AI Paper Atlas

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

Draw Your Mind: Personalized Generation via Condition-Level Modeling in Text-to-Image Diffusion Models

Hyungjin Kim, Seokho Ahn, Young-Duk Seo

ICCV 2025 · Image generation › Text-to-image diffusion · approach: Multi-subject personalization · 4 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 the guidance mechanism G (ablation)DrUM · PIP, Stable Diffusion V1CLIP score (target): 19.04 -> 25.13Improved
add the guidance mechanism G (ablation)DrUM · ML, Stable Diffusion V1CLIP score (target): 22.74 -> 29.49Improved
add coreset sampling S (ablation)DrUM · PIP, Stable Diffusion V1CLIP score (target): 25.49 -> 25.13No clear effect
add coreset sampling S (ablation)DrUM · ML, Stable Diffusion V1CLIP score (target): 29.56 -> 29.49No clear effect
add sampling and guidance together (ablation)DrUM · PIP, Stable Diffusion V1CLIP score (target): 18.13 -> 25.13Improved
use DrUM instead of TVpersonalized generation · PIP, Stable Diffusion V1CLIP score improvement (%): +22.40% -> +34.83%Improved
use DrUM instead of TVpersonalized generation · ML, Stable Diffusion V3CLIP score improvement (%): DrUM -5.60% vs TV -4.47%Hurt
use DrUM instead of TV and PMGpersonalized generation · ML, OpenCLIP ViT-LText align improvement (%): -12.42% (TV) -> +3.13%Improved
use coreset sampling instead of random or uniform samplinguser profiling · PIP/ML, OpenCLIP ViT-LText alignImproved
use DrUM on ML dataset with complex product informationDrUM · ML (Stable Diffusion V3)CLIP score: +4.26% (SDXL) vs -5.60% (SD V3)Hurt

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