Position: Universal Aesthetic Alignment Narrows Artistic Expression

TL;DR

This paper highlights systemic biases in aesthetic-aligned image generation models that favor conventional beauty and penalize anti-aesthetic outputs, limiting artistic diversity and user control.

Contribution

It constructs a broad aesthetics dataset and evaluates models revealing a bias towards conventional beauty and penalization of anti-aesthetic images.

Findings

Models default to beautiful outputs even when instructed otherwise

Reward models penalize anti-aesthetic images matching user prompts

Bias confirmed through image editing and artwork evaluation

Abstract

Over-aligning image generation models to a generalized aesthetic preference conflicts with user intent, particularly when "anti-aesthetic" outputs are requested for artistic or critical purposes. This adherence prioritizes developer-centered values, compromising user autonomy and aesthetic pluralism. We test this bias by constructing a wide-spectrum aesthetics dataset and evaluating state-of-the-art generation and reward models. This position paper finds that aesthetic-aligned generation models frequently default to conventionally beautiful outputs, failing to respect instructions for low-quality or negative imagery. Crucially, reward models penalize anti-aesthetic images even when they perfectly match the explicit user prompt. We confirm this systemic bias through image-to-image editing and evaluation against real abstract artworks. Our code, fine-tuned models, and datasets are available on our meta-expression intentionally anti-aesthetics webpage: https://weathon.github.io/icml2026_position/.