nxnai/Voost
[SIGGRAPH Asia 25] Voost: A Unified and Scalable Diffusion Transformer for Bidirectional Virtual Try-On and Try-Off
Implements a unified diffusion transformer architecture that handles both garment insertion and removal in a single model, eliminating the need for separate pipelines. The approach leverages transformer-based denoising with robustness to diverse poses, garment types, backgrounds, and lighting conditions. Available as a public demo on Hugging Face Spaces and targets practical e-commerce and fashion applications.
338 stars.
Stars
338
Forks
26
Language
—
License
—
Category
Last pushed
Oct 14, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/nxnai/Voost"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Zheng-Chong/CatVTON
[ICLR 2025] CatVTON is a simple and efficient virtual try-on diffusion model with 1) Lightweight...
rizavelioglu/tryoffdiff
[CVPR'25-Demo] Official repository of "TryOffDiff: Virtual-Try-Off via High-Fidelity Garment...
muzishen/IMAGGarment
[TVCG 2026] 🎨 IMAGGarment🎨 : Fine-Grained Garment Generation with Controllable Structure,...
muzishen/IMAGDressing
[AAAI 2025]👔IMAGDressing👔: Interactive Modular Apparel Generation for Virtual Dressing. It...
miccunifi/ladi-vton
[ACM MM 2023] - LaDI-VTON: Latent Diffusion Textual-Inversion Enhanced Virtual Try-On