cs.CVNov 16, 2026

Trait Collapse in Text-to-Image Generation: Evaluating and Mitigating Personality Inconsistency in Visual Storytelling

Authors: Yuanbo Tong, Haoyuan Li, Jibiao Jiang, Zirui Wang, Yuchen Li, Jiamou Liu

Organizations: School of Computer Science, The University of Auckland Auckland, New Zealand

Abstract

In visual storytelling, a believable character must not only look consistent across scenes but also behave in ways that reflect their personality. Current text-to-image (T2I) models preserve visual appearance effectively, yet consistently fail to maintain personality-relevant behavior---a failure we term trait collapse. We show that conventional metrics (CLIP Score, DINO similarity) are blind to this failure, and that abstract personality descriptors and scene-level emotion labels do not produce consistent improvements over neutral prompts across models. To systematically diagnose trait collapse, we introduce ViStoryBench-Personality, a story-level benchmark combining an expert-validated Visual Cues Lexicon (Fleiss' κ=0.757κ= 0.757) with a six-dimensional metric suite covering personality alignment, cross-scene stability, and behavioral coherence. Evaluating seven T2I systems, we confirm a persistent semantic gap between abstract trait labels and visual evidence, and find that visual identity consistency does not imply personality consistency. To bridge this gap, we propose Trait-Behavior-Visual (TBV), a training-free prompting framework that decomposes personality traits into renderable visual constraints. TBV improves Personality Alignment Score by up to +22.1%+22.1\%, with larger gains in models with stronger language-conditioning capacity.

Figures & tables

Appendix figures & tables20 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. PIPBench: A Profile-Inclusive Framework for Personalized Image Generation Evaluation

    Jul 7, 2026Yuhang Wu, Shuxiang Zhang, Wee Hian Ching +2Image GenerationSynthetic Benchmark Generation