Text-to-image diffusion models excel at generating high-quality images from natural language descriptions but often fail to preserve subject consistency across multiple outputs, limiting their use in visual storytelling. Existing approaches rely on model fine-tuning or image conditioning, which are computationally expensive and require per-subject optimization. 1Prompt1Story, a training-free approach, concatenates all scene descriptions into a single prompt and rescales token embeddings, but it suffers from semantic leakage, where embeddings across frames become entangled, causing text misalignment. In this paper, we propose a simple yet effective training-free approach that addresses semantic entanglement from a geometric perspective by refining text embeddings to suppress unwanted semantics. Extensive experiments prove that our approach significantly improves both subject consistency and text alignment over existing baselines.
@article{arxiv.2512.16443,
title = {Geometric Disentanglement of Text Embeddings for Subject-Consistent Text-to-Image Generation using A Single Prompt},
author = {Shangxun Li and Youngjung Uh},
journal= {arXiv preprint arXiv:2512.16443},
year = {2026}
}