Consistency Models (CM) (Song et al., 2023) accelerate score-based diffusion model sampling at the cost of sample quality but lack a natural way to trade-off quality for speed. To address this limitation, we propose Consistency Trajectory Model (CTM), a generalization encompassing CM and score-based models as special cases. CTM trains a single neural network that can -- in a single forward pass -- output scores (i.e., gradients of log-density) and enables unrestricted traversal between any initial and final time along the Probability Flow Ordinary Differential Equation (ODE) in a diffusion process. CTM enables the efficient combination of adversarial training and denoising score matching loss to enhance performance and achieves new state-of-the-art FIDs for single-step diffusion model sampling on CIFAR-10 (FID 1.73) and ImageNet at 64x64 resolution (FID 1.92). CTM also enables a new family of sampling schemes, both deterministic and stochastic, involving long jumps along the ODE solution trajectories. It consistently improves sample quality as computational budgets increase, avoiding the degradation seen in CM. Furthermore, unlike CM, CTM's access to the score function can streamline the adoption of established controllable/conditional generation methods from the diffusion community. This access also enables the computation of likelihood. The code is available at https://github.com/sony/ctm.

翻译：一致性模型（Consistency Models, CM）(Song et al., 2023)以牺牲样本质量为代价加速基于分数的扩散模型采样，但缺乏在质量与速度间进行权衡的自然方式。为解决这一局限，我们提出一致性轨迹模型（Consistency Trajectory Model, CTM），这是一种将CM和基于分数的模型作为特例的泛化框架。CTM训练单个神经网络，可在单次前向传播中输出分数（即对数密度的梯度），并支持沿扩散过程中概率流常微分方程（Probability Flow Ordinary Differential Equation, ODE）在任意初始与最终时刻间自由遍历。CTM通过高效结合对抗训练与去噪分数匹配损失提升性能，在CIFAR-10（FID 1.73）和64×64分辨率ImageNet（FID 1.92）上实现了单步扩散模型采样的新最优FID值。CTM还催生了一系列沿ODE解轨迹进行长跳的确定性及随机采样方案。随着计算预算增加，CTM持续提升样本质量，避免了CM中出现的性能退化。此外，与CM不同，CTM对分数函数的访问能力可简化扩散社区中成熟可控/条件生成方法的适配，并支持计算似然。代码已开源：https://github.com/sony/ctm。