MIEScore: A Human-Aligned Benchmark for Multi-Source Image Editing

Dataset

You can download the MIEBench from the following link: MIEBench

Model Weights

You can download the model weights from the following link: MIEScore

Install

pip install -r requirements.txt

Inference

python inference.py \
--mode single \
--model_dir ./checkpoint \
--base_model_dir Qwen/Qwen3-VL-8B-Instruct \
--edited_image ./edited.png \
--source_images ./source1.png ./source2.png \
--instruction "Transfer the style of source image to the edited object"