Lanfeng Alan et al. · Text-to-Image

RDM (Representation Distribution Matching)

Trains one-step image generators with no teacher, adversary or trajectory by matching real vs generated feature distributions across 14 frozen encoders (balanced via a Lagrangian controller); surpasses the 4-step FLUX.2 teacher on GenEval (0.826 vs 0.794), with 63.6% of samples preferred over real photos by PickScore.