Our project supports virtual try-on, virtual try-off, and arbitrary-pose try-on in a unified framework, enabling flexible outfit transfer from only a single portrait and a target garment.
We release two sets of weights for inference on the VITON-HD and DeepFashion-MultiModal datasets, respectively.
Both support high-resolution image generation at [768, 1024].
The codes and checkpoints in this repository are under the
CC BY-NC-SA 4.0 license.