Cover Image

EFlow: Fast Few-Step Video Generator Training from Scratch via Efficient Solution Flow

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Park, Dogyun, Li, Yanyu, Tulyakov, Sergey, Kag, Anil
Format:	Preprint
Published:	2026
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

Sprint: Sparse-Dense Residual Fusion for Efficient Diffusion Transformers
by: Park, Dogyun, et al.
Published: (2025)

Diffusion-DRF: Free, Rich, and Differentiable Reward for Video Diffusion Fine-Tuning
by: Wang, Yifan, et al.
Published: (2026)

One Model, Many Budgets: Elastic Latent Interfaces for Diffusion Transformers
by: Haji-Ali, Moayed, et al.
Published: (2026)

Scalable Ranked Preference Optimization for Text-to-Image Generation
by: Karthik, Shyamgopal, et al.
Published: (2024)

Taming Diffusion Transformer for Efficient Mobile Video Generation in Seconds
by: Wu, Yushu, et al.
Published: (2025)

Towards Physical Understanding in Video Generation: A 3D Point Regularization Approach
by: Chen, Yunuo, et al.
Published: (2025)

H3AE: High Compression, High Speed, and High Quality AutoEncoder for Video Diffusion Models
by: Wu, Yushu, et al.
Published: (2025)

DenseDPO: Fine-Grained Temporal Preference Optimization for Video Diffusion Models
by: Wu, Ziyi, et al.
Published: (2025)

S2DiT: Sandwich Diffusion Transformer for Mobile Streaming Video Generation
by: Zhao, Lin, et al.
Published: (2026)

SF-V: Single Forward Video Generation Model
by: Zhang, Zhixing, et al.
Published: (2024)

AsCAN: Asymmetric Convolution-Attention Networks for Efficient Recognition and Generation
by: Kag, Anil, et al.
Published: (2024)

BitsFusion: 1.99 bits Weight Quantization of Diffusion Model
by: Sui, Yang, et al.
Published: (2024)

Blockwise Flow Matching: Improving Flow Matching Models For Efficient High-Quality Generation
by: Park, Dogyun, et al.
Published: (2025)

SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices
by: Hu, Dongting, et al.
Published: (2026)

TextCraftor: Your Text Encoder Can be Image Quality Controller
by: Li, Yanyu, et al.
Published: (2024)

Probabilistic Precision and Recall Towards Reliable Evaluation of Generative Models
by: Park, Dogyun, et al.
Published: (2023)

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

SnapGen: Taming High-Resolution Text-to-Image Models for Mobile Devices with Efficient Architectures and Training
by: Hu, Dongting, et al.
Published: (2024)

Snap Video: Scaled Spatiotemporal Transformers for Text-to-Video Synthesis
by: Menapace, Willi, et al.
Published: (2024)

SnapGen-V: Generating a Five-Second Video within Five Seconds on a Mobile Device
by: Wu, Yushu, et al.
Published: (2024)

Hierarchical Patch Diffusion Models for High-Resolution Video Generation
by: Skorokhodov, Ivan, et al.
Published: (2024)

Retrieve What's Missing: Coverage-Maximizing Retrieval for Consistent Long Video Generation
by: Joo, Minseok, et al.
Published: (2026)

Efficient Training with Denoised Neural Weights
by: Gong, Yifan, et al.
Published: (2024)

Can Text-to-Video Generation help Video-Language Alignment?
by: Zanella, Luca, et al.
Published: (2025)

DOLLAR: Few-Step Video Generation via Distillation and Latent Reward Optimization
by: Ding, Zihan, et al.
Published: (2024)

HyperHuman: Hyper-Realistic Human Generation with Latent Structural Diffusion
by: Liu, Xian, et al.
Published: (2023)

BiFM: Bidirectional Flow Matching for Few-Step Image Editing and Generation
by: Dai, Yasong, et al.
Published: (2026)

Self-Corrected Flow Distillation for Consistent One-Step and Few-Step Text-to-Image Generation
by: Dao, Quan, et al.
Published: (2024)

E$^{2}$GAN: Efficient Training of Efficient GANs for Image-to-Image Translation
by: Gong, Yifan, et al.
Published: (2024)

MoGAN: Improving Motion Quality in Video Diffusion via Few-Step Motion Adversarial Post-Training
by: Xue, Haotian, et al.
Published: (2025)

Leveraging Previous Steps: A Training-free Fast Solver for Flow Diffusion
by: Song, Kaiyu, et al.
Published: (2024)

FastLightGen: Fast and Light Video Generation with Fewer Steps and Parameters
by: Shao, Shitong, et al.
Published: (2026)

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

Stochastic Conditional Diffusion Models for Robust Semantic Image Synthesis
by: Ko, Juyeon, et al.
Published: (2024)

Diffusion Prior-Based Amortized Variational Inference for Noisy Inverse Problems
by: Lee, Sojin, et al.
Published: (2024)

SwiftVideo: A Unified Framework for Few-Step Video Generation through Trajectory-Distribution Alignment
by: Sun, Yanxiao, et al.
Published: (2025)

Causal Forcing++: Scalable Few-Step Autoregressive Diffusion Distillation for Real-Time Interactive Video Generation
by: Zhao, Min, et al.
Published: (2026)

4Real: Towards Photorealistic 4D Scene Generation via Video Diffusion Models
by: Yu, Heng, et al.
Published: (2024)

Adaptive Video Distillation: Mitigating Oversaturation and Temporal Collapse in Few-Step Generation
by: You, Yuyang, et al.
Published: (2026)

Improving Progressive Generation with Decomposable Flow Matching
by: Haji-Ali, Moayed, et al.
Published: (2025)