Release additional Lumina-Video checkpoints on Hugging Face

[NielsRogge]

Hello @ChrisLiu6 🤗

I'm Niels and work as part of 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/2502.06782.
The paper page lets people discuss about your paper and lets them find artifacts about it (your models for instance), you can also claim the paper as yours which will show up on your public profile at HF.

I noticed you've already released the Lumina-Video-f24R960 model on Hugging Face. That's fantastic! To maximize discoverability and usage, would you consider also uploading additional checkpoints mentioned in your README (different resolutions/frame rates) to the Hugging Face Hub?

Hosting on Hugging Face will give you more visibility/enable better discoverability. We can add tags in the model cards so that people find the models easier, link it to the paper page, etc. We can also help you create nice model cards.

If you're down, here's a guide on uploading models to Hugging Face: https://huggingface.co/docs/hub/models-uploading. If it's a custom PyTorch model, you can use the PyTorchModelHubMixin class which adds from_pretrained and push_to_hub to the model, allowing users to download and use your models directly. If you prefer another method, you can also upload via the UI or use hf_hub_download.

After uploading, we can link the models to your paper page (read here: https://huggingface.co/docs/hub/en/model-cards#linking-a-paper) for improved discoverability.

Let me know if you're interested or need any guidance.

Kind regards,

Niels
ML Engineer @ HF 🤗