All YIN No YANG

Artistic proposal that seeks to build a dialogue between contemporary Machine Learning methods for image generation and the process of individuation, understood as articulating the becoming of form. The varieties of formal divergence made possible using text-to-image diffusion models are explored, probing the efficacy of using semantic descriptions as a constraint to parameterise aesthetic variation within an original dataset of oil paintings. Research collaboration with Iulia Ionescu and Murad Khan, a moving image and performative experiment. 

Arandas, L., Ionescu, I., Khan, M., Grierson, M., Carvalhais, M. (2025). All YIN No YANG: Geometric Abstraction of Oil Paintings with Trained Models, Noise and Self-reference. In: Machado, P., Johnson, C., Santos, I. (eds) Artificial Intelligence in Music, Sound, Art and Design. EvoMUSART 2025. Lecture Notes in Computer Science, vol 15611. Springer, Cham. https://doi.org/10.1007/978-3-031-90167-6_17.

Arandas, L., Ionescu, I., Khan, M., Grierson, M., Carvalhais, M. (2023). All YIN No YANG: Automating Language-guided Diffusion Systems in Search of Abstraction. Book of abstracts "Explorations in Sound and New Media Art Conference" (ESNMAC). Published, artes.porto.ucp.pt.