Hugging Face's logo

stdstu123
/
Yume-5B-720P

Image-to-Video
Diffusers
Safetensors
ti2v
Text-to-Video
Image-to-Video
Diffusion Video Model
World Model
Model card Files
xet
Community
3

Improve model card metadata and add paper links

#1
by nielsr HF Staff - opened
base: refs/heads/main
←
from: refs/pr/1
Discussion Files changed
+38
-14
nielsr

This PR improves the model card for Yume-1.5 by:

  • Adding the image-to-video pipeline tag.
  • Removing the invalid <World Model> library name.
  • Linking the research papers (Yume and Yume-1.5) to their Hugging Face paper pages or Arxiv links.
  • Adding a sample usage section based on the GitHub repository's inference scripts.
 Improve model card metadata and add paper links9f99132a
stdstu123
 Owner

Thanks for improving the model card !
nielsr

Thanks, feel free to merge/

nielsr changed pull request status to closed

Sign up or log in to comment