SANA-Sprint：基于连续时间一致性蒸馏的一步扩散模型

SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillation

March 12, 2025

作者: Junsong Chen, Shuchen Xue, Yuyang Zhao, Jincheng Yu, Sayak Paul, Junyu Chen, Han Cai, Enze Xie, Song Han

cs.AI

摘要

本文介绍了SANA-Sprint，一种用于超快速文本到图像（T2I）生成的高效扩散模型。SANA-Sprint基于预训练的基础模型，并通过混合蒸馏技术进行增强，将推理步骤从20步大幅减少至1-4步。我们提出了三项关键创新：（1）我们提出了一种无需训练的方法，将预训练的流匹配模型转化为连续时间一致性蒸馏（sCM），避免了从头训练的高昂成本，实现了高效的训练。我们的混合蒸馏策略结合了sCM与潜在对抗蒸馏（LADD）：sCM确保与教师模型的对齐，而LADD则提升了单步生成的保真度。（2）SANA-Sprint是一个统一的步数自适应模型，能够在1-4步内实现高质量生成，消除了针对特定步数的训练，提高了效率。（3）我们将ControlNet与SANA-Sprint集成，实现了实时交互式图像生成，为用户交互提供即时视觉反馈。SANA-Sprint在速度与质量的权衡中确立了新的帕累托前沿，仅用1步便达到了7.59 FID和0.74 GenEval的顶尖性能，超越了FLUX-schnell（7.94 FID / 0.71 GenEval），同时速度提升了10倍（H100上0.1秒对比1.1秒）。在H100上，1024 x 1024图像的T2I延迟为0.1秒，ControlNet延迟为0.25秒，在RTX 4090上T2I延迟为0.31秒，展示了其在AI驱动的消费应用（AIPC）中的卓越效率和潜力。代码与预训练模型将开源发布。

English

This paper presents SANA-Sprint, an efficient diffusion model for ultra-fast text-to-image (T2I) generation. SANA-Sprint is built on a pre-trained foundation model and augmented with hybrid distillation, dramatically reducing inference steps from 20 to 1-4. We introduce three key innovations: (1) We propose a training-free approach that transforms a pre-trained flow-matching model for continuous-time consistency distillation (sCM), eliminating costly training from scratch and achieving high training efficiency. Our hybrid distillation strategy combines sCM with latent adversarial distillation (LADD): sCM ensures alignment with the teacher model, while LADD enhances single-step generation fidelity. (2) SANA-Sprint is a unified step-adaptive model that achieves high-quality generation in 1-4 steps, eliminating step-specific training and improving efficiency. (3) We integrate ControlNet with SANA-Sprint for real-time interactive image generation, enabling instant visual feedback for user interaction. SANA-Sprint establishes a new Pareto frontier in speed-quality tradeoffs, achieving state-of-the-art performance with 7.59 FID and 0.74 GenEval in only 1 step - outperforming FLUX-schnell (7.94 FID / 0.71 GenEval) while being 10x faster (0.1s vs 1.1s on H100). It also achieves 0.1s (T2I) and 0.25s (ControlNet) latency for 1024 x 1024 images on H100, and 0.31s (T2I) on an RTX 4090, showcasing its exceptional efficiency and potential for AI-powered consumer applications (AIPC). Code and pre-trained models will be open-sourced.