DisCa: Accelerating Video Diffusion Transformers with Distillation-Compatible Learnable Feature Caching

• URL: http://arxiv.org/abs/2602.05449v2
• Date: Fri, 06 Feb 2026 03:54:23 GMT
• Title: DisCa: Accelerating Video Diffusion Transformers with Distillation-Compatible Learnable Feature Caching
• Authors: Chang Zou, Changlin Li, Yang Li, Patrol Li, Jianbing Wu, Xiao He, Songtao Liu, Zhao Zhong, Kailin Huang, Linfeng Zhang,
• Abstract summary: This paper introduces a distillation-compatible learnable feature caching mechanism for the first time.<n>We employ a lightweight learnable neural predictor instead of traditional training-frees for diffusion models.<n>By undertaking these initiatives, we further push the acceleration boundaries to $11.8times$ while preserving generation quality.
• Score: 26.603292632638283
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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. The code will be made publicly available soon.

Related papers

• Predict to Skip: Linear Multistep Feature Forecasting for Efficient Diffusion Transformers [10.751183015853863]
  Diffusion Transformers (DiT) have emerged as a widely adopted backbone for high-fidelity image and video generation.<n>We propose textbfPrediT, a training-free acceleration framework that formulates feature prediction as a linear multistep problem.<n>Our method achieves up to $5.54times$ latency reduction across various DiT-based image and video generation models, while incurring negligible quality degradation.
  arXiv  Detail & Related papers  (2026-02-20T09:33:59Z)
• Input-Aware Sparse Attention for Real-Time Co-Speech Video Generation [39.27933931527444]
  Diffusion models can synthesize realistic co-speech video from audio for various applications, such as video creation and virtual agents.<n>In this work, we distill a many-step diffusion video model into a few-step student model.<n>We propose using accurate correspondence between input human pose keypoints to guide attention to relevant regions, such as the speaker's face, hands, and upper body.<n>This input-aware sparse attention reduces redundant computations and strengthens temporal correspondences of body parts, improving inference efficiency and motion coherence.
  arXiv  Detail & Related papers  (2025-10-02T23:35:52Z)
• Less is Enough: Training-Free Video Diffusion Acceleration via Runtime-Adaptive Caching [57.7533917467934]
  EasyCache is a training-free acceleration framework for video diffusion models.<n>We conduct comprehensive studies on various large-scale video generation models, including OpenSora, Wan2.1, and HunyuanVideo.<n>Our method achieves leading acceleration performance, reducing inference time by up to 2.1-3.3$times$ compared to the original baselines.
  arXiv  Detail & Related papers  (2025-07-03T17:59:54Z)
• Training-Free Motion Customization for Distilled Video Generators with Adaptive Test-Time Distillation [53.877572078307935]
  Distilled video generation models offer fast and efficient but struggle with motion customization when guided by reference videos.<n>We propose MotionEcho, a training-free test-time distillation framework that enables motion customization by leveraging diffusion teacher forcing.
  arXiv  Detail & Related papers  (2025-06-24T06:20:15Z)
• Accelerating Diffusion Transformer via Increment-Calibrated Caching with Channel-Aware Singular Value Decomposition [4.0594792247165]
  Diffusion transformer (DiT) models have achieved remarkable success in image generation.<n>We propose increment-calibrated caching, a training-free method for DiT acceleration.<n>Our method eliminates more than 45% and improves IS by 12 at the cost of less than 0.06 FID increase.
  arXiv  Detail & Related papers  (2025-05-09T06:56:17Z)
• One-Step Diffusion Model for Image Motion-Deblurring [85.76149042561507]
  We propose a one-step diffusion model for deblurring (OSDD), a novel framework that reduces the denoising process to a single step.<n>To tackle fidelity loss in diffusion models, we introduce an enhanced variational autoencoder (eVAE), which improves structural restoration.<n>Our method achieves strong performance on both full and no-reference metrics.
  arXiv  Detail & Related papers  (2025-03-09T09:39:57Z)
• From Slow Bidirectional to Fast Autoregressive Video Diffusion Models [48.35054927704544]
  Current video diffusion models achieve impressive generation quality but struggle in interactive applications due to bidirectional attention dependencies.<n>We address this limitation by adapting a pretrained bidirectional diffusion transformer to an autoregressive transformer that generates frames on-the-fly.<n>Our model achieves a total score of 84.27 on the VBench-Long benchmark, surpassing all previous video generation models.
  arXiv  Detail & Related papers  (2024-12-10T18:59:50Z)
• Adaptive Caching for Faster Video Generation with Diffusion Transformers [52.73348147077075]
  Diffusion Transformers (DiTs) rely on larger models and heavier attention mechanisms, resulting in slower inference speeds. We introduce a training-free method to accelerate video DiTs, termed Adaptive Caching (AdaCache) We also introduce a Motion Regularization (MoReg) scheme to utilize video information within AdaCache, controlling the compute allocation based on motion content.
  arXiv  Detail & Related papers  (2024-11-04T18:59:44Z)
• DeepCache: Accelerating Diffusion Models for Free [65.02607075556742]
  DeepCache is a training-free paradigm that accelerates diffusion models from the perspective of model architecture. DeepCache capitalizes on the inherent temporal redundancy observed in the sequential denoising steps of diffusion models. Under the same throughput, DeepCache effectively achieves comparable or even marginally improved results with DDIM or PLMS.
  arXiv  Detail & Related papers  (2023-12-01T17:01:06Z)
• Self-Conditioned Probabilistic Learning of Video Rescaling [70.10092286301997]
  We propose a self-conditioned probabilistic framework for video rescaling to learn the paired downscaling and upscaling procedures simultaneously. We decrease the entropy of the information lost in the downscaling by maximizing its conditioned probability on the strong spatial-temporal prior information. We extend the framework to a lossy video compression system, in which a gradient estimator for non-differential industrial lossy codecs is proposed.
  arXiv  Detail & Related papers  (2021-07-24T15:57:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.