---
pipeline_tag: image-text-to-text
---

This repository contains the checkpoints for the model presented in the paper [Unified Multimodal Discrete Diffusion](https://huggingface.co/papers/2503.20853).

The code is available at [https://github.com/alexanderswerdlow/unidisc](https://github.com/alexanderswerdlow/unidisc).
The project page is available at [https://unidisc.github.io/](https://unidisc.github.io/).

The UniDisc checkpoints are available on Hugging Face:
* [Interleaved Image-Text](https://huggingface.co/aswerdlow/unidisc_interleaved)
* [Non-Interleaved (Static)](https://huggingface.co/aswerdlow/unidisc_non_interleaved)