Hi @ryan-seungyong-lee 馃
Niels here from the open-source team at Hugging Face. I discovered your work through Hugging Face Daily Papers: https://huggingface.co/papers/2607.09362
The paper page lets people discuss about your paper and lets them find artifacts about it, and it's awesome that you've already hosted the VITON-HD-edit dataset on the Hub under the NXN-Labs organization!
Would you also like to host the pre-trained model checkpoints for CtrlVTON and VIP-SAM on https://huggingface.co/models?
Hosting them on Hugging Face will give your work more visibility and enable better discoverability. We can add metadata tags (such as image-to-image and image-segmentation) to the model cards so that people can easily find them, and link them directly to your paper page on Hugging Face.
If you're down, I'm leaving a guide here. If it's a custom PyTorch model, you can use the PyTorchModelHubMixin class which adds from_pretrained and push_to_hub to your model, allowing people to download and use them right away. Alternatively, you can directly upload the files through the Hugging Face web UI, and users can load them using hf_hub_download.
After they are uploaded, we can also link the models to the paper page (read how here) so people can discover them easily.
Let me know if you're interested or if you need any guidance!
Kind regards,
Niels
ML Engineer @ HF 馃
Hi @ryan-seungyong-lee 馃
Niels here from the open-source team at Hugging Face. I discovered your work through Hugging Face Daily Papers: https://huggingface.co/papers/2607.09362
The paper page lets people discuss about your paper and lets them find artifacts about it, and it's awesome that you've already hosted the VITON-HD-edit dataset on the Hub under the
NXN-Labsorganization!Would you also like to host the pre-trained model checkpoints for CtrlVTON and VIP-SAM on https://huggingface.co/models?
Hosting them on Hugging Face will give your work more visibility and enable better discoverability. We can add metadata tags (such as
image-to-imageandimage-segmentation) to the model cards so that people can easily find them, and link them directly to your paper page on Hugging Face.If you're down, I'm leaving a guide here. If it's a custom PyTorch model, you can use the PyTorchModelHubMixin class which adds
from_pretrainedandpush_to_hubto your model, allowing people to download and use them right away. Alternatively, you can directly upload the files through the Hugging Face web UI, and users can load them using hf_hub_download.After they are uploaded, we can also link the models to the paper page (read how here) so people can discover them easily.
Let me know if you're interested or if you need any guidance!
Kind regards,
Niels
ML Engineer @ HF 馃