---
license: other
license_name: server-side-public-license
license_link: https://www.mongodb.com/legal/licensing/server-side-public-license
tags:
- diffusion
- virtual try-on
- virtual try-off
- image generation
- fashion
- e-commerce
base_model:
- CompVis/stable-diffusion-v1-4
pipeline_tag: image-to-image
library_name: diffusers
---

## TryOffDiff

The models proposed in the paper _"TryOffDiff: Virtual-Try-Off via High-Fidelity Garment Reconstruction using Diffusion Models"_
[[paper]][paper_arxiv] [[project page]][project_page]:
- `tryoffdiff.pth`: The pre-trained StableDiffusion-v1.4 fine-tuned on `VITON-HD-train` dataset.
- `.pth`: A U-Net trained from scratch on `VITON-HD-train` dataset.
- `.pth`: 


## Usage

```python
from huggingface_hub import hf_hub_download

class TryOffDiff(nn.Module):
    def __init__(self):
        super().__init__()
        self.unet = UNet2DConditionModel.from_pretrained("CompVis/stable-diffusion-v1-4", subfolder="unet")
        self.transformer = torch.nn.TransformerEncoderLayer(d_model=768, nhead=8, batch_first=True)
        self.proj = nn.Linear(1024, 77)
        self.norm = nn.LayerNorm(768)

    def adapt_embeddings(self, x):
        x = self.transformer(x)
        x = self.proj(x.permute(0, 2, 1)).permute(0, 2, 1)
        return self.norm(x)

    def forward(self, noisy_latents, t, cond_emb):
        cond_emb = self.adapt_embeddings(cond_emb)
        return self.unet(noisy_latents, t, encoder_hidden_states=cond_emb).sample

path_model = hf_hub_download(
    repo_id="rizavelioglu/tryoffdiff",
    filename="tryoffdiff.pth",  # or one of ablations ["ldm-1", "ldm-2", "ldm-3", ...]
)
net = TryOffDiff()
net.load_state_dict(torch.load(path_model, weights_only=False))
net.eval().to(device)
```

> Check out the demo code on [HuggingFace Spaces][hf_spaces] for the full running example.

> Also, check out [GitHub repository][github] to get more information on
> training, inference, and evaluation.

### License
TL;DR: Not available for commercial use, unless the FULL source code is shared! \
This project is intended solely for academic research. No commercial benefits are derived from it.
Models are licensed under [Server Side Public License (SSPL)][license]

### Citation
If you find this repository useful in your research, please consider giving a star ⭐ and a citation:
```
@article{velioglu2024tryoffdiff,
  title     = {TryOffDiff: Virtual-Try-Off via High-Fidelity Garment Reconstruction using Diffusion Models},
  author    = {Velioglu, Riza and Bevandic, Petra and Chan, Robin and Hammer, Barbara},
  journal   = {arXiv},
  year      = {2024},
  note      = {\url{https://doi.org/nt3n}}
}
```

[hf_spaces]: https://huggingface.co/spaces/rizavelioglu/tryoffdiff/blob/main/app.py
[project_page]: https://rizavelioglu.github.io/tryoffdiff/
[paper_arxiv]: https://arxiv.org/abs/2411.18350
[github]: https://github.com/rizavelioglu/tryoffdiff
[license]: https://www.mongodb.com/legal/licensing/server-side-public-license