Kandinsky 6.0 Video

A free, open video model from Kandinsky Lab that makes 5-second clips with matching sound, including lip-synced speech, from a description or a photo. The large Pro version needs a data-centre GPU; the 3B Lite version suits a strong home GPU. Commercial use allowed.

Go to Kandinsky 6.0 Video’s website

Free to try?Yes

Can I sell what I make?Yes

Open or closedDownloadable, with conditions

Skill neededTechnical

The facts, with sources

Open or closed: Downloadable, with conditions
You can download and run it, but the licence limits use
Gated on Hugging Face: sign in and accept conditions.
source · checked 7 Nov 2026 · checked on the maker's own page
Licence: MIT (Permissive (e.g. Apache 2.0, MIT))
source · checked 7 Nov 2026 · checked on the maker's own page
Can I sell what I make?: Yes
MIT licence permits commercial use.
source · checked 7 Nov 2026 · checked on the maker's own page
Cost: Free option: Free to download; you pay for your own hardware
Plans below.
How you use it: On your own computer
Runs with Diffusers, ComfyUI, vLLM, SGLang or FastVideo. GPU memory not stated.
source · checked 7 Nov 2026 · checked, but the page was unclear or partial
Skill needed: Technical
source · checked 7 Nov 2026 · checked on the maker's own page
Made by: Kandinsky Lab
Card credits Team Kandinsky; no company or country stated on the card.
source · checked 7 Nov 2026 · checked, but the page was unclear or partial
Status: Available
Weights uploaded Sep 2026; paper (arXiv 2610.05608) dated 4 Oct 2026.
source · checked 7 Nov 2026 · checked, but the page was unclear or partial

What you can make with it

A video, from a description (main use)
A video, by bringing a photo to life
A video, a soundtrack or sound for a video

text to videoimage to video

Text-to-audio-video and image-to-audio-video; separate super-resolution model to 1080p.

source · checked 7 Nov 2026 · checked on the maker's own page

Plans and prices

No paid plans listed.

source · checked 7 Nov 2026 · checked on the maker's own page

Rights and safety

Limits: max video seconds: 5; note: 121 frames at 24 fps, generated at 864x480 then upscaled.
source · checked 7 Nov 2026 · checked on the maker's own page

Where you can run it

Hugging Face

Other options for “A video, from a description”

Adobe Express, Adobe Firefly, Adobe Premiere, Akool, Animoto, Arcads, Canva AI (Magic Studio), CapCut, Civitai, CogVideoX, ComfyUI, Creatify, DeeVid AI, DomoAI, Dreamina, Dzine, fal, Filmora, FlexClip, Fliki, FLORA, FLUX 3, Fotor, Gemini Omni 1.2 Flash

About this entry. Facts last checked 7 Nov 2026 against the maker’s own pages (each fact links to its source). Entry status: draft. Plain-English summary written by Plainly.

Spot an error? Tell us, with a link to the source. How corrections work