提出首个针对单流扩散Transformer的可控概念删除方法，解决生成崩溃问题。
Z-Erase: Enabling Concept Erasure in Single-Stream Diffusion Transformers
- 设计解耦更新框架，使已有删除方法适配单流模型
- 引入拉格朗日引导的自适应调节机制，平衡删除与保留
- 理论证明可收敛至帕累托平稳点，适合安全可控生成场景
概念删除是文本到图像模型中移除不希望内容的重要安全机制。尽管在U-Net和双流架构（如Flux）中已广泛研究，但在新兴的单流扩散变压器范式（如Z-Image）中仍缺乏探索。在该范式下，文本和图像标记通过共享参数作为统一序列处理，直接应用已有删除方法常导致生成崩溃。为此，我们提出Z-Erase，首个专为单流T2I模型设计的概念删除方法。为保证生成稳定性，Z-Erase首先提出流解耦概念删除框架，解耦更新过程，使现有方法适用于单流模型。在此框架内，进一步引入拉格朗日引导的自适应删除调制算法，更优地平衡敏感的删除-保留权衡。此外，我们提供严格的收敛分析，证明Z-Erase可收敛至帕累托平稳点。实验表明，Z-Erase成功克服生成崩溃问题，在多种任务上达到当前最优性能。
原文摘要 · Abstract (English)
Concept erasure serves as a vital safety mechanism for removing unwanted concepts from text-to-image (T2I) models. While extensively studied in U-Net and dual-stream architectures (e.g., Flux), this task remains under-explored in the recent emerging paradigm of single-stream diffusion transformers (e.g., Z-Image). In this new paradigm, text and image tokens are processed as a single unified sequence via shared parameters. Consequently, directly applying prior erasure methods typically leads to generation collapse. To bridge this gap, we introduce Z-Erase, the first concept erasure method tailored for single-stream T2I models. To guarantee stable image generation, Z-Erase first proposes a Stream Disentangled Concept Erasure Framework that decouples updates and enables existing methods on single-stream models. Subsequently, within this framework, we introduce Lagrangian-Guided Adaptive Erasure Modulation, a constrained algorithm that further balances the sensitive erasure-preservation trade-off. Moreover, we provide a rigorous convergence analysis proving that Z-Erase can converge to a Pareto stationary point. Experiments demonstrate that Z-Erase successfully overcomes the generation collapse issue, achieving state-of-the-art performance across a wide range of tasks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。