# levihsu/OOTDiffusion

[AAAI 2025] Official implementation of "OOTDiffusion: Outfitting Fusion based Latent Diffusion for Controllable Virtual Try-on"

Repository: https://github.com/levihsu/OOTDiffusion
Canonical: https://ross.abutalabs.com/products/ootdiffusion
Language: Python
License: NOASSERTION
License Family: other
Last push: 2024-05-13T08:50:07+00:00

## Health v2 (maintenance only)
Score: 26/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 68
- inputs: {"age_days": 952, "days_push": 842, "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 6586, forks 959 (observed 2026-08-28T04:09:45.474259+00:00)

## What it is
Official implementation of OOTDiffusion, a latent diffusion model for controllable virtual try-on that generates images of a person wearing a specified garment. It provides inference code and pretrained checkpoints for half-body and full-body try-on, with a Hugging Face demo.

## Use cases
- generate images of a person wearing a specific outfit
- virtual try-on for e-commerce product photos
- try clothes on a model photo using AI
- swap garment onto a person image with diffusion models
- half-body and full-body outfit try-on generation

## When to choose
- you need research-grade virtual try-on with published checkpoints
- you want a runnable reference implementation of the AAAI 2025 paper
- you work with VITON-HD or Dress Code style datasets

## When to avoid
- you need training code (not yet released)
- you require a production API or commercial license (license is non-standard)
- you need Windows or macOS support (only tested on Ubuntu Linux)

## Facets
- artifact type: application
- maturity: maintenance
- function: image-processing, machine-learning, deep-learning
- domain: image-processing, artificial-intelligence, e-commerce
- platform: python
- tags: virtual-try-on, diffusion-models, latent-diffusion, fashion, image-generation, research-code, linux, gpu

## Member repositories
- levihsu/OOTDiffusion (main) score 26

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:45.474259+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 2026-08-29T17:43:35.090750+00:00, confidence not recorded.
  - readme: https://github.com/levihsu/OOTDiffusion (fetched 2026-08-28T04:09:45.474259+00:00, sha 02b4b0d0a907)
- Data as of 2026-08-30T08:39:29.467469+00:00.