Seeding Diversity into AI Art

TL;DR

This paper introduces a method combining evolutionary algorithms with GANs and CLIP to enhance novelty and diversity in AI-generated art, addressing the lack of creativity and originality in traditional generative models.

Contribution

It proposes a novel hybrid approach that integrates evolutionary divergence with GANs and CLIP, promoting more creative and diverse AI art outputs.

Findings

Visual diversity can counteract GANs' tendency to produce similar images.

Evolutionary interventions improve the novelty of generated images.

The method increases both diversity and adherence to semantic prompts.

Abstract

This paper argues that generative art driven by conformance to a visual and/or semantic corpus lacks the necessary criteria to be considered creative. Among several issues identified in the literature, we focus on the fact that generative adversarial networks (GANs) that create a single image, in a vacuum, lack a concept of novelty regarding how their product differs from previously created ones. We envision that an algorithm that combines the novelty preservation mechanisms in evolutionary algorithms with the power of GANs can deliberately guide its creative process towards output that is both good and novel. In this paper, we use recent advances in image generation based on semantic prompts using OpenAI's CLIP model, interrupting the GAN's iterative process with short cycles of evolutionary divergent search. The results of evolution are then used to continue the GAN's iterative process; we hypothesise that this intervention will lead to more novel outputs. Testing our hypothesis using novelty search with local competition, a quality-diversity evolutionary algorithm that can increase visual diversity while maintaining quality in the form of adherence to the semantic prompt, we explore how different notions of visual diversity can affect both the process and the product of the algorithm. Results show that even a simplistic measure of visual diversity can help counter a drift towards similar images caused by the GAN. This first experiment opens a new direction for introducing higher intentionality and a more nuanced drive for GANs.