Hi @Taited 🤗
Niels here from the open-source team at Hugging Face. I discovered your work on Arxiv and was wondering whether you would like to submit it to hf.co/papers to improve its discoverability. If you are one of the authors, you can submit it at https://huggingface.co/papers/submit.
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, and add Github and project page URLs.
I saw in your GitHub repository that you plan to release the code, pretrained weights (the main model and the auxiliary compositional model), and the canonical human dataset by May 2026. It's awesome to see that you already have a demo running on Hugging Face Spaces!
It'd be great to make these checkpoints and the dataset available on the 🤗 Hub as well, to improve their discoverability and visibility.
Uploading models
You can host your model checkpoints at https://huggingface.co/models. Hosting on the Hub allows people to find them when filtering by tasks (like image-to-video or image-to-image). 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.
Uploading dataset
It would also be awesome to make the canonical human dataset available on 🤗 so that people can easily explore it using the dataset viewer and load it with a single line of code:
from datasets import load_dataset
dataset = load_dataset("Taited/your-dataset-name")See here for a guide: https://huggingface.co/docs/datasets/loading.
If you need more resources for your demo, we can also provide you a ZeroGPU grant, which gives you A100 GPUs for free.
Let me know if you're interested or need any help regarding this!
Cheers,
Niels
ML Engineer @ HF 🤗
Hi @Taited 🤗
Niels here from the open-source team at Hugging Face. I discovered your work on Arxiv and was wondering whether you would like to submit it to hf.co/papers to improve its discoverability. If you are one of the authors, you can submit it at https://huggingface.co/papers/submit.
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, and add Github and project page URLs.
I saw in your GitHub repository that you plan to release the code, pretrained weights (the main model and the auxiliary compositional model), and the canonical human dataset by May 2026. It's awesome to see that you already have a demo running on Hugging Face Spaces!
It'd be great to make these checkpoints and the dataset available on the 🤗 Hub as well, to improve their discoverability and visibility.
Uploading models
You can host your model checkpoints at https://huggingface.co/models. Hosting on the Hub allows people to find them when filtering by tasks (like
image-to-videoorimage-to-image). 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.Uploading dataset
It would also be awesome to make the canonical human dataset available on 🤗 so that people can easily explore it using the dataset viewer and load it with a single line of code:
See here for a guide: https://huggingface.co/docs/datasets/loading.
If you need more resources for your demo, we can also provide you a ZeroGPU grant, which gives you A100 GPUs for free.
Let me know if you're interested or need any help regarding this!
Cheers,
Niels
ML Engineer @ HF 🤗