Just-in-Time: Training-Free Spatial Acceleration for Diffusion Transformers

TL;DR

This paper introduces JiT, a training-free spatial acceleration framework for diffusion transformers, significantly speeding up image synthesis with minimal loss in quality by focusing on spatial redundancy.

Contribution

JiT is a novel, training-free method that accelerates diffusion transformers by approximating spatial computations with sparse anchor tokens and a deterministic micro-flow.

Findings

Achieves up to 7x speedup in image synthesis.

Maintains nearly lossless performance.

Outperforms existing acceleration methods.

Abstract

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.