---
license: other
license_name: ml-mgie
license_link: https://github.com/apple/ml-mgie/blob/main/LICENSE.txt
---

# [ICLR'24] Guiding Instruction-based Image Editing via Multimodal Large Language Models
This repo contains [LLaVA-7B](https://huggingface.co/liuhaotian/LLaVA-Lightning-7B-delta-v1-1) and [pre-trained MGIE ckpt](https://docs-assets.developer.apple.com/ml-research/models/mgie/mgie_7b.tar.gz) (on IPr2Pr + MagicBrush) for [MGIE](https://huggingface.co/spaces/tsujuifu/ml-mgie)
<img src="https://raw.githubusercontent.com/apple/ml-mgie/main/mgie.png" width="60%" />

Please follow the [offical repo](https://github.com/apple/ml-mgie) and [ipynb](https://github.com/apple/ml-mgie/blob/main/demo.ipynb) to use it
<img src="https://raw.githubusercontent.com/apple/ml-mgie/main/demo.png" width="60%" />

```
@inproceedings{fu2024mgie,
  author = {Tsu-Jui Fu and Wenze Hu and Xianzhi Du and William Yang Wang and Yinfei Yang, and Zhe Gan}, 
  title = {{Guiding Instruction-based Image Editing via Multimodal Large Language Models}}, 
  booktitle = {International Conference on Learning Representations (ICLR)}, 
  year = {2024} 
}
```