AI Paper Atlas

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

Generating Multi-Image Synthetic Data for Text-to-Image Customization

Nupur Kumari, Xi Yin, Jun-Yan Zhu, Ishan Misra, Samaneh Azadi

ICCV 2025 · Image generation › Text-to-image diffusion · approach: Personalized and region-controlled generation · 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 normalized image/text guidance inference (ablation)IP-Adapter Plus · DreamBooth (1 reference image)TIFA: 0.615 -> 0.816Improved
add normalized guidance inference (ablation)IP-Adapter Plus · DreamBooth (1 reference image)MDINOv2-I (property change): 0.737 -> 0.668Hurt
add normalized guidance instead of guidance rescale (ablation)IP-Adapter Plus · DreamBooth (1 reference image)Geometric score: 0.710 -> 0.756Improved
fine-tune on SynCD dataset (ablation)IP-Adapter Plus · DreamBooth (1 reference image)Geometric score: 0.756 -> 0.819Improved
add masked shared attention reference conditioning (ablation)IP-Adapter Plus · DreamBooth (1 reference image)Geometric score: 0.819 -> 0.825Improved
use 3 reference images instead of 1 at inference (ablation)Ours (3B) · DreamBoothGeometric score: 0.825 -> 0.838Improved
add masked shared attention in dataset generation (ablation)SynCD deformable · SynCD dataset curationDINOv2-I: 0.626 -> 0.700Improved
add detailed object descriptions to prompts (ablation)SynCD deformable · SynCD dataset curationDINOv2-I: 0.564 -> 0.700Improved
add feature warping with 3D assets (ablation)SynCD rigid · SynCD dataset curationDINOv2-I: 0.572 -> 0.598Improved
add MSA on top of depth guidance (ablation)SynCD rigid · SynCD dataset curationDINOv2-I: 0.495 -> 0.572Improved
increase training dataset from 100 to 95K samples (ablation)Ours (12B) · DreamBoothMDINOv2-I: 0.736 -> 0.774Improved
increase training dataset from 100 to 95K samples (ablation)Ours (3B) · DreamBoothMDINOv2-I: 0.790 -> 0.813Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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