nyu-visionx

/

siglip2_decoder

like 0

Follow

VISIONx @ NYU 149

Hi! I'm Niels from the Hugging Face community science team.

This PR adds a comprehensive model card to the repository. It includes:

• Metadata for license, library_name, and pipeline_tag.
• Links to the paper (Scaling Text-to-Image Diffusion Transformers with Representation Autoencoders), project page, and official GitHub repository.
• A brief description of the model and its findings.
• Sample CLI usage for inference as found in the official documentation.
• Citation information.

This update will make the model more discoverable and provide users with the necessary context and links to the official implementation.