# rlawjdghek/StableVITON

[CVPR2024] StableVITON: Learning Semantic Correspondence with Latent Diffusion Model for Virtual Try-On

Repository: https://github.com/rlawjdghek/StableVITON
Canonical: https://ross.abutalabs.com/products/stableviton
Homepage: https://rlawjdghek.github.io/StableVITON/
Language: Python
License Family: other
Last push: 2025-10-12T11:55:22+00:00

## Health v2 (maintenance only)
Score: 47/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 46, release rhythm 35, longevity 71
- inputs: {"age_days": 1005, "days_push": 325, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1261, forks 210 (observed 2026-08-28T04:04:10.204408+00:00)

## What it is
StableVITON is the official PyTorch implementation of a CVPR 2024 paper that performs image-based virtual try-on using a pre-trained latent diffusion model. It learns semantic correspondence between clothing and human body via zero cross-attention blocks to generate high-fidelity images of a person wearing a given garment.

## Use cases
- generate images of a person wearing a specific garment
- virtual try-on from a person photo and clothing photo
- try clothes on arbitrary person images using SAM segmentation
- research on diffusion-based image editing
- reproduce CVPR 2024 virtual try-on results on VITON-HD

## When to choose
- you need state-of-the-art academic virtual try-on with detail preservation
- you want to build on or extend a published diffusion-based try-on model
- you work with the VITON-HD benchmark dataset

## When to avoid
- you need a production-ready e-commerce try-on service with support and license
- you lack a CUDA GPU or cannot run heavy diffusion inference
- you need a no-code or hosted solution

## Facets
- artifact type: library
- maturity: stable
- function: image-processing, machine-learning, deep-learning, stable-diffusion
- domain: computer-vision, image-processing, artificial-intelligence, deep-learning
- platform: python
- tags: virtual-try-on, diffusion-model, latent-diffusion, cvpr2024, fashion, image-generation, research-code, linux, gpu

## Member repositories
- rlawjdghek/StableVITON (main) score 47

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:10.204408+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T05:04:20.365262+00:00, confidence not recorded.
  - readme: https://github.com/rlawjdghek/StableVITON (fetched 2026-08-28T04:04:10.204408+00:00, sha 01d629e054d4)
  - homepage: https://rlawjdghek.github.io/StableVITON/ (fetched 2026-08-29T12:16:58.033793+00:00, sha f43b3722cab9)
- Data as of 2026-08-30T08:39:29.467469+00:00.