Hugging Face's logo

dorni
/
UniVerse-1-Base

Any-to-Any
Diffusers
Safetensors
Model card Files
xet
Community
2

Update pipeline tag to `any-to-any` and add paper abstract

#1
by nielsr HF Staff - opened
base: refs/heads/main
←
from: refs/pr/1
Discussion Files changed
+6
-2
nielsr

This PR improves the model card for UniVerse-1 by:

  • Updating the pipeline_tag: The pipeline_tag in the metadata is changed from other to any-to-any. This more accurately reflects the model's capability to perform unified audio-video generation from text and reference images. This update will enhance the model's discoverability on the Hugging Face Hub, allowing users to find it under appropriate multimodal generation filters (e.g., https://huggingface.co/models?pipeline_tag=any-to-any).
  • Adding the paper abstract: The abstract of the paper, "UniVerse-1: Unified Audio-Video Generation via Stitching of Experts," is added to provide a quick and informative overview of the model directly within the model card.

No other changes were made to existing links or code snippets, adhering to the guidelines provided.

 Update pipeline tag to `any-to-any` and add paper abstractfaadd9f9
Cannot merge
This branch has merge conflicts in the following files:
  • README.md

Sign up or log in to comment