Awesome
🔥 Apple's official repo is open-sourced at ml-mgie
[ICLR'24] Guiding Instruction-based Image Editing via Multimodal Large Language Models
A Gradio demo of MGIE
<img src='./_imgs/gradio.gif' width='25%' />Gradio Demo
Follow Requirements to build env and put app.py in ml-mgie
Put official LLaVA-7B in _ckpt/LLaVA-7B-v1 and download pre-trained ckpt (on IPr2Pr + MagicBrush) in _ckpt/mgie_7b
gradio app.py
<img src='./_imgs/gradio.png' width='100%' />