Reproduce “Samila: A Generative Art Generator” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Sadra Sabouri, Sepand Haghighi, Elena Masrour
Samila is a Python-based library developed to generate generative art by applying mathematical functions and controlled randomness. The system demonstrates how a combination of two specific random seeds can deterministically reproduce unique artworks, and how fixing one seed while varying the other creates "visual families" of art with shared graphical characteristics.
Key insights
- Generative art can achieve a balance between unpredictability and artistic intentionality through the careful implementation of controlled randomness.
- The use of a dual-seed mechanism allows for both the exact reproduction of a specific artwork and the systematic generation of 'visual families' that share underlying aesthetic and graphical characteristics.
- A structured algorithmic approach to constructing complex random mathematical equations, involving terms, operators, and pseudo-random functions, can reliably yield diverse and aesthetically compelling emergent patterns.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.