aimagelab/multimodal-garment-designer
A latent diffusion model for editing fashion images on human models, published at ICCV 2023.
Not currently ranked — collecting fresh signals.
star history
This repository implements a human-centric latent diffusion model for fashion image editing. It allows designers to manipulate and visualize clothing on human models using multimodal conditioning. The approach builds on stable diffusion techniques and is evaluated on standard fashion datasets like VITON-HD and DressCode.
Frequently asked
- What is aimagelab/multimodal-garment-designer?
- A latent diffusion model for editing fashion images on human models, published at ICCV 2023.
- Is multimodal-garment-designer open source?
- Yes — aimagelab/multimodal-garment-designer is an open-source project tracked on heatdrop.
- What language is multimodal-garment-designer written in?
- aimagelab/multimodal-garment-designer is primarily written in Python.
- How popular is multimodal-garment-designer?
- aimagelab/multimodal-garment-designer has 445 stars on GitHub.
- Where can I find multimodal-garment-designer?
- aimagelab/multimodal-garment-designer is on GitHub at https://github.com/aimagelab/multimodal-garment-designer.