Spectral Progressive Diffusion for Efficient Image and Video Generation

ArXi:2605.18736v1 Announce Type: new Diffusion models have been shown to implicitly generate visual content autoregressively in the frequency domain, where low-frequency components are generated earlier in the denoising process while high-frequency details emerge only in later timesteps. This structure offers a natural opportunity for efficient generation, as high-resolution computation on noise-dominated frequencies is largely redundant.