We introduce CADE 2.5 (Comfy Adaptive Detail Enhancer), a sampler-level guidance stack for SD/SDXL latent diffusion models. The central module, ZeResFDG, unifies (i) frequency-decoupled guidance that reweights low- and high-frequency components of the guidance signal, (ii) energy rescaling that matches the per-sample magnitude of the guided prediction to the positive branch, and (iii) zero-projection that removes the component parallel to the unconditional direction. A lightweight spectral EMA with hysteresis switches between a conservative and a detail-seeking mode as structure crystallizes during sampling. Across SD/SDXL samplers, ZeResFDG improves sharpness, prompt adherence, and artifact control at moderate guidance scales without any retraining. In addition, we employ a training-free inference-time stabilizer, QSilk Micrograin Stabilizer (quantile clamp + depth/edge-gated micro-detail injection), which improves robustness and yields natural high-frequency micro-texture at high resolutions with negligible overhead. For completeness we note that the same rule is compatible with alternative parameterizations (e.g., velocity), which we briefly discuss in the Appendix; however, this paper focuses on SD/SDXL latent diffusion models.

翻译：本文介绍CADE 2.5（Comfy Adaptive Detail Enhancer），一种面向SD/SDXL潜在扩散模型的采样器级引导堆栈。其核心模块ZeResFDG整合了三个关键技术：（i）频率解耦引导，对引导信号的低频与高频分量进行重新加权；（ii）能量重缩放，使每个样本的引导预测幅度与正向分支相匹配；（iii）零投影，移除与无条件方向平行的分量。通过带滞后效应的轻量级频谱指数移动平均，在采样过程中随着结构逐渐成形，系统会在保守模式与细节增强模式之间自动切换。在各类SD/SDXL采样器中，ZeResFDG能在中等引导尺度下显著提升图像锐度、提示词遵循度与伪影控制能力，且无需任何重新训练。此外，我们采用免训练的推理时稳定器——QSilk微粒度稳定器（分位数钳位+深度/边缘门控的微细节注入），该技术能提升模型鲁棒性，并在高分辨率下生成自然的高频微纹理，且计算开销可忽略。为保持完整性，我们指出该规则同样兼容其他参数化形式（如速度参数化），附录将对此进行简要讨论；但本文主要聚焦于SD/SDXL潜在扩散模型。