MrFlow: Training-Free 10-25x Speedup for Flow-Matching Text-to-Image Models

Beihang University

Research official + media 2 src. ~1 min

MrFlow accelerates pretrained flow-matching text-to-image models without retraining: generates coarse structure at low resolution, upsamples with a lightweight GAN, injects low-strength noise for detail recovery, then refines at full resolution. Achieves 10x end-to-end speedup on FLUX.1-dev and Qwen-Image with under 1% quality degradation; up to 25x combined with timestep distillation.

Why it matters

Training-free means it applies immediately to any already-released flow-matching model; gains stack with distillation and directly benefit API providers and local GPU users running FLUX variants.

Importance: 3/5

10-25x inference speedup with no retraining and <1% quality loss; immediately deployable across the FLUX ecosystem.

diffusion efficiency inference text-to-image flow-matching

Sources

official arXiv:2607.01642 — MrFlow

media HuggingFace Daily Papers