恰逢其时：面向扩散 Transformer 的免训练空间加速
Just-in-Time: Training-Free Spatial Acceleration for Diffusion Transformers
JiT 把扩散 Transformer 的采样加速从时间维度转到空间维度：只对动态选出的稀疏锚 token 计算 ODE，再用确定性 micro-flow 把新增 token 平滑接入潜变量，可直接套用到 FLUX、DiT 类骨干上做免训练推理加速。
原文依据 JiT formulates a spatially approximated generative ordinary differential equation (ODE) that drives the full latent state evolution based on computations from a dynamically selected, sparse subset of anchor tokens.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论扩散 Transformer 已在图像合成上确立了新的最优性能，但迭代采样带来的高计算开销严重制约了其实际部署。现有加速方法往往聚焦于时间维度，却忽视了生成过程中固有的显著空间冗余——全局结构早在细粒度细节形成之前就已出现，对所有空间区域施加统一计算是一种关键的低效。本文提出 Just-in-Time（JiT），一个新颖的免训练框架，通过在空间域进行加速来应对这一挑战。JiT 构建了一个空间近似的生成常微分方程（ODE），仅基于动态选取的稀疏锚 token 子集的计算结果来驱动完整潜变量状态的演化。为确保在纳入新 token 以扩展潜变量状态维度时实现无缝过渡，我们提出确定性微流（deterministic micro-flow），一种简单而有效的有限时间 ODE，同时保持结构连贯性与统计正确性。在最优的 FLUX.1-dev 模型上的大量实验表明，JiT 可实现最高 7 倍加速且性能几乎无损，显著优于现有加速方法，并在推理速度与生成保真度之间建立了新的更优权衡。
英文原文摘要 1428 字符
Diffusion Transformers have established a new state-of-the-art in image synthesis, but the high computational cost of iterative sampling severely hampers their practical deployment. While existing acceleration methods often focus on the temporal domain, they overlook the substantial spatial redundancy inherent in the generative process, where global structures emerge long before fine-grained details are formed. The uniform computational treatment of all spatial regions represents a critical inefficiency. In this paper, we introduce Just-in-Time (JiT), a novel training-free framework that addresses this challenge by acceleration in the spatial domain. JiT formulates a spatially approximated generative ordinary differential equation (ODE) that drives the full latent state evolution based on computations from a dynamically selected, sparse subset of anchor tokens. To ensure seamless transitions as new tokens are incorporated to expand the dimensions of the latent state, we propose a deterministic micro-flow, a simple and effective finite-time ODE that maintains both structural coherence and statistical correctness. Extensive experiments on the state-of-the-art FLUX.1-dev model demonstrate that JiT achieves up to a 7x speedup with nearly lossless performance, significantly outperforming existing acceleration methods and establishing a new and superior trade-off between inference speed and generation fidelity.