Kandinsky 2.2

Kandinsky 2.1 is a cutting-edge AI system that generates art based on user inputs. Launched by Sberbank and developed by SberAI, in collaboration with AIRIA and Sberdevices, It is named after the famous Russian abstract artist Wassily Kandinsky. It allows users to generate, edit, and manipulate images using various neural network functions, creating unique visual expressions from scratch or by modifying existing images.

Kandinsky is known for its creativity and artistic results but with the new update, it seems to be going more towards realism by default. It offers a higher base resolution (1024x1024), produces wider scenes, and more detail in general.

Its predecessor, Kandinsky 2.1 is a very creative model that produces interesting art. Although it can produce realistic images, it is not its strong suit. Kandinsky 2.2 takes a similar approach to Midjourney v5 and goes more towards realism. It is still capable of producing creative images, but if you give no direction, it tends to produce realistic images by default.

Kandinsky 2.2 is significantly better at fine details compared to 2.1 and seems to be favoring wider scenes in general. Kandinsky 2.1 is able to produce fine details on some scenes, especially close-ups, but it struggles when the shot gets wider or there is a need for too many fine details.

How to prompt?

If you're looking for a tool that can generate high-quality and versatile images, then Kandinsky 2.2 might be just what you need! Since the tool gives you realistic results by default, make sure to define the preferred image style in your prompt to get the best result. Apart from the subject and the style, you can set color theme, environment, lighting, camera angle, and any detail you like.