AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

FMBoost: Boosting Latent Diffusion with Flow Matching

Johannes S Fischer, Ming Gui, Pingchuan Ma, Nick Stracke, Stefan Andreas Baumann, Vincent Tao Hu, Björn Ommer

ECCV 2024 · Image generation › Fast diffusion sampling · approach: Flow matching distillation · 33 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use coupling flow matching instead of one-step L1/L2 regression for latent upsampling (ablation)latent upsampler · FacesHQFID: 4.52 -> 1.36Improved
use coupling flow matching instead of a diffusion upsampler (ablation)latent upsampler · FacesHQFID: 2.72 -> 1.36Improved
use data-dependent coupling (start from low-res latent) instead of naive flow matching from noise (ablation)flow matching upsampler · FacesHQp-FID: 2.10 -> 1.62Improved
use data-dependent coupling instead of naive flow matching (ablation)flow matching upsampler · FacesHQFID: 1.37 -> 1.36No clear effect
use CFM instead of diffusion upsampler at 4 steps (256 to 1024)SD1.5 upsampling · Zero-shot LAION-5kp-FID: 50.53 -> 24.02Improved
use CFM instead of diffusion upsampler at 40 steps (512 to 1024)SD1.5 upsampling · Zero-shot LAION-5kFID: 22.29 -> 21.67Improved
add Gaussian noise augmentation to the low-res latent (ablation)CFM · FID and p-FID, 256 to 1024FIDImproved
upsample low-res latent in pixel space instead of nearest or bilinear in latent space (ablation)CFM · convergenceconvergence speed and qualityImproved
boost SD1.5 with CFM instead of using LCM-LoRA SDXL for 1024 imageshigh-resolution synthesis · Zero-shot LAION-5k 1024x1024FID: 28.98 -> 21.67Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy