Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: May 14, 2026

Three-Dimensional Mapping of the Rotation of Interactive Virtual Objects with Eye-Tracking Data
06:36

Three-Dimensional Mapping of the Rotation of Interactive Virtual Objects with Eye-Tracking Data

Published on: October 18, 2024

DGADiff: Decoupled Guide Attention with Diffusion Model for Portrait Stylization.

Yi Ren1, Zihan Shen2, Junchao Fan3

  • 1School of Transportation and Logistics Engineering, Wuhan University of Technology, Wuhan 430070, China.

Sensors (Basel, Switzerland)
|May 13, 2026
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

HiPro-AD: Sparse Trajectory Transformer for End-to-End Autonomous Driving with Hybrid Spatiotemporal Attention.

Sensors (Basel, Switzerland)·2026
Same author

YOLO-FFRD: Dynamic Small-Scale Pedestrian Detection Algorithm Based on Feature Fusion and Rediffusion Structure.

Sensors (Basel, Switzerland)·2025
Same author

Elucidating subcellular architecture and dynamics at isotropic 100-nm resolution with 4Pi-SIM.

Nature methods·2024
Same author

Terahertz scanning near-field optical microscopy for biomedical detection: Recent advances, challenges, and future perspectives.

Biotechnology advances·2024
Same author

Enhanced Detection and Recognition of Road Objects in Infrared Imaging Using Multi-Scale Self-Attention.

Sensors (Basel, Switzerland)·2024
Same author

Performance degradation study of NiCo<sub>2</sub>O<sub>4</sub>-based asymmetric supercapacitors.

RSC advances·2023
Same journal

Enhancing Unsupervised Multi-Source Domain Adaptation for Person Re-Identification via Mixture of Experts and Graph-Based Relation.

Sensors (Basel, Switzerland)·2026
Same journal

Development of an Instrumented Glove for Palmar Pressure Assessment in Kayakers.

Sensors (Basel, Switzerland)·2026
Same journal

Development and Experimental Validation of an Autonomous IoT-Based Monitoring System for Real-Time Water Quality Assessment in the Amazon River.

Sensors (Basel, Switzerland)·2026
Same journal

Semi-Supervised Adversarial Learning Framework for Controller Area Network Bus Intrusion Detection.

Sensors (Basel, Switzerland)·2026
Same journal

Smart Optimization Method for Safety Signs in Innovative Manufacturing Environments Integrating Industrial Field IoT Sensors and Knowledge Graphs.

Sensors (Basel, Switzerland)·2026
Same journal

Three-Dimensional Modeling and Performance Analysis of Dynamic mmWave V2I Networks Based on Stochastic Geometry.

Sensors (Basel, Switzerland)·2026
See all related articles

DGADiff enhances portrait stylization using a diffusion model and a novel Decoupled Guide Attention Mechanism (DGA) to prevent pattern drift. This training-free framework achieves accurate fine-grained facial style transfer.

Area of Science:

  • Computer Vision
  • Artificial Intelligence
  • Image Processing

Background:

  • Diffusion models have advanced portrait stylization.
  • Lack of clear supervisory signals causes pattern drift in target portraits.

Purpose of the Study:

  • Introduce DGADiff, a training-free stylization framework.
  • Address pattern drift and improve fine-grained facial style transfer.

Main Methods:

  • Leverage a pre-trained latent consistency model (LCM) for efficient feature sampling.
  • Design a Decoupled Guide Attention Mechanism (DGA) to disentangle U-Net attention.
  • Separate attention into self-attention and masked-attention tracks for accurate style pattern transfer.

Main Results:

Keywords:
decoupled guide attentiondiffusion modelimage generationlatent consistency model

More Related Videos

Group Synchronization During Collaborative Drawing Using Functional Near-Infrared Spectroscopy
07:53

Group Synchronization During Collaborative Drawing Using Functional Near-Infrared Spectroscopy

Published on: August 5, 2022

Diffusion Tensor Magnetic Resonance Imaging in the Analysis of Neurodegenerative Diseases
09:33

Diffusion Tensor Magnetic Resonance Imaging in the Analysis of Neurodegenerative Diseases

Published on: July 28, 2013

Related Experiment Videos

Last Updated: May 14, 2026

Three-Dimensional Mapping of the Rotation of Interactive Virtual Objects with Eye-Tracking Data
06:36

Three-Dimensional Mapping of the Rotation of Interactive Virtual Objects with Eye-Tracking Data

Published on: October 18, 2024

Group Synchronization During Collaborative Drawing Using Functional Near-Infrared Spectroscopy
07:53

Group Synchronization During Collaborative Drawing Using Functional Near-Infrared Spectroscopy

Published on: August 5, 2022

Diffusion Tensor Magnetic Resonance Imaging in the Analysis of Neurodegenerative Diseases
09:33

Diffusion Tensor Magnetic Resonance Imaging in the Analysis of Neurodegenerative Diseases

Published on: July 28, 2013

  • DGADiff achieves favorable results across multiple metrics.
  • Demonstrates effectiveness in content-to-style and style-to-content multi-domain tasks.
  • Spatial attention decoupling proves effective for portrait stylization.

Conclusions:

  • DGADiff successfully overcomes pattern drift in diffusion-based portrait stylization.
  • The Decoupled Guide Attention Mechanism enables accurate fine-grained style transfer.
  • The framework offers an effective training-free solution for portrait stylization.