Hi @wangzx1994 🤗
I'm Niels and work as part of the open-source team at Hugging Face. I discovered your work through Hugging Face Daily Papers: https://huggingface.co/papers/2607.18703
The paper page lets people discuss your paper and find related artifacts, and you can also claim the paper to show it on your public profile, as well as link your GitHub repository.
I saw you have set up a repository for AlayaRenderer-Flash (https://github.com/AlayaLab/AlayaRenderer-Flash). When you are ready to publish the code, would you also like to host the pre-trained model weights (such as the distilled codecs and the autoregressive renderer checkpoints) on https://huggingface.co/models?
Hosting on Hugging Face will give your project more visibility and enable better discoverability within the ML community. We can add metadata tags to your model cards so that people can easily find them, and link the models directly to your paper page.
If you're interested, you can find a guide on uploading models here. For custom PyTorch architectures, you can use the PyTorchModelHubMixin class to easily add from_pretrained and push_to_hub functionality. Alternatively, people can download files directly using hf_hub_download.
Let me know if you're interested or if you need any guidance!
Kind regards,
Niels
Hi @wangzx1994 🤗
I'm Niels and work as part of the open-source team at Hugging Face. I discovered your work through Hugging Face Daily Papers: https://huggingface.co/papers/2607.18703
The paper page lets people discuss your paper and find related artifacts, and you can also claim the paper to show it on your public profile, as well as link your GitHub repository.
I saw you have set up a repository for AlayaRenderer-Flash (https://github.com/AlayaLab/AlayaRenderer-Flash). When you are ready to publish the code, would you also like to host the pre-trained model weights (such as the distilled codecs and the autoregressive renderer checkpoints) on https://huggingface.co/models?
Hosting on Hugging Face will give your project more visibility and enable better discoverability within the ML community. We can add metadata tags to your model cards so that people can easily find them, and link the models directly to your paper page.
If you're interested, you can find a guide on uploading models here. For custom PyTorch architectures, you can use the PyTorchModelHubMixin class to easily add
from_pretrainedandpush_to_hubfunctionality. Alternatively, people can download files directly using hf_hub_download.Let me know if you're interested or if you need any guidance!
Kind regards,
Niels