Cover Image

Shortcutting Pre-trained Flow Matching Diffusion Models is Almost Free Lunch

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Cai, Xu, Wu, Yang, Chen, Qianli, Wu, Haoran, Xiang, Lichuan, Wen, Hongkai
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Free Lunch for Stabilizing Rectified Flow Inversion
by: Wang, Chenru, et al.
Published: (2026)

On the Design of One-step Diffusion via Shortcutting Flow Paths
by: Lin, Haitao, et al.
Published: (2025)

High-Order Matching for One-Step Shortcut Diffusion Models
by: Chen, Bo, et al.
Published: (2025)

Switch EMA: A Free Lunch for Better Flatness and Sharpness
by: Li, Siyuan, et al.
Published: (2024)

Leveraging Semantic Attribute Binding for Free-Lunch Color Control in Diffusion Models
by: Laria, Héctor, et al.
Published: (2025)

PTDiffusion: Free Lunch for Generating Optical Illusion Hidden Pictures with Phase-Transferred Diffusion Model
by: Gao, Xiang, et al.
Published: (2025)

Freeplane: Unlocking Free Lunch in Triplane-Based Sparse-View Reconstruction Models
by: Sun, Wenqiang, et al.
Published: (2024)

ODE$_t$(ODE$_l$): Shortcutting the Time and the Length in Diffusion and Flow Models for Faster Sampling
by: Gudovskiy, Denis, et al.
Published: (2025)

Reversible Inversion for Training-Free Exemplar-guided Image Editing
by: Li, Yuke, et al.
Published: (2025)

One Step Diffusion via Shortcut Models
by: Frans, Kevin, et al.
Published: (2024)

FLOSS: Free Lunch in Open-vocabulary Semantic Segmentation
by: Benigmim, Yasser, et al.
Published: (2025)

FreeCus: Free Lunch Subject-driven Customization in Diffusion Transformers
by: Zhang, Yanbing, et al.
Published: (2025)

Incorporating Pre-trained Diffusion Models in Solving the Schrödinger Bridge Problem
by: Tang, Zhicong, et al.
Published: (2025)

Free Lunch for Generating Effective Outlier Supervision
by: Pei, Sen, et al.
Published: (2023)

Slight Corruption in Pre-training Data Makes Better Diffusion Models
by: Chen, Hao, et al.
Published: (2024)

You Only Look One Step: Accelerating Backpropagation in Diffusion Sampling with Gradient Shortcuts
by: Dou, Hongkun, et al.
Published: (2025)

Exploring Diffusion and Flow Matching Under Generator Matching
by: Patel, Zeeshan, et al.
Published: (2024)

PFDM: Parser-Free Virtual Try-on via Diffusion Model
by: Niu, Yunfang, et al.
Published: (2024)

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment
by: Schusterbauer, Johannes, et al.
Published: (2025)

FreeBind: Free Lunch in Unified Multimodal Space via Knowledge Fusion
by: Wang, Zehan, et al.
Published: (2024)

Reinforce Adjoint Matching: Scaling RL Post-Training of Diffusion and Flow-Matching Models
by: Bergmeister, Andreas, et al.
Published: (2026)

Gaussian Mixture Flow Matching Models
by: Chen, Hansheng, et al.
Published: (2025)

RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion Transformers
by: Zhao, Min, et al.
Published: (2025)

There is No VAE: End-to-End Pixel-Space Generative Modeling via Self-Supervised Pre-training
by: Lei, Jiachen, et al.
Published: (2025)

Quantum-Gated Task-interaction Knowledge Distillation for Pre-trained Model-based Class-Incremental Learning
by: Li, Linjie, et al.
Published: (2026)

Pyramidal Flow Matching for Efficient Video Generative Modeling
by: Jin, Yang, et al.
Published: (2024)

Energy-Calibrated VAE with Test Time Free Lunch
by: Luo, Yihong, et al.
Published: (2023)

FlowEdit: Inversion-Free Text-Based Editing Using Pre-Trained Flow Models
by: Kulikov, Vladimir, et al.
Published: (2024)

Accelerating Diffusion Models for Inverse Problems through Shortcut Sampling
by: Liu, Gongye, et al.
Published: (2023)

D4C: Data-Free Quantization for Contrastive Language-Image Pre-training Models
by: Zhang, Wenlun, et al.
Published: (2025)

Dynamical Diffusion: Learning Temporal Dynamics with Diffusion Models
by: Guo, Xingzhuo, et al.
Published: (2025)

Token Pruning for Caching Better: 9 Times Acceleration on Stable Diffusion for Free
by: Zhang, Evelyn, et al.
Published: (2024)

Slot-Guided Adaptation of Pre-trained Diffusion Models for Object-Centric Learning and Compositional Generation
by: Akan, Adil Kaan, et al.
Published: (2025)

Diff-Instruct: A Universal Approach for Transferring Knowledge From Pre-trained Diffusion Models
by: Luo, Weijian, et al.
Published: (2023)

(Almost) Free Modality Stitching of Foundation Models
by: Singh, Jaisidh, et al.
Published: (2025)

Free Lunch for Unified Multimodal Models: Enhancing Generation via Reflective Rectification with Inherent Understanding
by: Jiang, Yibo, et al.
Published: (2026)

Flow Distillation Sampling: Regularizing 3D Gaussians with Pre-trained Matching Priors
by: Chen, Lin-Zhuo, et al.
Published: (2025)

Linearized Coupling Flow with Shortcut Constraints for One-Step Face Restoration
by: Sun, Xiaohui, et al.
Published: (2026)

Post-training Quantization for Text-to-Image Diffusion Models with Progressive Calibration and Activation Relaxing
by: Tang, Siao, et al.
Published: (2023)

Free Lunch Alignment of Text-to-Image Diffusion Models without Preference Image Pairs
by: Xian, Jia Jun Cheng, et al.
Published: (2025)