Although text-to-image diffusion models generally exhibit strong prompt-following ability, we identify a persistent and previously underexplored failure pattern in which a small subset of prompts d...
<p><strong>Tác giả:</strong> Yifan Yuan, Xiangyu Liu, Hongming Shan, Yu Han, Yu Jiang, Hao Tan, Junping Zhang, Linlin Shen</p>
<p>Although text-to-image diffusion models generally exhibit strong prompt-following ability, we identify a persistent and previously underexplored failure pattern in which a small subset of prompts differing only in the object consistently fails to realize the same target concept under identical generation settings. We term this phenomenon object-dependent concept brittleness. Such cases suggest systematic internal blind spots rather than random sampling noise. In this paper, we present an inte...</p>
<p>📄 DOI: <a href="https://doi.org/https://doi.org/10.1145/3767308.3835084" target="_blank" rel="noopener">https://doi.org/10.1145/3767308.3835084</a></p>
<p>📖 <a href="https://doi.org/https://doi.org/10.1145/3767308.3835084" target="_blank" rel="noopener">Xem bài báo đầy đủ</a></p>
Bài viết được biên soạn lại bởi LIFVietnam. Nguồn tham khảo: OpenAlex
