hustvl

/

vgt_internvl3_1_6B_sft

like 0

Follow

HUST Vision Lab 97

This PR significantly enhances the model card for 'Visual Generation Tuning (VGT)' by:

• Adding the pipeline_tag: text-to-image to improve discoverability on the Hugging Face Hub.
• Including a detailed overview of the model and its key highlights.
• Providing a direct link to the official paper: Visual Generation Tuning.
• Linking to the GitHub repository: https://github.com/hustvl/VGT.
• Adding comprehensive installation instructions and a sample inference code snippet directly from the GitHub README to guide users on how to use the model.
• Ensuring the academic citation information is present.

This update aims to make the model card more informative, user-friendly, and discoverable.