Samila: A Generative Art Generator

TL;DR

Samila addresses the need for accessible, reproducible generative art by coupling a simple two-function mapping ($f_1$, $f_2$) of an initial point set $A_0$ to a transformed set $A_1$ under two random seeds. The method combines structured randomness with adjustable projection modes and I/O options, enabling repeatable yet diverse artworks and a coherent visual family when one seed varies. The work contributes a Python library, a formal randomness framework, and practical guidance for education and research in computational aesthetics, while outlining future directions including AI-driven generation and aesthetic metrics.

Abstract

Generative art merges creativity with computation, using algorithms to produce aesthetic works. This paper introduces Samila, a Python-based generative art library that employs mathematical functions and randomness to create visually compelling compositions. The system allows users to control the generation process through random seeds, function selections, and projection modes, enabling the exploration of randomness and artistic expression. By adjusting these parameters, artists can create diverse compositions that reflect intentionality and unpredictability. We demonstrate that Samila's outputs are uniquely determined by two random generation seeds, making regeneration nearly impossible without both. Additionally, altering the point generation functions while preserving the seed produces artworks with distinct graphical characteristics, forming a visual family. Samila serves as both a creative tool for artists and an educational resource for teaching mathematical and programming concepts. It also provides a platform for research in generative design and computational aesthetics. Future developments could include AI-driven generation and aesthetic evaluation metrics to enhance creative control and accessibility.

Figures (7)

• Figure 1: Example of Samila generative art.
• Figure 2: Samila artwork generation process. It started from a square of dense points and transformed them into the latent space to generate the artwork.
• Figure 3: An example of Samila artwork which has different point colors. This example was generated by user "meidefr" in our Discord channel.
• Figure 4: Effect of different plotting parameters on the artwork. In each of the columns, all the parameters except one that is mentioned are changed in different rows. In the column for the marker, we increased spot size and decreased step size to have fewer points with a bigger size for the sake of presenting the effect.
• Figure 5: Parse tree representation of the equation