# yisol/IDM-VTON

[ECCV2024] IDM-VTON : Improving Diffusion Models for Authentic Virtual Try-on in the Wild

Repository: https://github.com/yisol/IDM-VTON
Canonical: https://ross.abutalabs.com/products/idm-vton
Homepage: https://idm-vton.github.io/
Language: Python
License: NOASSERTION
License Family: other
Last push: 2025-03-07T09:42:54+00:00

## Health v2 (maintenance only)
Score: 30/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 10, release rhythm 35, longevity 64
- inputs: {"age_days": 897, "days_push": 544, "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 5156, forks 828 (observed 2026-08-28T04:09:11.444953+00:00)

## What it is
Official implementation of IDM-VTON, an ECCV 2024 paper that improves diffusion models for high-fidelity virtual try-on, swapping garments onto person images in the wild. It provides training and inference code built on SDXL with IP-Adapter, plus dataset preparation for VITON-HD and DressCode.

## Use cases
- swap clothing between photos of people
- generate virtual try-on images of garments on a person
- train a diffusion model for image-based clothes try-on
- run virtual try-on on the VITON-HD dataset
- try on dresses or shirts from a product photo onto a model image
- reproduce ECCV 2024 virtual try-on research results

## When to choose
- you need state-of-the-art research-grade virtual try-on with fine garment detail preservation
- you want to train or fine-tune a try-on model on VITON-HD or DressCode
- you have GPU resources and are comfortable with research code

## When to avoid
- you need a production-ready hosted API or polished end-user app
- you lack a GPU or cannot set up conda environments and large datasets
- you need a permissive license - the license is non-standard

## Facets
- artifact type: library
- maturity: active
- 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-models, eccv2024, garment-transfer, sdxl, ip-adapter, research-code, gpu, linux

## Member repositories
- yisol/IDM-VTON (main) score 30

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:11.444953+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 2026-08-29T18:01:54.848134+00:00, confidence not recorded.
  - readme: https://github.com/yisol/IDM-VTON (fetched 2026-08-28T04:09:11.444953+00:00, sha 2a90e9824331)
  - homepage: https://idm-vton.github.io/ (fetched 2026-08-29T08:56:00.672751+00:00, sha 6af8fc09d3d9)
- Data as of 2026-08-30T08:39:29.467469+00:00.