing and social-ready outputs.

• Two resolution tiers Choose 512P for faster, cheaper drafts or 1024P for sharper detail.

• Creator-friendly aspect ratios Built-in framing for 3:2, 1:1, and 2:3 to match common feed and creative formats.

• Fast, stable inference Designed for predictable performance in real-world pipelines and batch experimentation.

Parameters

How to use

1. Write a clear prompt describing the subject, action, environment, and style.
2. Select aspect_ratio for your delivery format (landscape, square, or portrait).
3. Choose resolution: 512P for quick drafts, 1024P for final detail.
4. Run the model and download the generated MP4.

Prompt tips

• Use clear verbs for motion: “walks,” “turns,” “sparks fly,” “camera pans slowly.”
• Keep the structure simple: subject → action → scene → lighting → style.
• For stronger coherence, describe one main shot rather than multiple scene changes.

Pricing

All videos are 5 seconds.

Use Cases

• Social media short clips and creative testing
• Storyboarding and previsualization
• Marketing concept drafts and ad iterations
• Stylized motion scenes for presentations and demos