Update README

README.md

@@ -6,18 +6,28 @@ license: apache-2.0
 
 # Model info
 
-`fbanime.pkl`: StyleGan2 model trained with official [StyleGan3](https://github.com/NVlabs/stylegan3).
+### fbanime.pkl
+
+StyleGan2 model trained with official [StyleGan3](https://github.com/NVlabs/stylegan3).
 But I modified the code (networks_stylegan2.py and dataset.py) to support non-square resolutions.
 
-`g_mapping.onnx`: onnx format mapping network of fbanime.pkl
+### g_mapping.onnx
+
+onnx format mapping network of fbanime.pkl
+
+### g_synthesis.onnx
 
-`g_synthesis.onnx`: onnx format synthesis network of fbanime.pkl
+onnx format synthesis network of fbanime.pkl
 
-`encoder.onnx`:  4e model trained with [encoder4editing-stylegan3](https://github.com/yj7082126/encoder4editing-stylegan3).
+### encoder.onnx
+
+e4e model trained with [encoder4editing-stylegan3](https://github.com/yj7082126/encoder4editing-stylegan3).
 I add support for official StyleGan2 model and change backbone to ResNet-34 in [restyle-encoder](https://github.com/yuval-alaluf/restyle-encoder).
 
-`waifu_dect.onnx` YOLOv5 model trained with official [YOLOv5](https://github.com/ultralytics/yolov5)
+### waifu_dect.onnx
+
+YOLOv5 model trained with official [YOLOv5](https://github.com/ultralytics/yolov5)
 
 # Usage
 
-see [demo](https://huggingface.co/spaces/skytnt/full-body-anime-gan/blob/main/app.py)
+see [demo](https://huggingface.co/spaces/skytnt/full-body-anime-gan/blob/main/app.py)