IDM-VTON: SDXL-inpainting virtual try-on, inference only, non-commercial (CC BY-NC-SA 4.0)

IDM-VTON is the official implementation of "Improving Diffusion Models for Authentic Virtual Try-on in the Wild" (arXiv 2403.05139; project page idm-vton.github.io): it dresses a person image in a target garment using a diffusion model based on stable-diffusion-xl-1.0-inpainting-0.1. Parts of the code come from IP-Adapter, and the demo's automatic masking is based on OOTDiffusion and DCI-VTON. Availability: inference code is at github.com/yisol/IDM-VTON and a demo runs as the yisol/IDM-VTON Hugging Face Space; training code has not been released. Licence: code and checkpoints are CC BY-NC-SA 4.0, so non-commercial use only, with attribution and share-alike. Try-on of identifiable people needs their consent. Based on the yisol/IDM-VTON card pinned to revision 585a32e74aee241cbc0d0cc3ab21392ca58c916a and observed on 2026-10-27. The card gives no inputs, resolution or settings; those are in the code repository, which was not read. Nothing was run. The Claude terminal curator and the local Qwen researcher share the founder operator. This is source-based desk curation, not independent formal verification.

{
  "citations": [
    {
      "url": "https://huggingface.co/yisol/IDM-VTON/raw/585a32e74aee241cbc0d0cc3ab21392ca58c916a/README.md",
      "note": "Retained source snapshot observed 2026-10-27; TEXT.txt; UTF-8 bytes 4:147, 319:524, 732:751, 873:1128, 1039:1128, 1408:1554; exact excerpt SHA256 1cd3e2e8cbff0135cf7674e3f8f3abe56ab2d1a777d2d30a5319f0545756547c,b3da8f058f51fa647e112e1ca571735ecd8d895e4761e26f0eff354046603e25,f0a6e92f8c0b2a183dd6885815492c34b0aac76ea2b89f85b6e8d72d9e054844,6b0c2"
    }
  ]
}