AI Paper Atlas

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

Directional Textual Inversion for Personalized Text-to-Image Generation

Kunhee Kim, NaHyeon Park, Kibeom Hong, Hyunjung Shim

ICLR 2026 · Image generation › Text-to-image diffusion · approach: T2I evaluation and controllable adapters · 0 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
fix in-distribution norm and optimize only direction (DTI vs TI)Textual Inversion on SDXL · DreamBooth, SigLIP text alignmenttext alignment: 0.292 -> 0.522Improved
DTI vs TI on image similarityTextual Inversion on SDXL · DreamBooth, DINOv2image similarity: 0.561 -> 0.450Hurt
DTI vs TI on SANA 1.5-4.8BTextual Inversion on SANA · DreamBoothtext alignment: 0.646 -> 0.757Improved
DTI vs TI on SANA 1.5-1.6B image similarityTextual Inversion on SANA · DreamBooth, DINOv2image similarity: 0.480 -> 0.479No clear effect
rescale TI embeddings to in-distribution norm after training (ablation)Textual Inversion on SDXL · DreamBoothtext alignment: 0.292 -> 0.466Improved
rescale TI embeddings to in-distribution norm after training (ablation)Textual Inversion on SDXL · DreamBoothimage similarity: 0.561 -> 0.243Hurt
use RSGD instead of AdamW with projection (ablation)DTI · DreamBooth (SDXL)text alignment: 0.463 -> 0.522Improved
use mean vocabulary norm instead of minimum norm (ablation)DTI · DreamBooth (SDXL)text alignment: 0.074 -> 0.522Improved
use mean vocabulary norm instead of OOD norm 5.0 (ablation)DTI · DreamBooth (SDXL)text alignment: 0.373 -> 0.522Improved
add vMF directional prior (kappa 1e-4 vs 0) (ablation)DTI · DreamBooth (SDXL)text alignment: 0.436 -> 0.522Improved
add vMF directional prior (kappa 1e-4 vs 0) (ablation)DTI · DreamBooth (SDXL)image similarity: 0.507 -> 0.450Hurt
increase vMF concentration to 0.5e-3 (ablation)DTI · DreamBooth (SDXL)image similarity: 0.450 -> 0.278Hurt

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