miccunifi/ladi-vton
A latent diffusion model enhanced with textual inversion that generates virtual try-on images of people wearing garments.
Not currently ranked — collecting fresh signals.
star history
LaDI-VTON is a virtual try-on system that synthesizes images of a target person wearing a given garment. It extends a latent diffusion model with a novel autoencoder module and learnable skip connections to enhance garment preservation and person fidelity. The approach uses textual inversion to enable garment-specific customization and was published at ACM Multimedia 2023.
Frequently asked
- What is miccunifi/ladi-vton?
- A latent diffusion model enhanced with textual inversion that generates virtual try-on images of people wearing garments.
- Is ladi-vton open source?
- Yes — miccunifi/ladi-vton is an open-source project tracked on heatdrop.
- What language is ladi-vton written in?
- miccunifi/ladi-vton is primarily written in Python.
- How popular is ladi-vton?
- miccunifi/ladi-vton has 464 stars on GitHub.
- Where can I find ladi-vton?
- miccunifi/ladi-vton is on GitHub at https://github.com/miccunifi/ladi-vton.