[AI Journey track] Generative models for 3D content

The lecture is about generative artificial intelligence in 5 main directions: 1. Text: generating texts using GigaChat and cases of its application. 2. Music: generative music with SymFormer and the possibilities of generative singing of neural networks. 3. Images: creating images based on a text and the ability to work with the Kandinsky 3.0 neural network. 4. Video: global trends in neural networks that create videos based on a text, as well as examples of Kandinsky Video’s work. 5. 3D: generative artificial intelligence in extended reality including customization of 3D-objects based on a text, fast 3D-scanning of the real world and generation of 3D-objects and 3D-scenes using neural networks.