AI Paper Atlas

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

Text2Outfit: Controllable Outfit Generation with Multimodal Language Models

Yuanhao Zhai, Yen-Liang Lin, Minxu Peng, Larry S. Davis, Ashwin Chandramouli, Junsong Yuan, David Doermann

ICCV 2025 · Image generation › Text-to-image diffusion · approach: Personalized and region-controlled generation · 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
add text modality to image tokens (multimodal feature) (ablation)Text2Outfit · Polyvore text-to-outfitAvg P@10: 63.76% -> 65.45%Improved
fine-tune LLM with LoRA instead of frozen (ablation)Text2Outfit · Polyvore text-to-outfitAvg P@10: 65.45% -> 84.82%Improved
fine-tune LLM with LoRA instead of frozen (ablation)Text2Outfit · Polyvore text-to-outfitCP score: 78.62% -> 86.95%Improved
use Local BCE instead of Global CE for attention mask loss (ablation)Text2Outfit · Polyvore text-to-outfitAvg P@10: 87.99 -> 89.95Improved
use Local BCE instead of Global CE for attention mask loss (ablation)Text2Outfit · Polyvore text-to-outfitCP score: 85.63 -> 83.43Hurt
add compatibility loss (ablation)Text2Outfit · Polyvore text-to-outfitCP score: 83.43 -> 84.05Improved
add compatibility loss (ablation)Text2Outfit · Polyvore text-to-outfitAvg P@10: 89.95 -> 90.05No clear effect
predict outfit composition instead of using all 11 categories (seed text)Text2Outfit · Polyvore seed-to-outfitComp. score (Claude-3): 2.59 -> 4.57Improved
predict outfit composition instead of using all 11 categories (seed image)Text2Outfit · Polyvore seed-to-outfitComp. score (Claude-3): 2.85 -> 4.32Improved
use fixed ground-truth mask instead of learnable maskText2Outfit · Polyvore text-to-outfitAvg P@10: 90.05 -> 92.56Improved
use outfit-level LLM model instead of single-item retrieval with Fashion-CLIP (text to image)Text2Outfit · Polyvore text-to-outfitAvg P@10: 78.76 -> 90.05Improved

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