worstcoder

/

SD3.5M-DiffusionNFT-MultiReward

like 5

This PR enhances the model card by:

• Adding pipeline_tag: text-to-image, making the model discoverable on the Hub for text-to-image tasks.
• Updating library_name to diffusers, which correctly reflects the primary library used to interact with this model (as indicated by adapter_config.json) and enables the automated "how to use" widget.
• Including a link to the official project page: https://research.nvidia.com/labs/dir/DiffusionNFT.
• Updating the paper link to the Hugging Face Papers page: https://huggingface.co/papers/2509.16117.
• Incorporating the paper's abstract for a more comprehensive description of the model.
• Updating the model description to correctly refer to "Diffusion Negative-aware FineTuning (DiffusionNFT)".