AI Paper Atlas

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

RealCustom++: Representing Images as Real Textual Word for Real-Time Customization

Zhendong Mao, Mengqi Huang, Fei Ding, Mingcong Liu, Qian He, Yongdong Zhang

TPAMI 2025 · Image generation › Text-to-image diffusion · approach: Personalized and region-controlled generation · 24 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 low-res cross-attn plus high-res self-attn mask guidance instead of conference version (ablation)RealCustom++ · DreamBench SDXLCLIP-B-T: 32.20 -> 33.43Improved
use low-res cross-attn plus high-res self-attn mask guidance instead of conference version (ablation)RealCustom++ · DreamBench SDXLCLIP-B-I: 84.23 -> 87.32Improved
use high-resolution instead of all-resolution self-attention for the mask (ablation)RealCustom++ · DreamBench SDXLCLIP-B-T: 31.08 -> 33.43Improved
add maximum mask normalization (ablation)RealCustom++ · DreamBench SDXLCLIP-B-T: 30.26 -> 33.43Improved
raise Top-K ratio from 0.1 to 0.2 (ablation)RealCustom++ · DreamBench SDXLCLIP-B-I: 84.43 -> 87.32Improved
raise Top-K ratio from 0.2 to 0.5 (ablation)RealCustom++ · DreamBench SDXLCLIP-B-T: 33.43 -> 31.08Hurt
add early stop mask regularization (ablation)RealCustom++ · DreamBench SDXLCLIP-B-I: 86.67 -> 87.32Improved
add cross-scale mechanism to the projector (ablation)RealCustom++ · DreamBench SDXLCLIP-B-I: 86.12 -> 87.32Improved
use cross-scale token concat + cross-layer element add instead of cross-scale element add (ablation)RealCustom++ · DreamBench SDXLCLIP-B-T: 29.94 -> 33.43Improved
add curriculum data strategy instead of 50% random mixing (ablation)RealCustom++ · DreamBench SDXLCLIP-B-I: 85.33 -> 86.11Improved
use curriculum cropping instead of fixed random cropping (ablation)RealCustom++ · DreamBench SDXLCLIP-B-I: 86.82 -> 87.32Improved
add multiview data to text-image data (curriculum) (ablation)RealCustom++ · DreamBench SDXLCLIP-B-T: 30.02 -> 32.10Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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