Hi @Crayon-Shinchan 🤗
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/2509.17627.
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 in your GitHub repository's "Todo List" that you are planning to release both the "OmniInsert" inference codes and the "InsertBench" dataset. It'd be great to make these checkpoints and the dataset available on the 🤗 hub once they are ready, to improve their discoverability/visibility.
We can add tags so that people find them when filtering https://huggingface.co/models and https://huggingface.co/datasets.
Uploading models (OmniInsert)
See here for a guide: https://huggingface.co/docs/hub/models-uploading.
In this case, we could leverage the PyTorchModelHubMixin class which adds from_pretrained and push_to_hub to any custom nn.Module. Alternatively, one can leverages the hf_hub_download one-liner to download a checkpoint from the hub.
The relevant pipeline tag for OmniInsert would be image-to-video, as it inserts subjects (typically from images) into videos.
We encourage researchers to push each model checkpoint to a separate model repository, so that things like download stats also work. We can then also link the checkpoints to the paper page.
Uploading dataset (InsertBench)
Would be awesome to make the InsertBench dataset available on 🤗 , so that people can do:
from datasets import load_dataset
dataset = load_dataset("your-hf-org-or-username/InsertBench")See here for a guide: https://huggingface.co/docs/datasets/loading.
The relevant task category for InsertBench would be image-to-video, as it's a benchmark for video insertion from references.
Besides that, there's the dataset viewer which allows people to quickly explore the first few rows of the data in the browser.
Let me know if you're interested/need any help regarding this once the code and dataset are released!
Cheers,
Niels
ML Engineer @ HF 🤗
Hi @Crayon-Shinchan 🤗
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/2509.17627.
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 in your GitHub repository's "Todo List" that you are planning to release both the "OmniInsert" inference codes and the "InsertBench" dataset. It'd be great to make these checkpoints and the dataset available on the 🤗 hub once they are ready, to improve their discoverability/visibility.
We can add tags so that people find them when filtering https://huggingface.co/models and https://huggingface.co/datasets.
Uploading models (OmniInsert)
See here for a guide: https://huggingface.co/docs/hub/models-uploading.
In this case, we could leverage the PyTorchModelHubMixin class which adds
from_pretrainedandpush_to_hubto any customnn.Module. Alternatively, one can leverages the hf_hub_download one-liner to download a checkpoint from the hub.The relevant pipeline tag for OmniInsert would be
image-to-video, as it inserts subjects (typically from images) into videos.We encourage researchers to push each model checkpoint to a separate model repository, so that things like download stats also work. We can then also link the checkpoints to the paper page.
Uploading dataset (InsertBench)
Would be awesome to make the InsertBench dataset available on 🤗 , so that people can do:
See here for a guide: https://huggingface.co/docs/datasets/loading.
The relevant task category for InsertBench would be
image-to-video, as it's a benchmark for video insertion from references.Besides that, there's the dataset viewer which allows people to quickly explore the first few rows of the data in the browser.
Let me know if you're interested/need any help regarding this once the code and dataset are released!
Cheers,
Niels
ML Engineer @ HF 🤗