paper-with-me

홈 › Papers

FSampler: Training Free Acceleration of Diffusion Sampling via Epsilon Extrapolation

2025-11-12 · Michael A. Vladimir arxiv

FSampler is a training free, sampler agnostic execution layer that accelerates diffusion sampling by reducing the number of function evaluations (NFE). FSampler maintains a short history of denoising signals (epsilon) from recent real model calls and extrapolates the next epsilon using finite difference predictors at second order, third order, or fourth order, falling back to lower order when history is insufficient. On selected steps the predicted epsilon substitutes the model call while keeping each sampler's update rule unchanged. Predicted epsilons are validated for finiteness and magnitude; a learning stabilizer rescales predictions on skipped steps to correct drift, and an optional gradient estimation stabilizer compensates local curvature. Protected windows, periodic anchors, and a cap on consecutive skips bound deviation over the trajectory. Operating at the sampler level, FSampler integrates with Euler/DDIM, DPM++ 2M/2S, LMS/AB2, and RES family exponential multistep methods and drops into standard workflows. FLUX.1 dev, Qwen Image, and Wan 2.2, FSampler reduces time by 8 to 22% and model calls by 15 to 25% at high fidelity (Structural Similarity Index (SSIM) 0.95 to 0.99), without altering sampler formulas. With an aggressive adaptive gate, reductions can reach 45 to 50% fewer model calls at lower fidelity (SSIM 0.73 to 0.74).

📄 PDF Abstract BibTeX arXiv:2511.09180

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Training-free Mixed-Resolution Latent Upsampling for Spatially Accelerated Diffusion Transformers

2025-07-11 · Wongi Jeong, Kyungryeol Lee, Hoigi Seo, Se Young Chun arxiv

Diffusion transformers (DiTs) offer excellent scalability for high-fidelity generation, but their computational overhead poses a great challenge for practical deployment. Existing acceleration methods primarily exploit t…

MosaicDiff: Training-free Structural Pruning for Diffusion Model Acceleration Reflecting Pretraining Dynamics

2025-10-13 · Bowei Guo, Shengkun Tang, Cong Zeng, Zhiqiang Shen arxiv

Diffusion models are renowned for their generative capabilities, yet their pretraining processes exhibit distinct phases of learning speed that have been entirely overlooked in prior post-training acceleration efforts in…

Analyzing and Improving Fast Sampling of Text-to-Image Diffusion Models

2026-02-28 · Zhenyu Zhou, Defang Chen, Siwei Lyu, Chun Chen 외 arxiv

Text-to-image diffusion models have achieved unprecedented success but still struggle to produce high-quality results under limited sampling budgets. Existing training-free sampling acceleration methods are typically dev…

Multi-Resolution Flow Matching: Training-Free Diffusion Acceleration via Staged Sampling

2026-07-02 · Xingyu Zheng, Xianglong Liu, Yifu Ding, Weilun Feng 외 arxiv

Hardware-agnostic strategies for accelerating text-to-image diffusion, such as timestep distillation and feature caching, can reduce inference time without custom kernels or system-level optimization. Among them, multi-r…

CHORDS: Diffusion Sampling Accelerator with Multi-core Hierarchical ODE Solvers

2025-07-21 · Jiaqi Han, Haotian Ye, Puheng Li, Minkai Xu 외 arxiv

Diffusion-based generative models have become dominant generators of high-fidelity images and videos but remain limited by their computationally expensive inference procedures. Existing acceleration techniques either req…