PixelRush：基于单步扩散的超快速免训练高分辨率图像生成
PixelRush: Ultra-Fast, Training-Free High-Resolution Image Generation via One-step Diffusion
把高分辨率文生图从「多轮反演+重生成」改成低步数下的图像块并行去噪，配合无缝融合与噪声注入抑制块间伪影和过平滑，可直接复用到任何预训练扩散模型的分辨率外推场景。
原文依据 PixelRush enables efficient patch-based denoising within a low-step regime
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论预训练扩散模型在生成高质量图像方面表现出色，但其本质上受限于原生训练分辨率。近期免训练方法试图通过在去噪过程中引入干预来突破这一限制；然而这些方法带来大量计算开销，生成单张 4K 图像往往需要五分钟以上。本文提出 PixelRush，首个面向实用高分辨率文生图生成的免调优框架。该方法建立在已有的基于图像块的推理范式之上，但无需多轮反演与重生成循环，而是在低步数机制下实现高效的基于图像块的去噪。针对少步生成中图像块融合引入的伪影，我们提出无缝融合策略；此外，我们通过噪声注入机制缓解过平滑效应。PixelRush 具有出色的效率，约 20 秒即可生成 4K 图像，相较最优方法实现 10 倍至 35 倍加速，同时保持更优的视觉保真度。大量实验验证了该方法的性能提升与输出质量。
英文原文摘要 1263 字符
Pre-trained diffusion models excel at generating high-quality images but remain inherently limited by their native training resolution. Recent training-free approaches have attempted to overcome this constraint by introducing interventions during the denoising process; however, these methods incur substantial computational overhead, often requiring more than five minutes to produce a single 4K image.In this paper, we present PixelRush, the first tuning-free framework for practical high-resolution text-to-image generation. Our method builds upon the established patch-based inference paradigm but eliminates the need for multiple inversion and regeneration cycles. Instead, PixelRush enables efficient patch-based denoising within a low-step regime. To address artifacts introduced by patch blending in few-step generation, we propose a seamless blending strategy. Furthermore, we mitigate over-smoothing effects through a noise injection mechanism. PixelRush delivers exceptional efficiency, generating 4K images in approximately 20 seconds representing a 10xto 35xspeedup over state-of-the-art methods while maintaining superior visual fidelity. Extensive experiments validate both the performance gains and the quality of outputs achieved by our approach.