paper-with-me

Papers

Characteristic Guidance: Non-linear Correction for Diffusion Model at Large Guidance Scale

2023-12-11 · Candi Zheng, Yuan Lan

Popular guidance for denoising diffusion probabilistic model (DDPM) linearly combines distinct conditional models together to provide enhanced control over samples. However, this approach overlooks nonlinear effects that become significant when guidance scale is large. To address this issue, we propose characteristic guidance, a guidance method that provides first-principle non-linear correction for classifier-free guidance. Such correction forces the guided DDPMs to respect the Fokker-Planck (FP) equation of diffusion process, in a way that is training-free and compatible with existing sampling methods. Experiments show that characteristic guidance enhances semantic characteristics of prompts and mitigate irregularities in image generation, proving effective in diverse applications ranging from simulating magnet phase transitions to latent space sampling.

📄 PDF Abstract BibTeX arXiv:2312.07586

Code (1)

scraed/CharacteristicGuidanceWebUI 공식 구현 pytorch

Tasks

DenoisingImage Generation

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Sparse Scheduled Diffusion Guidance for Inverse Problems

2026-03-09 · Abduragim Shtanchaev, Albina Ilina, Yazid Janati, Arip Asadulaev 외 arxiv

Pretrained diffusion models are effective priors for Bayesian inverse problems, but posterior sampling with these priors is often costly because data-consistency guidance is applied throughout the full reverse trajectory…

CFG-Ctrl: Control-Based Classifier-Free Diffusion Guidance

2026-03-03 · Hanyang Wang, Yiyang Liu, Jiawei Chi, Fangfu Liu 외 arxiv

Classifier-Free Guidance (CFG) has emerged as a central approach for enhancing semantic alignment in flow-based diffusion models. In this paper, we explore a unified framework called CFG-Ctrl, which reinterprets CFG as a…

Text-to-Image Generation

Geometry-Correct Diffusion Posterior Sampling with Denoiser-Pullback Curvature Guidance and Manifold-Aligned Damping

2026-05-27 · Seunghyeok Shin, Minwoo Kim, Dabin Kim, Hongki Lim arxiv

Diffusion posterior sampling conditions diffusion priors on measurements, but data-consistency updates are typically scaled by hand-tuned guidance weights and can destabilize sampling under stiff, operator-dependent curv…

MRI Reconstruction

The Unreasonable Effectiveness of Guidance for Diffusion Models

2024-11-15 · Tim Kaiser, Nikolas Adaloglou, Markus Kollmann

Guidance is an error-correcting technique used to improve the perceptual quality of images generated by diffusion models. Typically, the correction is achieved by linear extrapolation, using an auxiliary diffusion model …

Guiding Noisy Label Conditional Diffusion Models with Score-based Discriminator Correction

2025-08-27 · Dat Nguyen Cong, Hieu Tran Bao, Hoang Thanh-Tung arxiv

Diffusion models have gained prominence as state-of-the-art techniques for synthesizing images and videos, particularly due to their ability to scale effectively with large datasets. Recent studies have uncovered that th…