TRACE: Time-Adaptive Residual Attention Control with Content-Style Decomposition for Training-Free Diffusion Style Transfer

arXiv:2610.04922 · cs.CV · Submitted 2026-10-04 · Read on arXiv

cs.CV

Submitted: 2026-10-04

Updated: 2026-10-04

Comments: Accepted to ACCV 2026

Code: https://github.com/pixelchemy-research/TRACE

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Trace — 1× in this paper · explained in 2 episodes

Sources

• Training-Free Reward-Guided Image Editing via Trajectory Optimal Control
• Diffusion Posterior Sampling for General Noisy Inverse Problems
• Diffusion Model Guided Sampling with Pixel-Wise Aleatoric Uncertainty Estimation
• Prompt-to-Prompt Image Editing with Cross Attention Control
• Classifier-Free Diffusion Guidance
• AttenST: A Training-Free Attention-Driven Style Transfer Framework with Pre-Trained Diffusion Models
• Diffusion-based Image Translation using Disentangled Style and Content Representation
• RB-Modulation: Training-Free Personalization of Diffusion Models using Stochastic Optimal Control
• Measuring Style Similarity in Diffusion Models
• Denoising Diffusion Implicit Models
• Score-Based Generative Modeling through Stochastic Differential Equations
• InstantStyle: Free Lunch towards Style-Preserving in Text-to-Image Generation

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models