# shadow2496/VITON-HD

Official PyTorch implementation of "VITON-HD: High-Resolution Virtual Try-On via Misalignment-Aware Normalization" (CVPR 2021)

Repository: https://github.com/shadow2496/VITON-HD
Canonical: https://ross.abutalabs.com/products/viton-hd
Homepage: https://psh01087.github.io/VITON-HD
Language: Python
License: NOASSERTION
License Family: other
Topics: deep-learning, image-generation, normalization, virtual-try-on, viton, clothing-agnostic-representation
Last push: 2025-04-27T14:52:13+00:00

## Health v2 (maintenance only)
Score: 40/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 18, release rhythm 35, longevity 100
- inputs: {"age_days": 1980, "days_push": 493, "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 1161, forks 250 (observed 2026-08-28T04:03:49.394126+00:00)

## What it is
Official PyTorch implementation of VITON-HD (CVPR 2021), a high-resolution image-based virtual try-on model that transfers a clothing item onto a person's photo at 1024x768 resolution using misalignment-aware ALIAS normalization. It includes training/inference code and a preprocessed 1024x768 try-on dataset for research use.

## Use cases
- generate virtual try-on images of clothes on a person
- try on clothing items on model photos at high resolution
- research high-resolution image synthesis for fashion
- train a virtual try-on model on the VITON-HD dataset
- compare virtual try-on baselines for a paper
- build a fashion e-commerce outfit preview prototype

## When to choose
- you need a proven, citable virtual try-on baseline at 1024x768 resolution
- you want the official implementation with the matching preprocessed dataset
- you are doing academic research on clothing transfer or image generation

## When to avoid
- you need a production-ready try-on service with licensing for commercial use (dataset and code are research-only)
- you want text-prompt or diffusion-based dressing (see StableVITON or PromptDresser instead)
- you need a maintained product with support and frequent updates

## Facets
- artifact type: library
- maturity: maintenance
- function: image-processing, machine-learning, deep-learning
- domain: computer-vision, image-processing, deep-learning, e-commerce
- platform: python
- tags: virtual-try-on, image-generation, pytorch, gan, computer-vision, research-code, cvpr-2021, linux, gpu

## Member repositories
- shadow2496/VITON-HD (main) score 40

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:49.394126+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 2026-08-30T06:31:44.076536+00:00, confidence not recorded.
  - readme: https://github.com/shadow2496/VITON-HD (fetched 2026-08-28T04:03:49.394126+00:00, sha ba69d64bdd4b)
  - homepage: https://psh01087.github.io/VITON-HD (fetched 2026-08-29T12:36:16.514611+00:00, sha f15f8f65c165)
- Data as of 2026-08-30T08:39:29.467469+00:00.