Hi @yl-1993 🤗
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/2510.27684.
The paper page lets people discuss about your paper and lets them find artifacts about it.
It's fantastic to see the Wan2.2-Lightning models already available on the hub under the lightx2v organization! You can claim the paper as yours on HF to add the GitHub link and link these models to the paper page (read here) so they appear directly in the artifacts section.
I noticed in the paper and project page that you've also successfully distilled other models using Phased DMD, such as Qwen-Image (20B) and Wan2.1 (14B). Would you like to host these distilled checkpoints on Hugging Face as well?
Hosting them on the Hub will give your work significantly more visibility and enable better discoverability within the community. We can add metadata tags so that people find the models easier when filtering.
If you're down, 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 the model.
Let me know if you're interested or need any guidance!
Kind regards,
Niels
ML Engineer @ HF 🤗
Hi @yl-1993 🤗
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/2510.27684.
The paper page lets people discuss about your paper and lets them find artifacts about it.
It's fantastic to see the Wan2.2-Lightning models already available on the hub under the
lightx2vorganization! You can claim the paper as yours on HF to add the GitHub link and link these models to the paper page (read here) so they appear directly in the artifacts section.I noticed in the paper and project page that you've also successfully distilled other models using Phased DMD, such as Qwen-Image (20B) and Wan2.1 (14B). Would you like to host these distilled checkpoints on Hugging Face as well?
Hosting them on the Hub will give your work significantly more visibility and enable better discoverability within the community. We can add metadata tags so that people find the models easier when filtering.
If you're down, leaving a guide here. If it's a custom PyTorch model, you can use the PyTorchModelHubMixin class which adds
from_pretrainedandpush_to_hubto the model.Let me know if you're interested or need any guidance!
Kind regards,
Niels
ML Engineer @ HF 🤗