CVApr 19, 2025

The Path to Reconciling Quality and Safety in Text-to-Image Generation: Dataset, Method, and Evaluation

arXiv:2504.14290v21 citationsh-index: 8
Originality Highly original
AI Analysis

This addresses a fundamental challenge in deploying safe and high-quality text-to-image models, with incremental improvements in alignment methods.

The paper tackles the trade-off between safety and quality in text-to-image generation by introducing a unified framework with a new dataset, algorithm, and evaluation metric, achieving state-of-the-art safety alignment while better maintaining generation quality.

Content safety is a fundamental challenge for text-to-image (T2I) models, yet prevailing methods enforce a debilitating trade-off between safety and generation quality. We argue that mitigating this trade-off hinges on addressing systemic challenges in current T2I safety alignment across data, methods, and evaluation protocols. To this end, we introduce a unified framework for synergistic safety alignment. First, to overcome the flawed data paradigm that provides biased optimization signals, we develop LibraAlign-100K, the first large-scale dataset with dual annotations for safety and quality. Second, to address the myopic optimization of existing methods focus solely on safety reward, we propose Synergistic Preference Optimization (T2I-SPO), a novel alignment algorithm that extends the DPO paradigm with a composite reward function that integrates generation safety and quality to holistically model user preferences. Finally, to overcome the limitations of quality-agnostic and binary evaluation in current protocols, we introduce the Unified Alignment Score, a holistic, fine-grained metric that fairly quantifies the balance between safety and generative capability. Extensive experiments demonstrate that T2I-SPO achieves state-of-the-art safety alignment against a wide range of NSFW concepts, while better maintaining the model's generation quality and general capability

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes