Research map / Image generation / Text-to-image diffusion
MMTryon: Multi-Modal Multi-Reference Control for High-Quality Fashion Generation
Xujie Zhang, Ente Lin, Michael Kampffmeyer, Zhenyu Xie, Jiang Li, Ting Liu, Xiaochao Qu, Luoqi Liu, Xiaodan Liang
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add pretrained garment encoder (ablation) | MMTryon · Ablation (multi-modal try-on) | FID: 10.230 -> 8.187 | Improved |
| add pretrained garment encoder (ablation) | MMTryon · Ablation (multi-modal try-on) | CLIP score: 0.22 -> 0.30 | Improved |
| add text query loss (ablation) | MMTryon · Ablation (multi-modal try-on) | FID: 9.250 -> 8.187 | Improved |
| add text query loss (ablation) | MMTryon · Ablation (multi-modal try-on) | CLIP score: 0.24 -> 0.30 | Improved |
| add multi-reference attention (ablation) | MMTryon · Ablation (multi-modal try-on) | FID: 12.890 -> 8.187 | Improved |
| add multi-reference attention (ablation) | MMTryon · Ablation (multi-modal try-on) | KID: 0.87 -> 0.42 | Improved |
| add multi-reference attention (ablation) | MMTryon · Ablation (multi-modal try-on) | CLIP score: 0.18 -> 0.30 | Improved |
| compare against CatVTON on single-garment try-on | MMTryon · Single garment try-on (VITON-HD) | FID: 8.010 vs 8.702 | Hurt |
| compare against CatVTON on single-garment try-on | MMTryon · Single garment try-on (VITON-HD) | SSIM: 0.870 -> 0.902 | Improved |
| compare against Nano Banana on multi-modal try-on | MMTryon · Multi-modal try-on | CLIP score: 0.22 -> 0.30 | Improved |
| add diffusion loss to the garment encoder training (ablation) | MMTryon · Qualitative ablation | visual quality | Improved |
| add augmented high-quality inpainted dataset (ablation) | MMTryon · Qualitative ablation | query accuracy | Improved |
Closest papers by meaning
- Garments2Look: A Multi-Reference Dataset for High-Fidelity Outfit-Level Virtual Try-On with Clothing and Accessories (CVPR 2026 · similarity 0.92)
- MOFA-VTON: More Fashion Possibilities with Fine-Grained Adaptations in Virtual Try-On (CVPR 2026 · similarity 0.91)
- M&M VTO: Multi-Garment Virtual Try-On and Editing (CVPR 2024 · similarity 0.90)
- IMAGDressing-v1: Customizable Virtual Dressing (AAAI 2025 · similarity 0.89)
- Cascaded Diffusion Models for Virtual Try-On: Improving Control and Resolution (AAAI 2025 · similarity 0.88)
- MV-VTON: Multi-View Virtual Try-On with Diffusion Models (AAAI 2025 · similarity 0.88)
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.
