paper-with-me

홈 › Papers

CADE 2.5 - ZeResFDG: Frequency-Decoupled, Rescaled and Zero-Projected Guidance for SD/SDXL Latent Diffusion Models

2025-10-14 · Denis Rychkovskiy arxiv

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.

📄 PDF Abstract BibTeX arXiv:2510.12954

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Stability and selective extinction in complex mutualistic networks

2021-06-14 · Hyun Woo Lee, Jae Woo Lee, Deok-Sun Lee

We study species abundance in the empirical plant-pollinator mutualistic networks exhibiting broad degree distributions, with uniform intra-group competition assumed, by the Lotka-Volterra equation. The stability of a fi…

FUSE: Label-Free Image-Event Joint Monocular Depth Estimation via Frequency-Decoupled Alignment and Degradation-Robust Fusion

2025-03-25 · Pihai Sun, Junjun Jiang, Yuanqi Yao, Youyu Chen 외

Image-event joint depth estimation methods leverage complementary modalities for robust perception, yet face challenges in generalizability stemming from two factors: 1) limited annotated image-event-depth datasets causi…

Depth EstimationMonocular Depth EstimationTransfer Learning

Achieving Stability and Optimality: Control Strategy for a Wind Turbine Supplying an Electrolyzer in the Islanded Storage-less Microgrid

2025-01-15 · Bosen Yang, Kang Ma, Jin Lin, Mingjun Zhang 외

Wind power generation supplying electrolyzers in islanded microgrids is an essential technical pathway for green hydrogen production, attracting growing attention in the transition towards net zero carbon emissions. Both…

Scale-invariant Gaussian derivative residual networks

2026-03-03 · Andrzej Perzanowski, Tony Lindeberg arxiv

Generalisation across image scales remains a fundamental challenge for deep networks, which often fail to handle images at scales not seen during training (the out-of-distribution problem). In this paper, we present prov…

Scale Generalisation

Fast and Scalable Structural SVM with Slack Rescaling

2015-10-20 · Heejin Choi, Ofer Meshi, Nathan Srebro

We present an efficient method for training slack-rescaled structural SVM. Although finding the most violating label in a margin-rescaled formulation is often easy since the target function decomposes with respect to the…