AI Paper Atlas

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

Text-Anchored Score Composition: Tackling Condition Misalignment in Text-to-Image Diffusion Models

Luozhou Wang, Guibao Shen, Wenhang Ge, Guangyong Chen, Yijun Li, Yingcong Chen

ECCV 2024 · Image generation › Text-to-image diffusion · approach: Compositional text-to-image guidance · 7 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 attention realignment to score composition (ablation)TASC with ControlNets · ControlNets ablationimage-condition distance: 9.59% -> 1.58%Improved
add attention realignment to score composition (ablation)TASC with GLIGEN · GLIGEN ablationimage-condition distance: 6.23% -> 4.34%Improved
add attention realignment to score composition (ablation)TASC with GLIGEN · GLIGEN ablationimage-text similarity: 74.81% -> 79.87%Improved
add attention realignment to score composition (ablation)TASC with ControlNets · ControlNets ablationimage-text similarity: 73.78% -> 73.88%No clear effect
text-anchored score composition without realignment vs plain SD (ablation)Stable Diffusion with ControlNets · ControlNets ablationimage-text similarity: 69.49% -> 73.78%Improved
TASC vs Attend-and-Excite on CLIP scoreStable Diffusion · Misaligned-condition promptsCLIP Score: 0.3253 -> 0.3323Improved
TASC vs Attend-and-Excite on FIDStable Diffusion · MSCOCOFID: 111.41 -> 107.39Improved
TASC vs Attend-and-Excite on controllabilityControlNets · Controllability with ControlNetsrelative image-condition distance: 14.1% -> 1.6%Improved
StructureDiffusion instead of plain SDStable Diffusion · Misaligned-condition promptsCLIP Score: 0.2934 -> 0.2928No clear effect
TASC added compute versus plain SDStable Diffusion · Inference costTime (seconds): 9.70 -> 13.88Hurt

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