Overview
Kandinsky 2 is a multilingual text2image latent diffusion model that generates high-quality images from text prompts. It uses a combination of text encoders, diffusion image prior, and latent diffusion U-Net to produce visually appealing results.
Multilingual Text Encoding
Kandinsky 2 uses a combination of text encoders to support multiple languages.
Diffusion Image Prior
Kandinsky 2 uses a diffusion image prior to generate high-quality images.
Latent Diffusion U-Net
Kandinsky 2 uses a latent diffusion U-Net to produce visually appealing results.
Get started
- Open the official website and confirm the service is available in your region.
- Check the current plan, usage limits and terms for your intended use.
- Try a small task with sample data before committing to a paid plan.
Editorial note
Pricing checked: Sep 20, 2026. Tiered plans available. Review current pricing and subscription options on the official website.
Record updated: Sep 20, 2026
Suggest a correction
