AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

Toward Early Quality Assessment of Text-to-Image Diffusion Models

Huanlei Guo, Hongxin Wei, Bingyi Jing

CVPR 2026 · Image generation › Text-to-image diffusion · approach: Inference-time T2I improvement · 0 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
select top-1 of 5 seeds at t=0.2 using probe-predicted ImageRewardSD2 · MS-COCO valImageReward: 0.49 -> 1.59Improved
select top-1 of 5 seeds at t=0.2 using probe-predicted ImageRewardSD3.5-Medium · MS-COCO valImageReward: 1.12 -> 1.83Improved
select top-1 of 5 seeds at t=0.2 using probe-predicted ImageRewardFLUX.1-dev · MS-COCO valHPSv2.1: 29.14 -> 31.47Improved
select with ImageReward probe instead of BLIP-ITM probe (ablation)SD2 selection · MS-COCO valImageReward / CLIPScore: IR 1.09 -> 1.59; CLIPScore 33.96 -> 33.50Mixed
add early selection (Probe-Select)SD3-M FID · MS-COCOFID: 25.26 -> 25.01Improved
move probe checkpoint from t=0.1 to t=0.2 (ablation)Probe-Select (SD2) · Spearman with ImageRewardSpearman correlation: 0.70 -> 0.99Improved
move probe checkpoint from t=0.2 to later (0.3-0.6) (ablation)Probe-Select · Spearman correlation, all backbonesSpearman correlation: SD2 HPSv2.1 0.64 -> 0.64No clear effect
increase candidate pool N from 10 to 100 at fixed K=1 (ablation)Probe-Select (FLUX.1-dev) · 1000 MS-COCO captionsTop-1 ImageReward: 1.36 -> 1.45Improved
increase continued seeds K (ablation)Probe-Select (FLUX.1-dev) · 1000 MS-COCO captionsTop-K ImageRewardHurt
select seeds early vs draw more candidates without selection (ablation)FLUX.1-dev · 1000 MS-COCO captionsImageReward: 0.95 (no selection) -> 1.45 (Top-1, N=100)Improved

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