AI has seen a boost by the introduction of Transformers. This new Machine Learning paradigm uses attention to reflect context in language, music and images. 

One of the most legendary new models for Generative AI, GPT has become a new benchmark for Generative AI and has sparked innovation and competition in this field. 

Aleph Alpha from Germany takes the model even further by using a multimodal approach, that integrates text and image information, just like humans can do. 

With multimodal models it is possible not only to archive better image recognition, but to generate texts and images that are undistinguishable from human creations. So called Generative AI supports creative humans in writing, music and art to experiment and create with combinations that were not possible before.

Even though this field of research is still in it’s infancy, it throws a light beam on a future, where AI-created music will be a commodity like a spotify playlist.