单次采样生成高质量图像，无需多步迭代或复杂训练。
One Step Diffusion via Shortcut Models
- 用单一网络和训练阶段，通过条件控制跳过生成步骤。
- 在不同采样步数下均优于一致性模型和重流方法。
- 适合需要灵活推理步数的快速生成场景。
扩散模型和流匹配模型通过学习从噪声到数据的转换，实现了多样化且逼真的图像生成。然而，这些模型的采样过程需要经过多次神经网络前向传播进行逐步去噪，导致生成速度慢且成本高。以往加速采样方法需复杂的训练策略，如多阶段训练、多个网络或脆弱的调度机制。本文提出快捷模型（shortcut models），一类仅需单个网络和一次训练阶段的生成模型，可在单步或多步采样中生成高质量样本。该模型不仅依赖当前噪声水平，还根据目标采样步长进行条件建模，使模型能直接跳过生成过程中的部分步骤。在广泛的采样步数预算下，快捷模型始终优于一致性模型和重流方法。相比蒸馏方案，快捷模型将复杂度降低为单一网络与训练阶段，并支持推理时灵活调整采样步数。
原文摘要 · Abstract (English)
Diffusion models and flow-matching models have enabled generating diverse and realistic images by learning to transfer noise to data. However, sampling from these models involves iterative denoising over many neural network passes, making generation slow and expensive. Previous approaches for speeding up sampling require complex training regimes, such as multiple training phases, multiple networks, or fragile scheduling. We introduce shortcut models, a family of generative models that use a single network and training phase to produce high-quality samples in a single or multiple sampling steps. Shortcut models condition the network not only on the current noise level but also on the desired step size, allowing the model to skip ahead in the generation process. Across a wide range of sampling step budgets, shortcut models consistently produce higher quality samples than previous approaches, such as consistency models and reflow. Compared to distillation, shortcut models reduce complexity to a single network and training phase and additionally allow varying step budgets at inference time.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。