Copertina

SwitchCraft: Training-Free Multi-Event Video Generation with Attention Controls

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Xu, Qianxun, Song, Chenxi, Cai, Yujun, Zhang, Chi
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

FlowDirector: Training-Free Flow Steering for Precise Text-to-Video Editing
di: Li, Guangzhao, et al.
Pubblicazione: (2025)

CRAFT-LoRA: Content-Style Personalization via Rank-Constrained Adaptation and Training-Free Fusion
di: Li, Yu, et al.
Pubblicazione: (2026)

Free-Lunch Long Video Generation via Layer-Adaptive O.O.D Correction
di: Tian, Jiahao, et al.
Pubblicazione: (2026)

When and Where do Events Switch in Multi-Event Video Generation?
di: Liao, Ruotong, et al.
Pubblicazione: (2025)

FreeSwim: Revisiting Sliding-Window Attention Mechanisms for Training-Free Ultra-High-Resolution Video Generation
di: Wu, Yunfeng, et al.
Pubblicazione: (2025)

EventVAD: Training-Free Event-Aware Video Anomaly Detection
di: Shao, Yihua, et al.
Pubblicazione: (2025)

FreeControl: Efficient, Training-Free Structural Control via One-Step Attention Extraction
di: Lin, Jiang, et al.
Pubblicazione: (2025)

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

Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutation
di: Yang, Shuo, et al.
Pubblicazione: (2025)

FreeLong: Training-Free Long Video Generation with SpectralBlend Temporal Attention
di: Lu, Yu, et al.
Pubblicazione: (2024)

PAS: A Training-Free Stabilizer for Temporal Encoding in Video LLMs
di: Sun, Bowen, et al.
Pubblicazione: (2025)

RealCraft: Attention Control as A Tool for Zero-Shot Consistent Video Editing
di: Jin, Shutong, et al.
Pubblicazione: (2023)

TS-Attn: Temporal-wise Separable Attention for Multi-Event Video Generation
di: Zhang, Hongyu, et al.
Pubblicazione: (2026)

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

SocialDirector: Training-Free Social Interaction Control for Multi-Person Video Generation
di: Ouyang, Liangyang, et al.
Pubblicazione: (2026)

Taming Video Models for 3D and 4D Generation via Zero-Shot Camera Control
di: Song, Chenxi, et al.
Pubblicazione: (2025)

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

UniCtrl: Improving the Spatiotemporal Consistency of Text-to-Video Diffusion Models via Training-Free Unified Attention Control
di: Xia, Tian, et al.
Pubblicazione: (2024)

TIMI: Training-Free Image-to-3D Multi-Instance Generation with Spatial Fidelity
di: Cai, Xiao, et al.
Pubblicazione: (2026)

Interspatial Attention for Efficient 4D Human Video Generation
di: Shao, Ruizhi, et al.
Pubblicazione: (2025)

Mind the Time: Temporally-Controlled Multi-Event Video Generation
di: Wu, Ziyi, et al.
Pubblicazione: (2024)

DiTCtrl: Exploring Attention Control in Multi-Modal Diffusion Transformer for Tuning-Free Multi-Prompt Longer Video Generation
di: Cai, Minghong, et al.
Pubblicazione: (2024)

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

AlignVid: Training-Free Attention Scaling for Semantic Fidelity in Text-Guided Image-to-Video Generation
di: Liu, Yexin, et al.
Pubblicazione: (2025)

KGEdit: Ambiguity-Aware Knowledge Graphs for Training-Free Precise Video Generation and Editing
di: Cai, Mingshu, et al.
Pubblicazione: (2026)

MotionCraft: Crafting Whole-Body Motion with Plug-and-Play Multimodal Controls
di: Bian, Yuxuan, et al.
Pubblicazione: (2024)

FreeLong++: Training-Free Long Video Generation via Multi-band SpectralFusion
di: Lu, Yu, et al.
Pubblicazione: (2025)

Decomposed Attention Fusion in MLLMs for Training-Free Video Reasoning Segmentation
di: Han, Su Ho, et al.
Pubblicazione: (2025)

BachVid: Training-Free Video Generation with Consistent Background and Character
di: Yan, Han, et al.
Pubblicazione: (2025)

Prompt Relay: Inference-Time Temporal Control for Multi-Event Video Generation
di: Chen, Gordon, et al.
Pubblicazione: (2026)

LLaVA-MLB: Mitigating and Leveraging Attention Bias for Training-Free Video LLMs
di: Shen, Leqi, et al.
Pubblicazione: (2025)

FreeSpec: Training-Free Long Video Generation via Singular-Spectrum Reconstruction
di: Chen, Fangda, et al.
Pubblicazione: (2026)

LVSA: Training-Free Sparse Attention for Long Video Diffusion
di: Glorian, Gael, et al.
Pubblicazione: (2026)

Towards Generalized and Training-Free Text-Guided Semantic Manipulation
di: Hong, Yu, et al.
Pubblicazione: (2025)

EVDI++: Event-based Video Deblurring and Interpolation via Self-Supervised Learning
di: Zhang, Chi, et al.
Pubblicazione: (2025)

AnimateAnything: Consistent and Controllable Animation for Video Generation
di: Lei, Guojun, et al.
Pubblicazione: (2024)

High-Quality Cloud-Free Optical Image Synthesis Using Multi-Temporal SAR and Contaminated Optical Data
di: Duan, Chenxi
Pubblicazione: (2025)

Training-Free Layout-to-Image Generation with Marginal Attention Constraints
di: Chen, Huancheng, et al.
Pubblicazione: (2024)

StreamGVE: Training-Free Video Editing via Few-Step Streaming Video Generation
di: Jiao, Guanlong, et al.
Pubblicazione: (2026)

Free-GVC: Towards Training-Free Extreme Generative Video Compression with Temporal Coherence
di: Ling, Xiaoyue, et al.
Pubblicazione: (2026)