Adjust video layout

README.md

@@ -19,7 +19,20 @@ Currently, only the test code is available, and training scripts are coming soon
 
 **`2021-06-20`**: We release the scripts for arbitrary video and image processing.
 
+## Dependencies
+- python3.6+
+- pytorch1.5+
+- torchvision
+- opencv
+- pillow
+- numpy
+- moviepy
+- insightface
 
+## Usage
+[Preparation](./doc/guidance/preparation.md)
+
+[Simple Usage](./doc/guidance/usage.md)
 
 ## Results
 ![Results1](/doc/img/results1.PNG)
@@ -29,10 +42,16 @@ Currently, only the test code is available, and training scripts are coming soon
 ## Video
 <img src="./doc/img/video.webp"/>
 
-![video2](/doc/img/anni.webp)
+<div>
+<img width=24% src="./doc/img/anni.webp"/>
+<img width=24% src="./doc/img/chenglong.webp"/>
+<img width=24% src="./doc/img/zhoujielun.webp"/>
+<img width=24% src="./doc/img/zhuyin.webp"/>
+</div>
+<!-- ![video2](/doc/img/anni.webp)
 ![video3](/doc/img/chenglong.webp)
 ![video4](/doc/img/zhoujielun.webp)
-![video5](/doc/img/zhuyin.webp)
+![video5](/doc/img/zhuyin.webp) -->
 
 
 **High-quality videos can be found in the link below:**
@@ -52,21 +71,6 @@ Currently, only the test code is available, and training scripts are coming soon
 
 
 
-## Dependencies
-- python3.6+
-- pytorch1.5+
-- torchvision
-- opencv
-- pillow
-- numpy
-- moviepy
-- insightface
-
-## Usage
-[Preparation](./doc/guidance/preparation.md)
-
-[Simple Usage](./doc/guidance/usage.md)
-
 ## To cite our paper
 ```
 @inproceedings{DBLP:conf/mm/ChenCNG20,

doc/guidance/preparation.md

@@ -1,7 +1,8 @@
 
 # Preparation
 
-### Environment and Dependencies
+### Installation
+**We highly recommand that you use Anaconda for Installation**
 ```
 conda create -n simswap python=3.6
 conda activate simswap
@@ -9,7 +10,7 @@ conda install pytorch==1.8.0 torchvision==0.9.0 torchaudio==0.8.0 cudatoolkit=10
 (option): pip install --ignore-installed imageio
 pip install insightface==0.2.1 onnxruntime moviepy
 ```
-- We use the face detection and alignment methods from **[insightface](https://github.com/deepinsight/insightface)** for image preprocessing. Please download the relative files and save them to ./insightface_func/models from [this link](https://onedrive.live.com/?authkey=%21ADJ0aAOSsc90neY&cid=4A83B6B633B029CC&id=4A83B6B633B029CC%215837&parId=4A83B6B633B029CC%215834&action=locate).
+- We use the face detection and alignment methods from **[insightface](https://github.com/deepinsight/insightface)** for image preprocessing. Please download the relative files and unzip them to ./insightface_func/models from [this link](https://onedrive.live.com/?authkey=%21ADJ0aAOSsc90neY&cid=4A83B6B633B029CC&id=4A83B6B633B029CC%215837&parId=4A83B6B633B029CC%215834&action=locate).
 - The pytorch and cuda versions above are most recommanded. They may vary.
 - Using insightface with different versions is not recommanded. Please use this specific version.
 - These settings are tested valid on both Windows and Ununtu.