Copertina

Hyper-SD: Trajectory Segmented Consistency Model for Efficient Image Synthesis

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Ren, Yuxi, Xia, Xin, Lu, Yanzuo, Zhang, Jiacheng, Wu, Jie, Xie, Pan, Wang, Xing, Xiao, Xuefeng
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Hyper-Bagel: A Unified Acceleration Framework for Multimodal Understanding and Generation
di: Lu, Yanzuo, et al.
Pubblicazione: (2025)

Adversarial Distribution Matching for Diffusion Distillation Towards Efficient Image and Video Synthesis
di: Lu, Yanzuo, et al.
Pubblicazione: (2025)

Dense2MoE: Restructuring Diffusion Transformer to MoE for Efficient Text-to-Image Generation
di: Zheng, Youwei, et al.
Pubblicazione: (2025)

ResAdapter: Domain Consistent Resolution Adapter for Diffusion Models
di: Cheng, Jiaxiang, et al.
Pubblicazione: (2024)

ByteEdit: Boost, Comply and Accelerate Generative Image Editing
di: Ren, Yuxi, et al.
Pubblicazione: (2024)

RayFlow: Instance-Aware Diffusion Acceleration via Adaptive Flow Trajectories
di: Shao, Huiyang, et al.
Pubblicazione: (2025)

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

RAVEN: Real-time Autoregressive Video Extrapolation with Consistency-model GRPO
di: Lu, Yanzuo, et al.
Pubblicazione: (2026)

Coarse-to-Fine Latent Diffusion for Pose-Guided Person Image Synthesis
di: Lu, Yanzuo, et al.
Pubblicazione: (2024)

Diffusion Adversarial Post-Training for One-Step Video Generation
di: Lin, Shanchuan, et al.
Pubblicazione: (2025)

SegmentDreamer: Towards High-fidelity Text-to-3D Synthesis with Segmented Consistency Trajectory Distillation
di: Zhu, Jiahao, et al.
Pubblicazione: (2025)

VmambaIR: Visual State Space Model for Image Restoration
di: Shi, Yuan, et al.
Pubblicazione: (2024)

Relax Forcing: Relaxed KV-Memory for Consistent Long Video Generation
di: Zhao, Zengqun, et al.
Pubblicazione: (2026)

Training-free Diffusion Acceleration with Bottleneck Sampling
di: Tian, Ye, et al.
Pubblicazione: (2025)

HyperAlign: Hypernetwork for Efficient Test-Time Alignment of Diffusion Models
di: Xie, Xin, et al.
Pubblicazione: (2026)

ID-Aligner: Enhancing Identity-Preserving Text-to-Image Generation with Reward Feedback Learning
di: Chen, Weifeng, et al.
Pubblicazione: (2024)

NanoSD: Edge Efficient Foundation Model for Real Time Image Restoration
di: Sanyal, Subhajit, et al.
Pubblicazione: (2026)

ControlNet++: Improving Conditional Controls with Efficient Consistency Feedback
di: Li, Ming, et al.
Pubblicazione: (2024)

SD-FSMIS: Adapting Stable Diffusion for Few-Shot Medical Image Segmentation
di: Li, Meihua, et al.
Pubblicazione: (2026)

Cross Prompting Consistency with Segment Anything Model for Semi-supervised Medical Image Segmentation
di: Miao, Juzheng, et al.
Pubblicazione: (2024)

OnlineVPO: Align Video Diffusion Model with Online Video-Centric Preference Optimization
di: Zhang, Jiacheng, et al.
Pubblicazione: (2024)

Noise-Consistent Siamese-Diffusion for Medical Image Synthesis and Segmentation
di: Qiu, Kunpeng, et al.
Pubblicazione: (2025)

CTS: A Consistency-Based Medical Image Segmentation Model
di: Zhang, Kejia, et al.
Pubblicazione: (2024)

Control-A-Video: Controllable Text-to-Video Diffusion Models with Motion Prior and Reward Feedback Learning
di: Chen, Weifeng, et al.
Pubblicazione: (2023)

LiSD: An Efficient Multi-Task Learning Framework for LiDAR Segmentation and Detection
di: Xu, Jiahua, et al.
Pubblicazione: (2024)

Relation3D: Enhancing Relation Modeling for Point Cloud Instance Segmentation
di: Lu, Jiahao, et al.
Pubblicazione: (2025)

CM-MaskSD: Cross-Modality Masked Self-Distillation for Referring Image Segmentation
di: Wang, Wenxuan, et al.
Pubblicazione: (2023)

HisynSeg: Weakly-Supervised Histopathological Image Segmentation via Image-Mixing Synthesis and Consistency Regularization
di: Fang, Zijie, et al.
Pubblicazione: (2024)

FAST: Foreground-aware Diffusion with Accelerated Sampling Trajectory for Segmentation-oriented Anomaly Synthesis
di: Xu, Xichen, et al.
Pubblicazione: (2025)

MLNet: Mutual Learning Network with Neighborhood Invariance for Universal Domain Adaptation
di: Lu, Yanzuo, et al.
Pubblicazione: (2023)

HyperSeg: Towards Universal Visual Segmentation with Large Language Model
di: Wei, Cong, et al.
Pubblicazione: (2024)

FreeTumor: Advance Tumor Segmentation via Large-Scale Tumor Synthesis
di: Wu, Linshan, et al.
Pubblicazione: (2024)

Autoregressive Adversarial Post-Training for Real-Time Interactive Video Generation
di: Lin, Shanchuan, et al.
Pubblicazione: (2025)

Sparse Reconstruction of Optical Doppler Tomography with Alternative State Space Model and Attention
di: Li, Zhenghong, et al.
Pubblicazione: (2024)

TopoSD: Topology-Enhanced Lane Segment Perception with SDMap Prior
di: Yang, Sen, et al.
Pubblicazione: (2024)

SCoT: Unifying Consistency Models and Rectified Flows via Straight-Consistent Trajectories
di: Wu, Zhangkai, et al.
Pubblicazione: (2025)

HyperDet: Generalizable Detection of Synthesized Images by Generating and Merging A Mixture of Hyper LoRAs
di: Cao, Huangsen, et al.
Pubblicazione: (2024)

Generalized Consistency Trajectory Models for Image Manipulation
di: Kim, Beomsu, et al.
Pubblicazione: (2024)

Diffusion-Guided Mask-Consistent Paired Mixing for Endoscopic Image Segmentation
di: Jie, Pengyu, et al.
Pubblicazione: (2025)

Instance Consistency Regularization for Semi-Supervised 3D Instance Segmentation
di: Wu, Yizheng, et al.
Pubblicazione: (2024)