CADE 2.5 - ZeResFDG: Frequency-Decoupled, Rescaled and Zero-Projected Guidance for SD/SDXL Latent Diffusion Models
On the map: Diffusion models → Diffusion foundations and sampling
Abstract (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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 6 of its 7 references that are in the map. First posted on arXiv 14 Oct 2025.
Builds on
6 of 7 references.
Closest ancestors · 6
Same direction, newest first
- 2025Guidance in the Frequency Domain Enables High-Fidelity Sampling at Low CFG Scales24 Jun
- 2025Normalized Attention Guidance: Universal Negative Guidance for Diffusion Models27 May
- 2024Eliminating Oversaturation and Artifacts of High Guidance Scales in Diffusion Models3 Oct
- 2024Applying Guidance in a Limited Interval Improves Sample and Distribution Quality in Diffusion Models11 Apr
- 2024Self-Rectifying Diffusion Sampling with Perturbed-Attention Guidance26 Mar
- 2022Improving Sample Quality of Diffusion Models Using Self-Attention Guidance3 Oct
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025EMAG: Self-Rectifying Diffusion Sampling with Exponential Moving Average Guidance
- 2026Spectral Guidance for Flexible and Efficient Control of Diffusion Models
- 2026Plug-and-Play Guidance for Discrete Diffusion Models via Gradient-Informed Logit Correction
- 2026Error as Signal: Stiffness-Aware Diffusion Sampling via Embedded Runge-Kutta Guidance
- 2023Characteristic Guidance: Non-linear Correction for Diffusion Model at Large Guidance Scale
- 2025Feedback Guidance of Diffusion Models
- 2025Tortoise and Hare Guidance: Accelerating Diffusion Model Inference with Multirate Integration
- 2026On the Robustness of Distribution Support under Diffusion Guidance