Imagen de Portada

FreeControl: Efficient, Training-Free Structural Control via One-Step Attention Extraction

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Lin, Jiang, Chen, Xinyu, Wu, Song, Zhang, Zhiqiu, Zhang, Jizhi, Wang, Ye, Tang, Qiang, Wang, Qian, Yang, Jian, Yi, Zili
Formato:	Preprint
Publicado:	2025
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

SimInsert: Seamless Video Object Insertion via Regional Sparse Attention Fusion
por: Chen, Xinyu, et al.
Publicado: (2026)

Inversion-Free Video Style Transfer with Trajectory Reset Attention Control and Content-Style Bridging
por: Lin, Jiang, et al.
Publicado: (2025)

Region-to-Region: Enhancing Generative Image Harmonization with Adaptive Regional Injection
por: Zhang, Zhiqiu, et al.
Publicado: (2025)

Security Is Relative: Training-Free Vulnerability Detection via Multi-Agent Behavioral Contract Synthesis
por: Wang, Yongchao, et al.
Publicado: (2026)

RichControl: Structure- and Appearance-Rich Training-Free Spatial Control for Text-to-Image Generation
por: Pang, Lexi, et al.
Publicado: (2025)

One-to-More: High-Fidelity Training-Free Anomaly Generation with Attention Control
por: Rao, Haoxiang, et al.
Publicado: (2026)

SwitchCraft: Training-Free Multi-Event Video Generation with Attention Controls
por: Xu, Qianxun, et al.
Publicado: (2026)

Training-Free Multi-Step Inference for Target Speaker Extraction
por: You, Zhenghai, et al.
Publicado: (2026)

When to Lock Attention: Training-Free KV Control in Video Diffusion
por: Zeng, Tianyi, et al.
Publicado: (2026)

A Control Architecture for Training-Free Memory Use
por: Lu, Yanzhen, et al.
Publicado: (2026)

LASER: Tuning-Free LLM-Driven Attention Control for Efficient Text-conditioned Image-to-Animation
por: Zheng, Haoyu, et al.
Publicado: (2024)

Training-Free Open-Ended Object Detection and Segmentation via Attention as Prompts
por: Lin, Zhiwei, et al.
Publicado: (2024)

SpotActor: Training-Free Layout-Controlled Consistent Image Generation
por: Wang, Jiahao, et al.
Publicado: (2024)

OSTAF: A One-Shot Tuning Method for Improved Attribute-Focused T2I Personalization
por: Wang, Ye, et al.
Publicado: (2024)

Tuning-free Instruction-based Video Editing Via Structural Noise Initialization and Guidance
por: Wu, Song, et al.
Publicado: (2026)

One-Step Diffusion Transformer for Controllable Real-World Image Super-Resolution
por: Fang, Yushun, et al.
Publicado: (2025)

MotionClone: Training-Free Motion Cloning for Controllable Video Generation
por: Ling, Pengyang, et al.
Publicado: (2024)

A Training-Free Approach for Multi-ID Customization via Attention Adjustment and Spatial Control
por: Lin, Jiawei, et al.
Publicado: (2025)

FreeText: Training-Free Text Rendering in Diffusion Transformers via Attention Localization and Spectral Glyph Injection
por: Zhang, Ruiqiang, et al.
Publicado: (2026)

One-Shot Learning for Pose-Guided Person Image Synthesis in the Wild
por: Fan, Dongqi, et al.
Publicado: (2024)

FreeInsert: Personalized Object Insertion with Geometric and Style Control
por: Zhang, Yuhong, et al.
Publicado: (2025)

TripVVT: A Large-Scale Triplet Dataset and a Coarse-Mask Baseline for In-the-Wild Video Virtual Try-On
por: Shao, Dingbao, et al.
Publicado: (2026)

Numerical Analysis of Free Play-Induced Aeroelastic Phenomena: A Numerical Approach With Adaptive Step Size Control
por: Yu Qijing, et al.
Publicado: (2024)

Tuning-Free Visual Customization via View Iterative Self-Attention Control
por: Li, Xiaojie, et al.
Publicado: (2024)

TOFA: Training-Free One-Shot Federated Adaptation for Vision-Language Models
por: Zhang, Li, et al.
Publicado: (2025)

Training Free Guided Flow Matching with Optimal Control
por: Wang, Luran, et al.
Publicado: (2024)

$h$-control: Training-Free Camera Control via Block-Conditional Gibbs Refinement
por: Wang, Yuzhu, et al.
Publicado: (2026)

Vision‐Aided Damage Detection With Convolutional Multihead Self‐Attention Neural Network: A Novel Framework for Damage Information Extraction and Fusion
por: Yiming Zhang, et al.
Publicado: (2025)

Efficient Interfacial Electrical Energy Extraction of a Triboelectric Nanogenerator by the Charge Lock‐Free Strategy
por: Hongyu Yi, et al.
Publicado: (2025)

VividFace: High-Quality and Efficient One-Step Diffusion For Video Face Enhancement
por: Zhang, Shulian, et al.
Publicado: (2025)

One‐Pot Single‐Step Approach for the Controlled Synthesis of Multifunctional Microparticles
por: Bingbing Xie, et al.
Publicado: (2025)

A Training-Free Framework for Video License Plate Tracking and Recognition with Only One-Shot
por: Ding, Haoxuan, et al.
Publicado: (2024)

TalkPhoto: A Versatile Training-Free Conversational Assistant for Intelligent Image Editing
por: Hu, Yujie, et al.
Publicado: (2026)

AlphaFlowTSE: One-Step Generative Target Speaker Extraction via Conditional AlphaFlow
por: Li, Duojia, et al.
Publicado: (2026)

Spore: Efficient and Training-Free Privacy Extraction Attack on LLMs via Inference-Time Hybrid Probing
por: Cui, Yu, et al.
Publicado: (2026)

FIS-DiT: Breaking the Few-Step Video Inference Barrier via Training-Free Frame Interleaved Sparsity
por: Tang, Jian, et al.
Publicado: (2026)

Noise Consistency Training: A Native Approach for One-Step Generator in Learning Additional Controls
por: Luo, Yihong, et al.
Publicado: (2025)

ISAC: Training-Free Instance-to-Semantic Attention Control for Improving Multi-Instance Generation
por: Jo, Sanghyun, et al.
Publicado: (2025)

Dual-Channel Attention Guidance for Training-Free Image Editing Control in Diffusion Transformers
por: Li, Guandong
Publicado: (2026)

Adding Additional Control to One-Step Diffusion with Joint Distribution Matching
por: Luo, Yihong, et al.
Publicado: (2025)