Copertina

Leveraging Previous Steps: A Training-free Fast Solver for Flow Diffusion

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Song, Kaiyu, Lai, Hanjiang
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

Improving Training-free Conditional Diffusion Model via Fisher Information
di: Song, Kaiyu, et al.
Pubblicazione: (2024)

Flow Matching Posterior Sampling: A Training-free Conditional Generation for Flow Matching
di: Song, Kaiyu, et al.
Pubblicazione: (2024)

Rethinking Oversaturation in Classifier-Free Guidance via Low Frequency
di: Song, Kaiyu, et al.
Pubblicazione: (2025)

Enhancing Few-Shot Out-of-Distribution Detection with Gradient Aligned Context Optimization
di: Tong, Baoshun, et al.
Pubblicazione: (2024)

Test-time Alignment-Enhanced Adapter for Vision-Language Models
di: Tong, Baoshun, et al.
Pubblicazione: (2024)

An Iteration-Free Fixed-Point Estimator for Diffusion Inversion
di: Chen, Yifei, et al.
Pubblicazione: (2025)

Two Simple Principles for Diffusion-Based Test-Time Adaptation
di: Song, Kaiyu, et al.
Pubblicazione: (2023)

Topology Sculptor, Shape Refiner: Discrete Diffusion Model for High-Fidelity 3D Meshes Generation
di: Song, Kaiyu, et al.
Pubblicazione: (2025)

Differentiable Solver Search for Fast Diffusion Sampling
di: Wang, Shuai, et al.
Pubblicazione: (2025)

Pretrain like Your Inference: Masked Tuning Improves Zero-Shot Composed Image Retrieval
di: Chen, Junyang, et al.
Pubblicazione: (2023)

Distilling ODE Solvers of Diffusion Models into Smaller Steps
di: Kim, Sanghwan, et al.
Pubblicazione: (2023)

SlimFlow: Training Smaller One-Step Diffusion Models with Rectified Flow
di: Zhu, Yuanzhi, et al.
Pubblicazione: (2024)

Distilling Parallel Gradients for Fast ODE Solvers of Diffusion Models
di: Zhu, Beier, et al.
Pubblicazione: (2025)

Fast and Stable Diffusion Inverse Solver with History Gradient Update
di: He, Linchao, et al.
Pubblicazione: (2023)

DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models
di: Lu, Cheng, et al.
Pubblicazione: (2022)

Training-free Online Video Step Grounding
di: Zanella, Luca, et al.
Pubblicazione: (2025)

EFlow: Fast Few-Step Video Generator Training from Scratch via Efficient Solution Flow
di: Park, Dogyun, et al.
Pubblicazione: (2026)

Bespoke Non-Stationary Solvers for Fast Sampling of Diffusion and Flow Models
di: Shaul, Neta, et al.
Pubblicazione: (2024)

OmnimatteZero: Fast Training-free Omnimatte with Pre-trained Video Diffusion Models
di: Samuel, Dvir, et al.
Pubblicazione: (2025)

PixelRush: Ultra-Fast, Training-Free High-Resolution Image Generation via One-step Diffusion
di: Lai, Hong-Phuc, et al.
Pubblicazione: (2026)

NitroFusion: High-Fidelity Single-Step Diffusion through Dynamic Adversarial Training
di: Chen, Dar-Yen, et al.
Pubblicazione: (2024)

Fast3Dcache: Training-free 3D Geometry Synthesis Acceleration
di: Yang, Mengyu, et al.
Pubblicazione: (2025)

Noise-free Optimization in Early Training Steps for Image Super-Resolution
di: Lee, MinKyu, et al.
Pubblicazione: (2023)

Deep Data Consistency: a Fast and Robust Diffusion Model-based Solver for Inverse Problems
di: Chen, Hanyu, et al.
Pubblicazione: (2024)

Training-free Regional Prompting for Diffusion Transformers
di: Chen, Anthony, et al.
Pubblicazione: (2024)

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

Training-free Stylized Text-to-Image Generation with Fast Inference
di: Ma, Xin, et al.
Pubblicazione: (2025)

AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation
di: Gu, Yuchao, et al.
Pubblicazione: (2026)

Harmonizing Flows: Leveraging normalizing flows for unsupervised and source-free MRI harmonization
di: Beizaee, Farzad, et al.
Pubblicazione: (2024)

LeapAlign: Post-Training Flow Matching Models at Any Generation Step by Building Two-Step Trajectories
di: Liang, Zhanhao, et al.
Pubblicazione: (2026)

Training-free Geometric Image Editing on Diffusion Models
di: Zhu, Hanshen, et al.
Pubblicazione: (2025)

ERA-Solver: Error-Robust Adams Solver for Fast Sampling of Diffusion Probabilistic Models
di: Li, Shengming, et al.
Pubblicazione: (2023)

MotionDiff: Training-free Zero-shot Interactive Motion Editing via Flow-assisted Multi-view Diffusion
di: Ma, Yikun, et al.
Pubblicazione: (2025)

Steering One-Step Diffusion Model with Fidelity-Rich Decoder for Fast Image Compression
di: Chen, Zheng, et al.
Pubblicazione: (2025)

HiFlow: Training-free High-Resolution Image Generation with Flow-Aligned Guidance
di: Bu, Jiazi, et al.
Pubblicazione: (2025)

Training-free Conditional Image Embedding Framework Leveraging Large Vision Language Models
di: Kawarada, Masayuki, et al.
Pubblicazione: (2025)

GAFD-CC: Global-Aware Feature Decoupling with Confidence Calibration for OOD Detection
di: Zou, Kun, et al.
Pubblicazione: (2025)

LASPA: Latent Spatial Alignment for Fast Training-free Single Image Editing
di: Alharbi, Yazeed, et al.
Pubblicazione: (2024)

Scribble-Guided Diffusion for Training-free Text-to-Image Generation
di: Lee, Seonho, et al.
Pubblicazione: (2024)

Dreamguider: Improved Training free Diffusion-based Conditional Generation
di: Nair, Nithin Gopalakrishnan, et al.
Pubblicazione: (2024)