MrFlow is a multi-resolution staged sampling method that accelerates pretrained flow-matching diffusion models by 10x with under 1% quality loss using low-res generation, GAN super-resolution, noise injection, and high-res refinement.
Spectral Progressive Diffusion for Efficient Image and Video Generation
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
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. We propose Spectral Progressive Diffusion, a general framework that progressively grows resolution along the denoising trajectory of pretrained diffusion models. To this end, we develop a spectral noise expansion mechanism and derive an optimal resolution schedule from the model's power spectrum. Our framework supports training-free acceleration and a novel fine-tuning recipe that further improves efficiency and quality. We demonstrate significant speedups on state-of-the-art pretrained image and video generation models while preserving visual quality.
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Multi-Resolution Flow Matching: Training-Free Diffusion Acceleration via Staged Sampling
MrFlow is a multi-resolution staged sampling method that accelerates pretrained flow-matching diffusion models by 10x with under 1% quality loss using low-res generation, GAN super-resolution, noise injection, and high-res refinement.