多分辨率流匹配：通过分阶段采样的无需训练扩散加速

摘要

硬件无关的文本到图像扩散加速策略（如时间步蒸馏和特征缓存）可在无需定制内核或系统级优化的前提下减少推理时间。其中，多分辨率生成策略近期受到广泛关注，能在无需训练的情况下实现超过5倍的加速。然而，在潜在空间中执行上采样并选择性修改局部区域的设计，导致这类方法出现明显的模糊或伪影。为此，我们提出MrFlow——一种基于预训练流匹配模型的无训练多分辨率加速策略，采用分阶段从低分辨率到高分辨率的流水线。MrFlow首先在低分辨率下快速生成主体结构，随后在像素空间中使用轻量级预训练GAN模型执行超分辨率，接着注入低强度噪声实现高频重采样，最后在高分辨率下精细化细节。在FLUX.1-dev和Qwen-Image上的定量与定性结果表明，MrFlow利用低分辨率采样的二次令牌缩减与步骤需求降低特性，实现了10倍端到端加速，同时将OneIG指标保持在加速前1%的差距内，显著优于其他无训练加速策略，且无需任何训练或运行时动态识别。MrFlow还可进一步与预训练的时间步蒸馏策略正交结合，实现高达25倍的生成加速。

English

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-resolution generation strategies have recently received broad attention, attaining more than 5x speedup without any training. However, the design of performing upsampling in the latent space, together with the selective modification of partial regions, causes these methods to exhibit noticeable blurring or artifacts. To this end, we propose MrFlow, a training-free multi-resolution acceleration strategy for pretrained flow-matching models built upon a staged low-to-high-resolution pipeline. MrFlow first rapidly generates the main structure at low resolution, then performs super-resolution in the pixel space using a lightweight pretrained GAN-based model, subsequently injects low-strength noise to enable high-frequency resampling, and finally refines the details at high resolution. Quantitative and qualitative results on FLUX.1-dev and Qwen-Image show that MrFlow exploits the quadratic token reduction and reduced step requirement of low-resolution sampling to achieve 10x end-to-end acceleration while keeping OneIG within a 1% gap relative to that before acceleration, significantly surpassing other training-free acceleration strategies, and requiring no training or runtime dynamic identification whatsoever. MrFlow can further be directly combined orthogonally with pre-trained timestep distillation strategies, achieving even higher generation acceleration of up to 25x.