# Zheng-Chong/CatVTON

[ICLR 2025] CatVTON is a simple and efficient virtual try-on diffusion model with 1) Lightweight Network (899.06M parameters totally), 2) Parameter-Efficient Training (49.57M parameters trainable) and 3) Simplified Inference (< 8G VRAM for 1024X768 resolution).

Repository: https://github.com/Zheng-Chong/CatVTON
Canonical: https://ross.abutalabs.com/products/catvton
Language: Python
License: NOASSERTION
License Family: other
Topics: diffusion-models, fashion, try-on
Last push: 2025-12-16T00:59:26+00:00

## Health v2 (maintenance only)
Score: 40/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 57, release rhythm 8, longevity 56
- inputs: {"age_days": 792, "days_push": 261, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1824, forks 237 (observed 2026-08-28T04:05:41.196934+00:00)

## What it is
CatVTON is a lightweight diffusion model for virtual try-on that swaps clothing onto a person image using a concatenation-based architecture. It trains only ~49.57M parameters and runs inference under 8GB VRAM at 1024x768 resolution.

## Use cases
- try clothes on a photo virtually
- generate images of a person wearing different outfits
- build a virtual fitting room for an e-commerce store
- swap garments between person images
- run lightweight image-based clothing try-on on a single GPU
- research diffusion-based image editing for fashion

## When to choose
- you need efficient image-based virtual try-on with limited GPU memory
- you want a published, peer-reviewed try-on model (ICLR 2025)
- you need parameter-efficient fine-tuning of a try-on diffusion model
- you want a Gradio demo or Hugging Face integration for try-on

## When to avoid
- you need video try-on - use the successor CatV2TON instead
- you need a commercially licensed model - it is CC BY-NC-SA 4.0 (non-commercial)
- you need full-body or high-resolution generation beyond 1024x768
- you have no GPU available

## Facets
- artifact type: library
- maturity: active
- function: image-processing, machine-learning, deep-learning, llm-inference
- domain: computer-vision, image-processing, e-commerce, artificial-intelligence, deep-learning
- platform: python
- tags: virtual-try-on, diffusion-models, fashion, stable-diffusion, image-generation, gradio, iclr-2025, gpu, linux, docker

## Member repositories
- Zheng-Chong/CatVTON (main) score 40

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:41.196934+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 2026-08-30T03:19:42.785368+00:00, confidence not recorded.
  - readme: https://github.com/Zheng-Chong/CatVTON (fetched 2026-08-28T04:05:41.196934+00:00, sha a9be57f91d08)
- Data as of 2026-08-30T08:39:29.467469+00:00.