AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Glance: Accelerating Diffusion Models with 1 Sample

Zhuobai Dong, Rui Zhao, songjie wu, Suyang Hou, Junchao Yi, Zhengyuan Yang, Lijuan Wang, Alex Jinpeng Wang

ECCV 2026 · Image generation › Fast diffusion sampling · approach: Training-free diffusion acceleration · 3 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
add Fast-LoRA for late steps (ablation)Slow3 + Base5 · OneIG-Bench (Qwen-Image)Alignment: 0.805 -> 0.849Improved
add Slow-LoRA for early steps (ablation)Base3 + Fast5 · OneIG-Bench (Qwen-Image)Alignment: 0.747 -> 0.849Improved
use two phase-specific LoRAs instead of a single LoRA at identical timesteps (ablation)Single (identical) · OneIG-Bench (Qwen-Image)Alignment: 0.702 -> 0.849Improved
use phase-aware Slow-Fast instead of single uniform LoRA (ablation)Single (uniform) · OneIG-Bench (Qwen-Image)Alignment: 0.621 -> 0.849Improved
scale training set from 1 to 10 samples (ablation)Glance (Qwen 10x2) · OneIG-Bench (Qwen-Image)Alignment: 0.868 -> 0.874No clear effect
scale training set from 1 to 100 samples (ablation)Glance (Qwen 10x2) · OneIG-Bench (Qwen-Image)Alignment: 0.868 -> 0.876No clear effect
scale training set from 1 to 10 samples (ablation)Glance (Qwen 10x2) · OneIG-Bench (Qwen-Image)Style: 0.421 -> 0.414Hurt
increase LoRA timesteps from Slow3+Fast5 to Slow5+Fast5 (ablation)Glance (Qwen) · OneIG-Bench (Qwen-Image)Text: 0.692 -> 0.734Improved
increase LoRA timesteps from Slow5+Fast5 to Slow5+Fast10 (ablation)Glance (Qwen) · OneIG-Bench (Qwen-Image)Text: 0.734 -> 0.813Improved
train on text-rich Bookstore sample instead of Fox (ablation)Glance (Qwen 10x2) · OneIG-Bench (Qwen-Image)Alignment: 0.868 -> 0.797Hurt
train on out-of-domain real-world image instead of Fox (ablation)Glance (Qwen 10x2) · OneIG-Bench (Qwen-Image)Alignment: 0.868 -> 0.857No clear effect
train on pure Gaussian noise (ablation)Glance · single-sample trainingimage qualityHurt

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