Creative AI – Image to image translation into practice
Hours and dates
- Oct 29 from 10:00 to 17:00
AboutThe Algorithmic Gaze
Frederik De Bleser & Lieven Menschaert are part of the The Algorithmic Gaze’s team.The applications of artificial intelligence are everywhere: just think of image recognition, recommendation algorithms, voice and face recognition algorithms, … In the arts, AI also leads to interesting results, however often by using powerful hardware or existing datasets, and thus beyond the reach or control of most artists.Our mission is to bring AI into the artist’s practice by developing open-source tools and methodologies that make the domain more accessible and transparent. Our research asks how AI can become a trusted partner in the creative process, both during creation and execution. We explore how AI understands the materiality of body, space and time. Our approach avoids megalomanic datasets; instead we focus on carefully self-assembled datasets and an intuitive visual understanding of algorithms to avoid the bias inherent in large-scale models and take ownership of our own “small AI.”Frederik De Bleser is a researcher and lecturer at Sint Lucas Antwerp. His research focuses on the connection between art and technology and the development of free software tools for generative design, data visualization and artificial intelligence.Lieven Menschaert is a researcher and lecturer at Sint Lucas Antwerp and LUCA school of arts. His main interest is in generative and computational design and thus sees AI and machine learning as the logical next step in a procedural generation practice.
Workshops and MasterclassesCreative AI
Machine learning for creative purposes has progressed in leaps and bounds in the last years. But the whole process still feels like black magic. What does it take to train your own model? How do you even get started? And how can you use this process creatively?
During this workshop we’ll introduce some works made with creative AI and explore what it could mean for an artistic practice. We’ll go over the different steps on how to train an image-to-image model based on a dataset. The goal is to work together as a group to build one or two machine learning models.
This workshop is based on the research and tools developed by “The Algorithmic Gaze”, such as Figment, to get the data ready for training.
Participants should bring their own laptop. If you have an interesting, medium-size dataset (2000+ images) you can bring that as well.