Accelerating Rectified Flow Models via Trajectory-Aware Caching

TL;DR

TACache is a training-free, trajectory-aware caching framework that accelerates rectified flow models by intelligently skipping and reconstructing velocity evaluations, improving efficiency without sacrificing quality.

Contribution

It introduces a novel orthogonal decomposition of velocity acceleration and a two-stage skip-then-compensate approach for efficient sampling in RF models.

Findings

Achieves up to 4.14x speedup in text-to-image generation.

Attains 2.11x speedup in text-to-video generation.

Outperforms prior cache-based methods on fidelity metrics.

Abstract

Diffusion and rectified flow (RF) models generate high-fidelity images and videos, but their iterative velocity-field evaluations are computationally expensive. Existing caching methods accelerate sampling by skipping timesteps, yet their coarse approximations introduce accumulated errors over long skip intervals and degrade quality under aggressive acceleration. We propose TACache (Trajectory-Aware Cache), a training-free acceleration framework following a skip-then-compensate paradigm. TACache performs an orthogonal decomposition of discrete velocity acceleration along the RF trajectory into a parallel component and an orthogonal residual, isolating the magnitude and directional sources of per-step approximation error. The framework operates in two stages: offline, cumulative variation thresholds on the magnitude and direction indicators yield the skip schedule and bound how far each skip interval may extend; online, at each skipped step the offline statistics are combined with the sample's historical orthogonal direction to reconstruct the skipped velocity without additional model evaluations. Experiments on BAGEL, FLUX.1-dev, and Wan2.1-1.3B show that TACache achieves up to 4.14 speedup on text-to-image generation and 2.11 speedup on text-to-video generation, with consistent improvements over prior cache-based methods on all reference-based fidelity metrics. Code will be released soon.