FAQ — Kandinsky 5.0 Video Pro

Kandinsky 5.0 Video Pro is a large-scale video diffusion model built for professional video generation. It focuses on visual fidelity, motion stability, and precise semantic control, with text to video and image to video on kandinsky50.com.

Text to video creates a clip from a written description. Image to video starts from a still and adds motion while keeping composition aligned. Pick text for new scenes; pick image when the subject or product frame must stay consistent.

Upload a JPG, PNG, or WEBP still, set aspect ratio, and submit a motion prompt. The service returns a task you can poll until the MP4 is ready—see Image to Video.

Generated assets are standard MP4 videos suitable for web, social, and editing pipelines.

Time varies with queue and length. The dashboard shows live status while your task is processing.

Pricing and credits are listed on our Pricing page. New users typically start with a small credit pack.

The developer API is not connected yet. Use the website for text to video and image to video. We will publish API docs when programmatic access is ready.