BWCache: Accelerating Video Diffusion Transformers through Block-Wise Caching
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915825097637888 |
|---|---|
| author | Cui, Hanshuai Tang, Zhiqing Xu, Zhifei Yao, Zhi Zeng, Wenyi Jia, Weijia |
| author_facet | Cui, Hanshuai Tang, Zhiqing Xu, Zhifei Yao, Zhi Zeng, Wenyi Jia, Weijia |
| contents | Recent advancements in Diffusion Transformers (DiTs) have established them as the state-of-the-art method for video generation. However, their inherently sequential denoising process results in inevitable latency, limiting real-world applicability. Existing acceleration methods either compromise visual quality due to architectural modifications or fail to reuse intermediate features at proper granularity. Our analysis reveals that DiT blocks are the primary contributors to inference latency. Across diffusion timesteps, the feature variations of DiT blocks exhibit a U-shaped pattern with high similarity during intermediate timesteps, which suggests substantial computational redundancy. In this paper, we propose Block-Wise Caching (BWCache), a training-free method to accelerate DiT-based video generation. BWCache dynamically caches and reuses features from DiT blocks across diffusion timesteps. Furthermore, we introduce a similarity indicator that triggers feature reuse only when the differences between block features at adjacent timesteps fall below a threshold, thereby minimizing redundant computations while maintaining visual fidelity. Extensive experiments on several video diffusion models demonstrate that BWCache achieves up to 6$\times$ speedup with comparable visual quality. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_13789 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | BWCache: Accelerating Video Diffusion Transformers through Block-Wise Caching Cui, Hanshuai Tang, Zhiqing Xu, Zhifei Yao, Zhi Zeng, Wenyi Jia, Weijia Computer Vision and Pattern Recognition Artificial Intelligence Recent advancements in Diffusion Transformers (DiTs) have established them as the state-of-the-art method for video generation. However, their inherently sequential denoising process results in inevitable latency, limiting real-world applicability. Existing acceleration methods either compromise visual quality due to architectural modifications or fail to reuse intermediate features at proper granularity. Our analysis reveals that DiT blocks are the primary contributors to inference latency. Across diffusion timesteps, the feature variations of DiT blocks exhibit a U-shaped pattern with high similarity during intermediate timesteps, which suggests substantial computational redundancy. In this paper, we propose Block-Wise Caching (BWCache), a training-free method to accelerate DiT-based video generation. BWCache dynamically caches and reuses features from DiT blocks across diffusion timesteps. Furthermore, we introduce a similarity indicator that triggers feature reuse only when the differences between block features at adjacent timesteps fall below a threshold, thereby minimizing redundant computations while maintaining visual fidelity. Extensive experiments on several video diffusion models demonstrate that BWCache achieves up to 6$\times$ speedup with comparable visual quality. |
| title | BWCache: Accelerating Video Diffusion Transformers through Block-Wise Caching |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2509.13789 |