Saved in:
Bibliographic Details
Main Authors: Ruan, Bo-Kai, Ni, Zi-Xiang, Huang, Bo-Lun, Hsiao, Teng-Fang, Shuai, Hong-Han
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.20808
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916973929037824
author Ruan, Bo-Kai
Ni, Zi-Xiang
Huang, Bo-Lun
Hsiao, Teng-Fang
Shuai, Hong-Han
author_facet Ruan, Bo-Kai
Ni, Zi-Xiang
Huang, Bo-Lun
Hsiao, Teng-Fang
Shuai, Hong-Han
contents Diffusion models achieve impressive performance in high-fidelity image generation but often struggle with rare concepts that appear infrequently in the training distribution. Prior work attempts to address this issue by prompt switching, where generation begins with a frequent proxy prompt and later transitions to the original rare prompt. However, such designs typically rely on fixed schedules that disregard the model's internal dynamics, making them brittle across prompts and backbones. In this paper, we re-frame rare prompt generation through the lens of score replacement: the denoising trajectory of a rare prompt can be initially guided by the score of a semantically related frequent prompt, which acts as a proxy. However, as the process unfolds, the proxy score gradually diverges from the true rare prompt score. To control this drift, we introduce a bounded deviation criterion that triggers the switch once the deviation exceeds a threshold. This formulation offers both a principled justification and a practical mechanism for rare prompt generation, enabling adaptive switching that can be widely adopted by different models. Extensive experiments across SDXL, SD3, Flux, and Sana confirm that our method consistently improves rare concept synthesis, outperforming strong baselines in both automated metrics and human evaluations.
format Preprint
id arxiv_https___arxiv_org_abs_2505_20808
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Score Replacement with Bounded Deviation for Rare Prompt Generation
Ruan, Bo-Kai
Ni, Zi-Xiang
Huang, Bo-Lun
Hsiao, Teng-Fang
Shuai, Hong-Han
Computer Vision and Pattern Recognition
Diffusion models achieve impressive performance in high-fidelity image generation but often struggle with rare concepts that appear infrequently in the training distribution. Prior work attempts to address this issue by prompt switching, where generation begins with a frequent proxy prompt and later transitions to the original rare prompt. However, such designs typically rely on fixed schedules that disregard the model's internal dynamics, making them brittle across prompts and backbones. In this paper, we re-frame rare prompt generation through the lens of score replacement: the denoising trajectory of a rare prompt can be initially guided by the score of a semantically related frequent prompt, which acts as a proxy. However, as the process unfolds, the proxy score gradually diverges from the true rare prompt score. To control this drift, we introduce a bounded deviation criterion that triggers the switch once the deviation exceeds a threshold. This formulation offers both a principled justification and a practical mechanism for rare prompt generation, enabling adaptive switching that can be widely adopted by different models. Extensive experiments across SDXL, SD3, Flux, and Sana confirm that our method consistently improves rare concept synthesis, outperforming strong baselines in both automated metrics and human evaluations.
title Score Replacement with Bounded Deviation for Rare Prompt Generation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.20808