用不确定性引导生成，让文本提示更稳定地影响图像质量。
SoftCFG: Uncertainty-guided Stable Guidance for Visual Autoregressive Model
- 根据每个生成片段的置信度动态调整提示强度
- 在ImageNet上达成自回归模型最佳FID（13.8）
- 无需训练，可直接插入现有图像生成流程
自回归（AR）模型通过将图像建模为离散标记序列，成为强大的图像生成工具。尽管无分类器引导（CFG）已被用于提升条件生成效果，但在AR模型中仍面临两大问题：引导信号随解码过程快速衰减，以及强条件导致视觉不连贯。为此，我们提出SoftCFG，一种基于不确定性的推理方法，可在序列所有标记上分布自适应扰动。其核心思想是让每个生成标记按置信度贡献加权引导信号，确保信号持续传递并调和文本提示与视觉上下文间的冲突。为进一步稳定长序列生成，引入步骤归一化机制，限制SoftCFG累积扰动。该方法无需训练、模型无关，可无缝集成至现有AR生成流程。实验表明，SoftCFG显著优于标准CFG，在ImageNet 256×256上达到自回归模型最优的FID分数（13.8）。
原文摘要 · Abstract (English)
Autoregressive (AR) models have emerged as powerful tools for image generation by modeling images as sequences of discrete tokens. While Classifier-Free Guidance (CFG) has been adopted to improve conditional generation, its application in AR models faces two key issues: guidance diminishing, where the conditional-unconditional gap quickly vanishes as decoding progresses, and over-guidance, where strong conditions distort visual coherence. To address these challenges, we propose SoftCFG, an uncertainty-guided inference method that distributes adaptive perturbations across all tokens in the sequence. The key idea behind SoftCFG is to let each generated token contribute certainty-weighted guidance, ensuring that the signal persists across steps while resolving conflicts between text guidance and visual context. To further stabilize long-sequence generation, we introduce Step Normalization, which bounds cumulative perturbations of SoftCFG. Our method is training-free, model-agnostic, and seamlessly integrates with existing AR pipelines. Experiments show that SoftCFG significantly improves image quality over standard CFG and achieves state-of-the-art FID on ImageNet 256*256 among autoregressive models.
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。