Normalizing Trajectory Models

Apple Machine Learning Research · 1 week ago · 9

Normalizing Trajectory Models (NTM) reframe few-step reverse diffusion as conditional normalizing flows, enabling exact likelihood training for the full generative trajectory. The method produces high-quality text-to-image samples in four sampling steps. It replaces earlier few-step approaches that rely on distillation or other objectives by keeping the likelihood framework and supports self-distillation from the model’s own score function.