Civiverse: A Dataset for Analyzing User Engagement with Open-Source Text-to-Image Models

TL;DR

This paper introduces the Civiverse dataset for analyzing user engagement with open-source text-to-image models, revealing preferences for explicit content and semantic homogenization, highlighting societal issues in AI-generated visuals.

Contribution

It provides the first systematic cultural analysis of open-source TTI platforms using a large-scale prompt dataset, revealing user behaviors and societal biases.

Findings

Predominance of explicit content generation

Semantic homogenization of prompts

Potential reinforcement of stereotypes

Abstract

Text-to-image (TTI) systems, particularly those utilizing open-source frameworks, have become increasingly prevalent in the production of Artificial Intelligence (AI)-generated visuals. While existing literature has explored various problematic aspects of TTI technologies, such as bias in generated content, intellectual property concerns, and the reinforcement of harmful stereotypes, open-source TTI frameworks have not yet been systematically examined from a cultural perspective. This study addresses this gap by analyzing the CivitAI platform, a leading open-source platform dedicated to TTI AI. We introduce the Civiverse prompt dataset, encompassing millions of images and related metadata. We focus on prompt analysis, specifically examining the semantic characteristics of text prompts, as it is crucial for addressing societal issues related to generative technologies. This analysis provides insights into user intentions, preferences, and behaviors, which in turn shape the outputs of these models. Our findings reveal a predominant preference for generating explicit content, along with a focus on homogenization of semantic content. These insights underscore the need for further research into the perpetuation of misogyny, harmful stereotypes, and the uniformity of visual culture within these models.