提出可蒸馏的可学习特征缓存，视频生成加速11.8倍且不降质。
DisCa: Accelerating Video Diffusion Transformers with Distillation-Compatible Learnable Feature Caching
- 用轻量神经预测器替代传统启发式缓存，更精准捕捉特征演化。
- 在少步蒸馏下实现11.8倍加速，生成质量无损失。
- 适合追求高速高质视频生成的开发者与研究者。
尽管扩散模型在视频生成领域取得巨大成功，但计算开销迅速上升。现有加速方法中，特征缓存因无需训练且提速显著而流行，但过度压缩会导致语义和细节丢失。另一常用方法——训练感知的步数蒸馏，在图像生成中表现良好，但在视频生成中几步蒸馏时性能急剧下降。此外，将无训练特征缓存直接应用于少步蒸馏模型时，因采样步数稀疏，质量损失更严重。本文首次提出一种可蒸馏的可学习特征缓存机制。采用轻量级可学习神经预测器替代传统无训练启发式方法，更准确捕捉高维特征演化过程。同时，针对大规模视频模型的高密度压缩蒸馏挑战，提出保守的受限均流（Restricted MeanFlow）方法，实现更稳定、无损的蒸馏。通过上述改进，将加速极限提升至11.8倍，同时保持生成质量。大量实验验证了方法的有效性。代码已公开：https://github.com/Tencent-Hunyuan/DisCa
原文摘要 · Abstract (English)
While diffusion models have achieved great success in the field of video generation, this progress is accompanied by a rapidly escalating computational burden. Among the existing acceleration methods, Feature Caching is popular due to its training-free property and considerable speedup performance, but it inevitably faces semantic and detail drop with further compression. Another widely adopted method, training-aware step-distillation, though successful in image generation, also faces drastic degradation in video generation with a few steps. Furthermore, the quality loss becomes more severe when simply applying training-free feature caching to the step-distilled models, due to the sparser sampling steps. This paper novelly introduces a distillation-compatible learnable feature caching mechanism for the first time. We employ a lightweight learnable neural predictor instead of traditional training-free heuristics for diffusion models, enabling a more accurate capture of the high-dimensional feature evolution process. Furthermore, we explore the challenges of highly compressed distillation on large-scale video models and propose a conservative Restricted MeanFlow approach to achieve more stable and lossless distillation. By undertaking these initiatives, we further push the acceleration boundaries to $11.8\times$ while preserving generation quality. Extensive experiments demonstrate the effectiveness of our method. Code has been made publicly available: https://github.com/Tencent-Hunyuan/DisCa
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。