These pictures were made with a compositional pattern-producing network (CPPN, top) and Stable Diffusion (SD, bottom). With this approach based on neural networks, we’ve achieved a much higher degree of personalization, allowing us to cater to our designers’ needs, and we are constantly working to improve it. The browser is used only for input-output. Since then, everything has been generated in a K8s GPU cluster using P圜harm and Datalore for local and remote development. In 2020, we released our first tool based on deep neural networks. Splash screens that were created using WebGL. The images below were created with this approach. At first, we mainly used WebGL-based tools, which generated everything randomly in the browser on the fly (the interactive archive is available here ). ![]() The history of internal tools for generating art at JetBrains starts about a decade ago. Our mission is to free graphic designers from routine tasks so they can concentrate on their core competence – creativity. At JetBrains, we are constantly refining our approach to creating pieces of art for use as website elements and release graphics.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |