AI Paper Atlas

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

MaskDiffusion: Boosting Text-to-Image Consistency with Conditional Mask

Yupeng Zhou, Daquan Zhou, Yaxing Wang, Jiashi Feng, Qibin Hou

IJCV 2024 · Image generation › Text-to-image diffusion · approach: Compositional text-to-image guidance · 17 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 conditional cross-attention maskStable Diffusion · User study (simple prompts)supporting rate: 3.10% -> 83.16%Improved
add conditional cross-attention maskStable Diffusion · User study (complex prompts)supporting rate: 9.16% -> 74.77%Improved
add conditional cross-attention maskStable Diffusion · CLIP scoreCLIP score: 26.16 -> 26.82Improved
add conditional cross-attention maskStable Diffusion · Inference timeseconds: 81s -> 81sNo clear effect
use mask instead of Attend-and-Excite iterative optimizationAttend-and-Excite · Inference timeseconds: 215s -> 81sImproved
use MaskDiffusion instead of Composable DiffusionComposable Diffusion · CLIP scoreCLIP score: 26.59 -> 26.82Improved
add momentum updating of cross-attention maps (ablation)MaskDiffusion · Qualitative object presencequalitativeImproved
add mask on 16x16 cross-attention resolution (ablation)MaskDiffusion · Qualitative consistencyqualitativeImproved

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