---
license: openrail++
library_name: diffusers
pipeline_tag: image-to-image
tags:
  - virtual-try-off
  - garment-reconstruction
  - viton-hd
---

# DualVTOFF checkpoints

Official checkpoints for *What Matters in Virtual Try-Off? Dual-UNet Diffusion
Models for Garment Reconstruction*. DualVTOFF reconstructs a canonical garment
image from a person image and a binary garment-region mask.

| Checkpoint | Output height x width |
| --- | --- |
| [VITON-HD-512-res](VITON-HD-512-res/) | 512 x 384 |
| [VITON-HD-1024-res](VITON-HD-1024-res/) | 1024 x 768 |

See the [inference code and instructions](https://github.com/locphattruong/dual-vtoff).
Each checkpoint includes its inference components, manifest, checksums, license,
and attribution notices.

## Licenses

The checkpoint weights in this directory are released under **CreativeML Open
RAIL++-M**, including the use restrictions in Attachment A. The full license is
included in [LICENSE](LICENSE). Users and downstream distributors must comply
with its use, attribution, and redistribution conditions.

The inference source code is released separately under Apache-2.0. Component
copyright and license notices are preserved in [NOTICE.md](NOTICE.md) and
[licenses/](licenses/). The code license does not replace this model license.
VITON-HD data is not included and remains subject to its separate dataset terms.