Kandinsky5
4 modes on this page
Kandinsky5 turns a text prompt into a video clip. Pick a mode, write the prompt, run it in the studio.
Input
FormMode
Prompt*
Aspect Ratio
Duration
Result
PreviewMotion preview, not Kandinsky5 output
$0.05 per video·~90s
What Kandinsky5 is for
Kandinsky5 from Sber turns a written prompt into a short video clip. Runtime is about 90 seconds and compute is $0.05 per video. Modes on this page: Text to Video (Distill), Text to Video, Image to Video, and Text to Video. It is a clip generator, not a full training-video editor.
Kandinsky5 is billed in Knowlify credits at the compute cost ($0.05 per video). A typical run is about 90 seconds. Published rate: Your request will cost $0.05 for a 5-second video and $0.10 for a 10-second video, regardless of resolution.
Pick Kandinsky5 for text to video at $0.05 per video and ~90s. Compare it with Argil Avatar, Bernini R, Cogvideox 5b on the related cards below if you need a different look, speed, or input type.
How to use Kandinsky5
- 1. Upload the still Kandinsky5 should start from, then write the change or motion in Input.
- 2. Run it. The prompt and file hand off to the Knowlify studio, where Kandinsky5 generates.
- 3. Stay in the studio if you want that frame or clip inside a longer narrated video.
What you need
- A prompt that names the subject, camera move, and lighting.
- A source still (PNG or JPG) for the model to start from.
- Aspect Ratio (3:2, 1:1, 2:3).
- Duration (5s, 10s).
Example prompt
a husky team running across frozen lake, breath clouds, dark studio product, one hard key, glossy, no text, no watermark
Frequently asked questions
How do I run Kandinsky5?
Run Kandinsky5 on Knowlify at /generate/kandinsky5. This page has 4 modes in one dropdown. Write the prompt on this page and it opens in the studio, where Kandinsky5 generates a short clip. The same studio also turns documents into full narrated videos.
Where can I use Kandinsky5 online?
On Knowlify (Sber's model, knowlify.com/generate/kandinsky5). You do not need a separate playground. Kandinsky5 runs in the studio next to document-to-video.
Can I make a longer video with Kandinsky5?
Kandinsky5 itself produces a short clip. On Knowlify you can take that output, or skip it and upload a document, and generate a full narrated video with a script you can edit.
What do I need to run Kandinsky5?
A prompt and a source still. Kandinsky5 will not invent the starting frame for you on this mode.
How long does Kandinsky5 take?
Plan on about 90 seconds for a typical run, then whatever queue time the studio has. Video models sit at the high end of that range.
Does Kandinsky5 have more than one mode?
Yes. This page has 4 modes: Text to Video (Distill), Text to Video, Image to Video, and Text to Video. Switch them in the Mode dropdown instead of opening a new URL.
What does Kandinsky5 cost?
Your request will cost $0.05 for a 5-second video and $0.10 for a 10-second video, regardless of resolution. Knowlify charges this as credits, at the compute cost.
What is Kandinsky5 best for?
Kandinsky 5.0 Distilled is a lightweight diffusion model for fast, high-quality text-to-video generation. It turns a text prompt into a video clip.
Do I need an account to use Kandinsky5?
Yes. Kandinsky5 runs in the Knowlify studio, which needs a free account. Anything you type on this page comes with you.