hustvl

/

DiffusionVL-Qwen2.5VL-7B

like 6

Follow

HUST Vision Lab 105

This PR enhances the model card by:

• Adding pipeline_tag: image-text-to-text to improve discoverability on the Hugging Face Hub, as the model takes images and text inputs to generate text.
• Adding library_name: transformers to enable the automated "how to use" widget, as evidenced by the provided sample usage code snippet leveraging the transformers library.
• Including a direct link to the Hugging Face paper page (https://huggingface.co/papers/2512.15713) for easy access to the associated research on the Hub.

The existing license and tags remain unchanged. The sample usage section is already present and correctly formatted.