Hugging Face's logo

tedlasai
/
learn2refocus

Image-to-Video
Diffusers
Safetensors
Model card Files
xet
 Community
2

Add model card and metadata

#1
by nielsr HF Staff - opened
base: refs/heads/main
←
from: refs/pr/1
Discussion Files changed
+36
-0
nielsr

Hi! I'm Niels from the community science team at Hugging Face. I noticed this model repository was missing a model card and relevant metadata.

This PR adds:

  • Metadata: Including the image-to-video pipeline tag and the diffusers library name to improve discoverability and enable automated code snippets.
  • Model Description: A brief summary of the research and links to the paper, project page, and official GitHub repository.
  • Sample Usage: A code snippet based on the official GitHub README for running inference.
  • Citation: The official BibTeX citation for this work.

Please let me know if you'd like any adjustments!
Add model card and metadata734b9ce2
tedlasai
 Owner

The info you used was for another repo. I have just put in my own simple readme that links to the project page.

tedlasai changed pull request status to closed
nielsr

Hi, thanks. Any reason why it was wrong? I found it based on the README here: https://github.com/tedlasai/blur2vid
tedlasai
 Owner

this paper is actually https://github.com/tedlasai/learn2refocus -> not blur2vid :)

tedlasai
 Owner

Both SIGGRAPH papers by the same author (me). So I understand they are easy to confuse. Even I confuse them myself haha
nielsr

Oh ok. I saw the "checkpoints" section here: https://raw.githubusercontent.com/tedlasai/blur2vid/refs/heads/main/README.md links to the learn2refocus model, I guess that paper will have different checkpoints
tedlasai
 Owner

Oops, thats me confusing them ... Sorry, I'll fix that.
tedlasai
 Owner

@nielsr For this paper, the dataset is around 1.6TB. Any chance this could be allocated?
nielsr

For that you can email us as explained here: https://huggingface.co/docs/hub/en/storage-limits#sharing-large-datasets-on-the-hub

Sign up or log in to comment