Kandinsky 2Translation site

A non-generative LLM model that learns by watching videos. It produces excellent recognition and detection results

A classic voice reader that will read your text with ease

An open-source AI tool that generates natural voices from text using a model with 600 million parameters. Create your own voice

A new way to transform and edit your videos using pre-trained text-image diffusion models. Project on GitHub

Animate portraits with a single image. This AI lets you quickly obtain realistic results via precise settings and a wide variety of styles

Generate 3D models from text (prompt). Benefit from 2D diffusion and 3D data consistency