LearniBridge: Learnable Calibration of Feature Caching for Diffusion Models Acceleration

• URL: http://arxiv.org/abs/2606.26778v1
• Date: Thu, 25 Jun 2026 09:12:51 GMT
• Title: LearniBridge: Learnable Calibration of Feature Caching for Diffusion Models Acceleration
• Abstract summary: LearniBridge is a learnable calibration mechanism for feature caching that bridges multiple timesteps through lightweight LoRA updates.<n>Experiments on image and video generation show that LearniBridge achieves up to $5.87times$, $5.75times$, and $4.10times$ acceleration on FLUX, HunyuanVideo, and WAN2.1, respectively.
• Score: 13.139080503923248
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Diffusion Transformers (DiTs) have driven substantial progress in image and video generation but suffer from prohibitive computational costs. Feature caching accelerates inference by reusing intermediate representations. Existing methods rely on historical features for implementation simplicity, yet suffer from severe error accumulation at high acceleration ratios. To address this limitation, we investigate the nature of the requisite feature correction. We demonstrate that the optimal calibration update is characterized by a shared low-rank subspace across diverse prompts. Guided by this structural insight, we propose LearniBridge, a learnable calibration mechanism for feature caching that bridges multiple timesteps through lightweight LoRA updates. This mechanism enables effective calibration requiring only 3-5 training samples. Extensive experiments on image and video generation show that LearniBridge achieves up to $5.87\times$, $5.75\times$, and $4.10\times$ acceleration on FLUX, HunyuanVideo, and WAN2.1, respectively. On WAN2.1, it improves VBench by 1.28% over the previous SOTA at $4.10\times$ acceleration. Our code is available at https://github.com/Iiiiiiirene/LearniBridge.

Related papers

• MobileWan: Closing the Quality Gap for Mobile Video Diffusion [53.20920841863923]
  MobileWan is the first 5B-scale video diffusion model deployable on a commercial mobile device.<n>Our system generates 5-second 480x832 videos at 16 FPS in 20 seconds end-to-end latency, achieving a VBench score of 83.79.
  arXiv  Detail & Related papers  (2026-07-07T11:52:46Z)
• Beyond Fixed Formulas: Data-Driven Linear Predictor for Efficient Diffusion Models [18.678454642609996]
  We propose L2P (Learnable Linear Predictor), a data-driven caching framework that replaces fixed coefficients with learnable per-timestep weights.<n>Rapidly trained in 20 seconds on a single GPU, L2P accurately reconstructs current features from past trajectories.
  arXiv  Detail & Related papers  (2026-04-29T07:22:16Z)
• Adaptive Spectral Feature Forecasting for Diffusion Sampling Acceleration [58.19554276924402]
  We propose spectral diffusion feature forecaster (Spectrum) to enable global, long-range feature reuse with tightly controlled error.<n>We achieve up to 4.79$times$ speedup on FLUX.1 and 4.67$times$ speedup on Wan2.1-14B, while maintaining much higher sample quality compared with the baselines.
  arXiv  Detail & Related papers  (2026-03-02T08:59:11Z)
• LESA: Learnable Stage-Aware Predictors for Diffusion Model Acceleration [12.183601881545039]
  Diffusion models have achieved remarkable success in image and video generation tasks.<n>However, the high computational demands of Diffusion Transformers pose a significant challenge to their practical deployment.<n>We propose a LEarnable Stage-Aware (LESA) predictor framework based on two-stage training.
  arXiv  Detail & Related papers  (2026-02-24T02:53:28Z)
• S$^2$Q-VDiT: Accurate Quantized Video Diffusion Transformer with Salient Data and Sparse Token Distillation [55.35880044416441]
  We propose S$2$Q-VDiT, a post-training quantization framework for video diffusion models (V-DMs)<n>Under W4A6 quantization, S$2$Q-VDiT achieves lossless performance while delivering $3.9times$ model compression and $1.3times$ inference acceleration.
  arXiv  Detail & Related papers  (2025-08-06T02:12:29Z)
• 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)
• MagCache: Fast Video Generation with Magnitude-Aware Cache [91.2771453279713]
  We introduce a novel and robust discovery: a unified magnitude law observed across different models and prompts.<n>We introduce a Magnitude-aware Cache (MagCache) that adaptively skips unimportant timesteps using an error modeling mechanism and adaptive caching strategy.<n> Experimental results show that MagCache achieves 2.10x-2.68x speedups on Open-Sora, CogVideoX, Wan 2.1, and HunyuanVideo, while preserving superior visual fidelity.
  arXiv  Detail & Related papers  (2025-06-10T17:59:02Z)
• From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers [14.402483491830138]
  Diffusion Transformers (DiT) have revolutionized high-fidelity image and video synthesis, yet their computational demands remain prohibitive for real-time applications.<n> feature caching has been proposed to accelerate diffusion models by caching the features in the previous timesteps and then reusing them in the following timesteps.<n>We propose TaylorSeer, which firstly shows that features of diffusion models at future timesteps can be predicted based on their values at previous timesteps.
  arXiv  Detail & Related papers  (2025-03-10T05:09:42Z)
• HarmoniCa: Harmonizing Training and Inference for Better Feature Caching in Diffusion Transformer Acceleration [31.982294870690925]
  We develop a novel learning-based caching framework dubbed HarmoniCa.<n>It incorporates Step-Wise Denoising Training (SDT) to ensure the continuity of the denoising process.<n>Our framework achieves over $40%$ latency reduction (i.e., $2.07times$ theoretical speedup) and improved performance on PixArt-$alpha$.
  arXiv  Detail & Related papers  (2024-10-02T16:34:29Z)
• 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)

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.