PhilipC

/

HumanOmniV2

like 19

This PR enhances the model card for HumanOmniV2 by:

• Adding the pipeline_tag: video-text-to-text to improve model discoverability on the Hugging Face Hub.
• Specifying library_name: transformers, which enables the "how to use" widget and indicates compatibility.
• Setting license: apache-2.0 to clearly state the model's license.
• Updating the paper link to include the Hugging Face Papers page.
• Adding a direct link to the GitHub repository for easy access to the code.
• Integrating comprehensive details from the GitHub README, including a full overview, news, experimental results, training and evaluation instructions, and usage examples.
• Correcting image paths to ensure proper rendering on the Hub.