The Kandinsky 2.1 block is an open-source multilingual image generation model. It is best used to create high-resolution portraits given a text description in any language.

The Kandinsky 2.1 block has 1 input and 1 output.

Inputs:

  • Text: This input is the multilingual description of the image the model should generate. It is best to use artistic references and art styles in this prompt.

Output:

  • Image: The response returns the generated image from the Kandinsky 2.1 model based on the text input.