FreqCa: Accelerating Diffusion Models via Frequency-Aware Caching
The application of diffusion transformers is suffering from their significant inference costs. Recently, feature caching has been proposed to solve this problem by reusing features from previous timesteps, thereby skipping computation in future timesteps. However, previous feature caching assumes that features in adjacent timesteps are similar or continuous, which does not always hold in all settings. To investigate this, this paper begins with an analysis from the frequency domain, which reveal that different frequency bands in the features of diffusion models exhibit different dynamics across timesteps. Concretely, low-frequency components, which decide the structure of images, exhibit higher similarity but poor continuity. In contrast, the high-frequency bands, which decode the details of images, show significant continuity but poor similarity. These interesting observations motivate us to propose Frequency-aware Caching (FreqCa) which directly reuses features of low-frequency components based on their similarity, while using a second-order Hermite interpolator to predict the volatile high-frequency ones based on its continuity. Besides, we further propose to cache Cumulative Residual Feature (CRF) instead of the features in all the layers, which reduces the memory footprint of feature caching by 99%. Extensive experiments on FLUX.1-dev, FLUX.1-Kontext-dev, Qwen-Image, and Qwen-Image-Edit demonstrate its effectiveness in both generation and editing. Codes are available in the supplementary materials and will be released on GitHub.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
FreqCache: Accelerating Embodied VLN Models with Adaptive Frequency-Guided Token Caching
Vision-Language-Navigation (VLN) models exhibit excellent navigation accuracy but incur high computational overhead. Token caching has emerged as a promising training-free strategy to reduce this cost by reusing token co…
Frequency-Aware Error-Bounded Caching for Accelerating Diffusion Transformers
Diffusion Transformers (DiTs) have emerged as the dominant architecture for high-quality image and video generation, yet their iterative denoising process incurs substantial computational cost during inference. Existing …
Video GenerationSenCache: Accelerating Diffusion Model Inference via Sensitivity-Aware Caching
Diffusion models achieve state-of-the-art video generation quality, but their inference remains expensive due to the large number of sequential denoising steps. This has motivated a growing line of research on accelerati…
Video GenerationSeaCache: Spectral-Evolution-Aware Cache for Accelerating Diffusion Models
Diffusion models are a strong backbone for visual generation, but their inherently sequential denoising process leads to slow inference. Previous methods accelerate sampling by caching and reusing intermediate outputs ba…
Accelerating Frequency Domain Diffusion Models with Error-Feedback Event-Driven Caching
Diffusion models achieve remarkable success in time series generation. However, slow inference limits their practical deployment. We propose E$^2$-CRF (Error-Feedback Event-Driven Cumulative Residual Feature caching) to …