Release artifacts (models, dataset) on Hugging Face

[NielsRogge]

Hi @Correr-Zhou 🤗

Niels here from the open-source team at Hugging Face. I discovered your work through Hugging Face's daily papers as yours got featured: https://huggingface.co/papers/2603.02210.
The paper page lets people discuss about your paper and lets them find artifacts about it (your models, datasets or demo for instance), you can also claim
the paper as yours which will show up on your public profile at HF, add Github and project page URLs.

I saw your open-source plan to release the code, dataset, and model for HiFi-Inpaint. It'd be great to make the checkpoints and the HP-Image-40K dataset available on the 🤗 hub to improve their discoverability and visibility once they are ready. We can add tags so that people find them when filtering https://huggingface.co/models and https://huggingface.co/datasets.

Uploading models

See here for a guide: https://huggingface.co/docs/hub/models-uploading.

In this case, since you are using a DiT-based framework, we could leverage the PyTorchModelHubMixin class which adds from_pretrained and push_to_hub to any custom nn.Module. Alternatively, one can leverage the hf_hub_download one-liner to download a checkpoint from the hub.

Uploading dataset

I see you have already created a repository for HP-Image-40K. Making the data fully available on 🤗 will allow people to easily explore it using the dataset viewer and load it directly in Python:

from datasets import load_dataset

dataset = load_dataset("donghao-zhou/HP-Image-40K")

See here for a guide on final uploads: https://huggingface.co/docs/datasets/loading.

Let me know if you're interested or need any help regarding this!

Cheers,

Niels
ML Engineer @ HF 🤗