History
Malevich / Kandinsky 1.0
1.3B / 12B parameters — text‑to‑image generation at 256×256 resolution. Autoregressive approach, trained on Russian‑language data
Kandinsky 2.0 / 2.1
2B / 3.3B parameters — diffusion‑based generation. Supports 101 languages. Enables inpainting, outpainting, and image editing at resolution up to 768×768
Kandinsky 2.2
4.8B parameters — generates photorealistic images at 1024×1024 resolution. Supports ControlNet for precise editing and 4‑second video clips
Kandinsky 3.0
11.9B parameters — high‑fidelity image generation with improved text alignment
Kandinsky Video 1.0
17.5B parameters — generates 8‑second videos from text. Uses keyframe interpolation at 512×512 resolution
Kandinsky Flash / 3.1
Flash (11.9B) generates images in just 4 steps — 10× faster than standard diffusion. 3.1 (15.5B) uses Flash as a refiner to boost quality and adds cultural awareness for Russian‑language prompts
Kandinsky Video 1.1
17.5B parameters — generates 5.5‑second videos, trained on 4.6M text‑video pairs with captions generated by LLaVA‑1.5
Kandinsky 4.0
17.5B parameters — generates images and 12‑second videos from text, with audio generation conditioned on video input
Kandinsky 4.1
14B parameters — refined image generation with improved aesthetics, guided by expert artist feedback
Kandinsky 5.0
6B / 2B / 19B parameters — new family based on Flow Matching. Image Lite (6B) for HD generation and editing, Video Lite (2B) ranked #1 among open‑source models in its class, and Video Pro (19B) for HD video with strong text and Russian‑concept understanding
Kandinsky 6 Image Pro
The flagship: a Mixture‑of‑Experts image model, twice as fast as its predecessor, with free professional‑grade editing built in
Kandinsky 6.0 Video
3B / 29B parameters — foundation models for synchronized video and audio generation. 5‑second clips with 44 kHz audio and lip‑sync from text or an image, with built‑in super‑resolution to Full‑HD. Open source under the MIT license