Diffusion-based models decompose sampling into many small Gaussian denoising steps -- an assumption that breaks down when generation is compressed to a few coarse transitions. Existing few-step methods address this through distillation, consistency training, or adversarial objectives, but sacrifice the likelihood framework in the process. We introduce Normalizing Trajectory Models (NTM), which models each reverse step as an expressive conditional normalizing flow with exact likelihood training. Architecturally, NTM combines shallow invertible blocks within each step with a deep parallel predictor across the trajectory, forming an end-to-end network trainable from scratch or initializable from pretrained flow-matching models. Its exact trajectory likelihood further enables self-distillation: a lightweight denoiser trained on the model's own score produces high-quality samples in four steps. On text-to-image benchmarks, NTM matches or outperforms strong image generation baselines in just four sampling steps while uniquely retaining exact likelihood over the generative trajectory.

翻译：扩散模型将采样过程分解为许多小的高斯去噪步骤——当生成过程被压缩为少量粗糙的转换时，这一假设将不再成立。现有的少步方法通过蒸馏、一致性训练或对抗性目标来解决这一问题，但在此过程中牺牲了似然框架。我们引入了归一化轨迹模型（NTM），它将每个反向步骤建模为具有精确似然训练的表达性条件归一化流。在架构上，NTM在每个步骤内结合了浅层可逆块，并在轨迹上结合了深度并行预测器，形成了一种可从零开始训练或从预训练的流匹配模型初始化的端到端网络。其精确的轨迹似然进一步支持自蒸馏：一个在模型自身得分上训练的轻量级去噪器可在四步内生成高质量样本。在文本到图像基准测试中，NTM在仅需四步采样的条件下匹配或优于强大的图像生成基线，同时独特地保留了生成轨迹上的精确似然。