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

Dogyun Park, Yanyu Li, Sergey Tulyakov, Anil KagarXiv 2026 · arXiv

TL;DR

EFlow introduces an efficient framework to train few-step video diffusion transformers from scratch, completely bypassing the need for expensive teacher distillation. By combining a token-droppable hybrid attention mechanism with a lightweight guidance training recipe, EFlow achieves up to a 2.5× increase in training throughput and generates high-quality videos in just 4 steps, slashing inference latency by up to 45×.

What Problem Does This Problem Address?

Generating high-fidelity videos using Video Diffusion Transformers (VideoDiTs) faces a compounding "double bottleneck": heavy per-step compute due to the quadratic complexity of spatiotemporal self-attention, and the requirement of dozens of iterative sampling steps.

While few-step generation methods exist to solve the sampling bottleneck, they typically rely on complex, multi-stage teacher distillation pipelines. Training a few-step model from scratch using solution-flow matching avoids distillation but introduces massive training overhead; it requires multiple network evaluations per step to enforce consistency and compute Classifier-Free Guidance (CFG). EFlow aims to solve both bottlenecks simultaneously, making from-scratch few-step video transformer training computationally practical.

Methods

The authors introduce three core components to achieve multi-level efficiency:

  1. Gated Local-Global Attention (GLGA): Traditional efficient DiTs rely on convolutional layers to recover local details lost by linear attention. However, convolutions assume a dense, regular grid, making them break when tokens are randomly dropped to save compute. GLGA solves this by fusing global linear attention (for long-range context) with local sliding-window attention (for fine details) via an input-aware gating mechanism. Because it avoids grid-aligned convolutions, it is highly stable under aggressive random token-dropping (up to 75%) during training.
  2. Path-Drop Guided (PDG) Training: To avoid the double-forward pass typically required by CFG (conditional and unconditional branches), PDG replaces the expensive unconditional branch with a computationally cheap "weak-path" pass that simply skips the middle transformer layers.
  3. Mean-Velocity Additivity (MVA) Regularizer: To prevent integration errors from accumulating over the large time jumps used in few-step inference, MVA enforces a global mathematical constraint (the semigroup property) ensuring that a single large jump matches the composition of smaller intermediate steps.
Gated Local-Global Attention Module Architecture

Datasets

  • Kinetics-700: Used for class-conditional video generation experiments to isolate architectural and objective performance.
  • Proprietary Large-Scale Text-to-Video Dataset: Used to evaluate high-resolution (480p) text-to-video generation capabilities.

The models were evaluated quantitatively using Fréchet Video Distance (FVD) and the VBench benchmark suite.

Key Insights and Ideas

  • Convolutions are the enemy of token dropping: Standard spatial convolutions require structured grid neighborhoods. Dropping tokens destroys this contiguity, causing catastrophic model degradation. Replacing convolutions with sliding-window attention preserves local expressivity while remaining robust to token removal.
  • The Semigroup Property Fixes Few-Step Drift: In few-step generation, taking massive time jumps causes trajectory drift, leading to blur and structural collapse. Forcing the network to obey the semigroup property via the MVA regularizer acts as a virtual refinement factor, allowing a 4-step model to achieve the structural fidelity of a 50-step model.
  • Unconditional paths don't need full capacity: CFG targets can be stabilized using a lightweight, block-skipped "weak" version of the model as the unconditional baseline, eliminating the need for a full second forward pass during training.

Key Results

  • Inference Speedup: EFlow achieves a 45.3× lower inference latency compared to standard iterative models like Wan2.1-1.3B, generating a 480p video clip in just 3.09 seconds using only 4 inference steps.
  • Training Throughput: EFlow delivers up to 2.5× higher training throughput compared to standard solution-flow baselines and 1.6× over standard flow matching.
  • Quality Improvements: On Kinetics-700, upgrading to the PDG-SFM objective with the MVA regularizer improved the 4-step generation quality significantly, dropping the FVD score from 185.2 to 146.7.
EFlow Inference Latency and Scaling

Limitations and Future Work

  • Scale: The framework was tested up to a 1.5B parameter model at 480p resolution. Its behavior at industry scales (10B+ parameters, 720p/1080p resolutions) remains uncharacterized.
  • Lack of Pre-trained Priors: Because EFlow trains entirely from scratch, it lacks the rich "world knowledge" priors inherited by models fine-tuned from massive pre-trained text-to-image foundation models. This results in lower absolute semantic scores on open-ended benchmarks like VBench.

Future directions include adapting this sparse training framework to support the highly efficient fine-tuning of pre-trained dense models and pushing towards stable 1- or 2-step generation.

Summary updated

Abstract

Scaling video diffusion transformers is fundamentally bottlenecked by two compounding costs: the expensive quadratic complexity of attention per step, and the iterative sampling steps. In this work, we propose EFlow, an efficient few-step training framework, that tackles these bottlenecks simultaneously. To reduce sampling steps, we build on a solution-flow objective that learns a function mapping a noised state at time t to time s. Making this formulation computationally feasible and high-quality at video scale, however, demands two complementary innovations. First, we propose Gated Local-Global Attention, a token-droppable hybrid block which is efficient, expressive, and remains highly stable under aggressive random token-dropping, substantially reducing per-step compute. Second, we develop an efficient few-step training recipe. We propose Path-Drop Guided training to replace the expensive guidance target with a computationally cheap, weak path. Furthermore, we augment this with a Mean-Velocity Additivity regularizer to ensure high fidelity at extremely low step counts. Together, our EFlow enables a practical from-scratch training pipeline, achieving up to 2.5x higher training throughput over standard solution-flow, and 45.3x lower inference latency than standard iterative models with competitive performance on Kinetics and large-scale text-to-video datasets.
BibTeX
@misc{park2026eflow,
  author = {Dogyun Park and Yanyu Li and Sergey Tulyakov and Anil Kag},
  title = {{EFlow: Fast Few-Step Video Generator Training from Scratch via Efficient Solution Flow}},
  year = {2026},
  eprint = {2603.27086},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2603.27086},
}
Figure