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（CM）（Song等人，2023）以牺牲样本质量为代价加速基于得分的扩散模型采样，但缺乏自然地在质量与速度之间进行权衡的能力。为解决这一局限性，我们提出一致性轨迹模型（CTM），这是一种将CM和基于得分的模型作为特例的泛化方法。CTM训练单个神经网络，该网络能够在单次前向传播中输出得分（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（ODE）在任意初始和最终时间之间进行无限制遍历。CTM能够高效结合对抗训练与去噪得分匹配损失以提升性能，并在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。CTM还衍生出一类新的确定性及随机性采样方案，涉及沿ODE解轨迹的长程跳跃。随着计算预算增加，CTM能持续提升样本质量，避免了CM中出现的性能退化现象。此外，与CM不同，CTM对得分函数的访问能力可简化扩散社区中成熟的可控/条件生成方法的采用。这一访问能力还支持似然计算。代码已开源至https://github.com/sony/ctm。