---
base_model:
- Efficient-Large-Model/Sana_1600M_1024px_BF16
- VIPL-GENUN/Jodi
tags:
- Diffusion
- Text-to-Image
- Controllable-Generation
- Image-Perception
pipeline_tag: image-to-image
library_name: diffusers
license: apache-2.0
---

# Jodi

We introduce Jodi, a diffusion framework that unifies visual generation and understanding by jointly modeling the image domain and multiple label domains.

- **arXiv**: <https://arxiv.org/abs/2505.19084>
- **Project page**: <https://VIPL-GENUN.github.io/Project-Jodi>
- **GitHub**: <https://github.com/VIPL-GENUN/Jodi>

![](./assets/banner.jpg)