README.md

metadata

pipeline_tag: image-text-to-text

This repository contains the checkpoints for the model presented in the paper Unified Multimodal Discrete Diffusion.

The code is available at https://github.com/aswerdlow/unidisc. The project page is available at https://unidisc.github.io/.

The UniDisc checkpoints are available on Hugging Face:

• Interleaved Image-Text
• Non-Interleaved (Static)