CorGi: Contribution-Guided Block-Wise Interval Caching for Training-Free Acceleration of Diffusion Transformers

TL;DR

CorGi introduces a training-free, contribution-guided caching method for diffusion transformers, significantly reducing redundant computation during inference without sacrificing image generation quality.

Contribution

It proposes a novel block-wise interval caching framework that selectively reuses transformer block outputs, enhancing inference speed in diffusion transformers.

Findings

Achieves up to 2.0x speedup on DiT models

Reduces redundant computation across denoising steps

Maintains high image generation quality

Abstract

Diffusion transformer (DiT) achieves remarkable performance in visual generation, but its iterative denoising process combined with larger capacity leads to a high inference cost. Recent works have demonstrated that the iterative denoising process of DiT models involves substantial redundant computation across steps. To effectively reduce the redundant computation in DiT, we propose CorGi (Contribution-Guided Block-Wise Interval Caching), training-free DiT inference acceleration framework that selectively reuses the outputs of transformer blocks in DiT across denoising steps. CorGi caches low-contribution blocks and reuses them in later steps within each interval to reduce redundant computation while preserving generation quality. For text-to-image tasks, we further propose CorGi+, which leverages per-block cross-attention maps to identify salient tokens and applies partial attention updates to protect important object details. Evaluation on the state-of-the-art DiT models demonstrates that CorGi and CorGi+ achieve up to 2.0x speedup on average, while preserving high generation quality.