Image generationVideo

Kandinsky

Sber's Russian family of image and video generation models. Understands Russian-language prompts and Russian cultural context well; released under MIT.

Developer
Sber (Kandinsky Lab), Russia
First release
Nov 2022
Latest release
Jul 2026
Sizes
2B – 19B
License
Commercial use allowedApache 2.0 (versions 2.x–4), MIT (Kandinsky 5 and WM 1.0)
Russian
Supported
Running
On your own serverNeeds a GPU
Industries
Marketing and content, Media and production, Education, Public sector
Deploy on your server Hugging Face GitHub

What it does

  • Images from Russian-language descriptions
  • Short promo videos from text or a photo
  • Instruction-based image editing
  • Visuals for social media

Where it is used

Marketing and social mediaMedia and publishingEducationPublic sector and companies required to use Russian software

Hardware requirements

LaptopLaptop or regular PC, up to 8 GB of VRAM — smaller versions
no versions
1 GPUOne GPU with 16–80 GB — mid-size versions
fits
ClusterServer with several GPUs — flagship versions
no versions

Versions

  1. Kandinsky WM 1.0
  2. Kandinsky 5.0 Image Lite / Video Pro
  3. Kandinsky 5.0 Video Lite
  4. Kandinsky 4.0 Video Flash
  5. Kandinsky 3.0
  6. Kandinsky 2.2
  7. Kandinsky 2.1
  8. Kandinsky 2.0

How to run it

On your own serverWeights are downloaded from Hugging Face and served with vLLM (load and API) or llama.cpp (modest hardware). The model then runs in a closed network with no per-request fees.Hugging Face
How much hardware you needCalculate the VRAM for the model size, context length and number of concurrent requests.Open the hardware calculator

I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems.

Frequently asked questions

Can Kandinsky be used in a commercial project?

Yes. License: Apache 2.0 (versions 2.x–4), MIT (Kandinsky 5 and WM 1.0). It allows commercial use, but it is still worth having a lawyer review the license before launch.

What hardware does Kandinsky need?

At minimum: One GPU with 16–80 GB — mid-size versions. Without a GPU the model is not practical. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does Kandinsky support Russian?

Yes, Russian is listed on the model card.

Where can I download Kandinsky and what does it cost?

The Kandinsky weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.

How I deploy it for clients

  1. SelectionI pick the model size for your task and hardware and test it on your examples.
  2. DeploymentI deploy it on your server or in a closed network and provide an API.
  3. Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
  4. IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.

Comparisons

Similar models

Image generationFLUXBlack Forest Labs · GermanyCommercial use with conditions

Image generation from the creators of Stable Diffusion. Renders text in images well and keeps the composition.

DetailsVideoWanAlibaba · ChinaCommercial use allowed

Text-to-video and image-to-video; the small version runs on a gaming GPU. After 2.2 only applied models are open: editing (VACE), audio-driven talking characters (S2V), dancing to music (Dancer).

DetailsImage generationZ-ImageAlibaba (Tongyi-MAI) · ChinaCommercial use allowed

A compact 6B model with photorealism on par with large models. The Turbo version produces an image in a few steps on a regular gaming GPU.

Details

Source: huggingface.co/kandinskylab/Kandinsky-5.0-T2I-Lite. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.