Skip to main content
Search

# ReLSA (Refined Latent Scale Adaptation)

1 related articles

Subscribe to updates
  1. arXiv

    FlexVSR freezes the streaming super-resolution prior and trains a 0.274M-parameter adapter, so one model covers continuous scales

    Real-time streaming video generation needs non-integer, variable magnification at deployment, yet fixed-scale generative video super-resolution either computes at its native scale and downsamples at redundant cost or retrains the diffusion transformer per scale and alters the shared prior. FlexVSR separates prior preparation from scale adaptation: the VAE, super-resolution DiT and upsampler stay frozen while a 0.274M-parameter latent adapter, ReLSA, builds a target-grid latent and then applies a scale-conditioned residual correction. Supervised at only two scales, it holds reconstruction and temporal consistency on unseen continuous scales and runs at lower latency than most compared streaming baselines.

You’re all caught up