Cover Image

UniCtrl: Improving the Spatiotemporal Consistency of Text-to-Video Diffusion Models via Training-Free Unified Attention Control

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Xia, Tian, Chen, Xuweiyi, Xu, Sihan
Format:	Preprint
Published:	2024
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

CtrlVDiff: Controllable Video Generation via Unified Multimodal Video Diffusion
by: Xi, Dianbing, et al.
Published: (2025)

UniGeo: Taming Video Diffusion for Unified Consistent Geometry Estimation
by: Sun, Yang-Tian, et al.
Published: (2025)

LightCtrl: Training-free Controllable Video Relighting
by: Peng, Yizuo, et al.
Published: (2026)

SAB3R: Semantic-Augmented Backbone in 3D Reconstruction
by: Chen, Xuweiyi, et al.
Published: (2025)

CameraCtrl: Enabling Camera Control for Text-to-Video Generation
by: He, Hao, et al.
Published: (2024)

UniAnimate: Taming Unified Video Diffusion Models for Consistent Human Image Animation
by: Wang, Xiang, et al.
Published: (2024)

Swap Attention in Spatiotemporal Diffusions for Text-to-Video Generation
by: Wang, Wenjing, et al.
Published: (2023)

SafeCtrl: Region-Based Safety Control for Text-to-Image Diffusion via Detect-Then-Suppress
by: Zhang, Lingyun, et al.
Published: (2025)

UniFL: Improve Latent Diffusion Model via Unified Feedback Learning
by: Zhang, Jiacheng, et al.
Published: (2024)

Semantic-Free Procedural 3D Shapes Are Surprisingly Good Teachers
by: Chen, Xuweiyi, et al.
Published: (2024)

SafeCtrl: Region-Aware Safety Control for Text-to-Image Diffusion via Detect-Then-Suppress
by: Zhang, Lingyun, et al.
Published: (2026)

TextCtrl: Diffusion-based Scene Text Editing with Prior Guidance Control
by: Zeng, Weichao, et al.
Published: (2024)

MotionCtrl: A Unified and Flexible Motion Controller for Video Generation
by: Wang, Zhouxia, et al.
Published: (2023)

CtrlAttack: A Unified Attack on World-Model Control in Diffusion Models
by: Xu, Shuhan, et al.
Published: (2026)

DualCamCtrl: Dual-Branch Diffusion Model for Geometry-Aware Camera-Controlled Video Generation
by: Zhang, Hongfei, et al.
Published: (2025)

Frame In-N-Out: Unbounded Controllable Image-to-Video Generation
by: Wang, Boyang, et al.
Published: (2025)

CameraCtrl II: Dynamic Scene Exploration via Camera-controlled Video Diffusion Models
by: He, Hao, et al.
Published: (2025)

ConfCtrl: Enabling Precise Camera Control in Video Diffusion via Confidence-Aware Interpolation
by: Yang, Liudi, et al.
Published: (2026)

CFG-Ctrl: Control-Based Classifier-Free Diffusion Guidance
by: Wang, Hanyang, et al.
Published: (2026)

AttriCtrl: Fine-Grained Control of Aesthetic Attribute Intensity in Diffusion Models
by: Chen, Die, et al.
Published: (2025)

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

Live2Diff: Live Stream Translation via Uni-directional Attention in Video Diffusion Models
by: Xing, Zhening, et al.
Published: (2024)

FreeTraj: Tuning-Free Trajectory Control in Video Diffusion Models
by: Qiu, Haonan, et al.
Published: (2024)

PhysCtrl: Generative Physics for Controllable and Physics-Grounded Video Generation
by: Wang, Chen, et al.
Published: (2025)

Ctrl-VI: Controllable Video Synthesis via Variational Inference
by: Duan, Haoyi, et al.
Published: (2025)

UniVidX: A Unified Multimodal Framework for Versatile Video Generation via Diffusion Priors
by: Chen, Houyuan, et al.
Published: (2026)

UniMLVG: Unified Framework for Multi-view Long Video Generation with Comprehensive Control Capabilities for Autonomous Driving
by: Chen, Rui, et al.
Published: (2024)

UniVBench: Towards Unified Evaluation for Video Foundation Models
by: Wei, Jianhui, et al.
Published: (2026)

UniGeo: Unifying Geometric Guidance for Camera-Controllable Image Editing via Video Models
by: Jiang, Hong, et al.
Published: (2026)

UniVid: The Open-Source Unified Video Model
by: Luo, Jiabin, et al.
Published: (2025)

RelaCtrl: Relevance-Guided Efficient Control for Diffusion Transformers
by: Cao, Ke, et al.
Published: (2025)

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

GaussCtrl: Multi-View Consistent Text-Driven 3D Gaussian Splatting Editing
by: Wu, Jing, et al.
Published: (2024)

LumiCtrl : Learning Illuminant Prompts for Lighting Control in Personalized Text-to-Image Models
by: Butt, Muhammad Atif, et al.
Published: (2025)

UniE2F: A Unified Diffusion Framework for Event-to-Frame Reconstruction with Video Foundation Models
by: Xu, Gang, et al.
Published: (2026)

VMix: Improving Text-to-Image Diffusion Model with Cross-Attention Mixing Control
by: Wu, Shaojin, et al.
Published: (2024)

UniVideo: Unified Understanding, Generation, and Editing for Videos
by: Wei, Cong, et al.
Published: (2025)

Ctrl123: Consistent Novel View Synthesis via Closed-Loop Transcription
by: Zhao, Hongxiang, et al.
Published: (2024)

ObjCtrl-2.5D: Training-free Object Control with Camera Poses
by: Wang, Zhouxia, et al.
Published: (2024)

TextGuider: Training-Free Guidance for Text Rendering via Attention Alignment
by: Baek, Kanghyun, et al.
Published: (2025)