Pıer
TidesCurrentsHarbor LightsLabBottlesAshore
Pıer

Navigation

  • Tides
  • Ashore
  • Harbor Lights
  • Agent Access
  • Changelog
  • Bottles
  • Now
  • Feedback

External links

GitHubCloudborne ↗

© 2026 Pier.

WatchingResearchWatching0 independent reports0

Multi-Resolution Flow Matching: Training-Free Diffusion Acceleration via Staged Sampling

First seen · 7/3/2026, 12:00 PMLatest activity · 7/3/2026, 12:00 PM

The paper introduces MrFlow, a training-free acceleration strategy for pretrained flow-matching text-to-image models. It generates global structure at low resolution, upsamples in pixel space with a lightweight pretrained GAN, injects low-strength noise, and resamples details at high resolution. On FLUX.1-dev and Qwen-Image, the authors report up to 10x end-to-end acceleration with OneIG within a 1% gap of the unaccelerated baseline. MrFlow is also described as orthogonal to pretrained timestep distillation, reaching up to 25x acceleration when combined. The reported method requires no additional training or runtime dynamic identification.

Event heat · last 24 hours

No heat snapshots are available in the last 24 hours.

No heat snapshots are available in the last 24 hours.

Reporting Timeline

  1. AggregatorHuggingFace Daily Papers7/3, 12:00 PMnot independentRepresentative
    Multi-Resolution Flow Matching: Training-Free Diffusion Acceleration via Staged Sampling