diff --git a/INSTALL.md b/INSTALL.md
new file mode 100644
index 0000000..576b126
--- /dev/null
+++ b/INSTALL.md
@@ -0,0 +1,27 @@
+# Installation
+
+## 1. Create A Conda Environment
+```shell
+conda create -n catvton python==3.9.0
+conda activate catvton
+```
+
+## 2. Install Requirments
+```shell
+cd CatVTON-main  # or your path to CatVTON project dir
+pip install -r requirements.txt
+```
+**For inference only, the above packages are enough**. 
+
+## 3. Detectron2 & DensePose
+If you want to deploy the gradio app with automatic mask generation, you need to install **Detectron2 & DensePose** by following commands:
+```shell
+# Detectron2
+git clone https://github.com/facebookresearch/detectron2.git
+python -m pip install -e detectron2
+# DensePose
+pip install git+https://github.com/facebookresearch/detectron2@main#subdirectory=projects/DensePose
+```
+When installing, ensure that the runtime CUDA version for PyTorch aligns with the CUDA version of your system; otherwise, errors may occur.
+
+If there is a misalignment, the solution is to reinstall PyTorch with a CUDA version that matches your system's version. For more information on installing PyTorch with the correct CUDA version, you can visit the [PyTorch Get Started page for previous versions](https://pytorch.org/get-started/previous-versions/). 
\ No newline at end of file
diff --git a/README.md b/README.md
index e3a3b76..be00033 100644
--- a/README.md
+++ b/README.md
@@ -34,8 +34,11 @@
 - **`2024/7/21`**: Our [**Inference Code**](https://github.com/Zheng-Chong/CatVTON/blob/main/inference.py) and [**Weights** 🤗](https://huggingface.co/zhengchong/CatVTON) are released.
 - **`2024/7/11`**: Our [**Online Demo**](http://120.76.142.206:8888) is released 😁.
 
+## Installation
+An [Installation Guide](https://github.com/Zheng-Chong/CatVTON/INSTALL.md) is provided to help build the conda environment for CatVTON. When deploying the app, you will need Detectron2 & DensePose, but these are not required for inference on datasets. Install the packages according to your needs.
 
 ## Deployment (Gradio App)
+
 To deploy the Gradio App for CatVTON on your own mechine, just run the following command, and checkpoints will be automaticly download from HuggingFace.
 
 ```PowerShell
diff --git a/requirements.txt b/requirements.txt
index 62007c5..311d96a 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -1,38 +1,18 @@
 accelerate==0.31.0
-asposestorage==1.0.2
-caffe2==0.8.1
-cityscapesscripts==2.2.3
-cloudpickle==3.0.0
 diffusers==0.29.2
-docutils==0.21.2
-fvcore==0.1.5.post20221221
-gradio==4.38.1
+gradio==4.39.0
 huggingface_hub==0.23.4
-joblib==1.4.2
 matplotlib==3.9.1
-mock==5.1.0
-numexpr==2.10.1
-numpy==2.0.1
-onnx==1.16.1
-opencv_contrib_python==4.10.0.84
+numpy==1.26.4
 opencv_python==4.10.0.84
-opencv_python_headless==4.10.0.84
-Pillow==10.4.0
-psutil==6.0.0
-pycocotools==2.0.8
+pillow==10.3.0
 PyYAML==6.0.1
-PyYAML==6.0.1
-recommonmark==0.7.1
-scipy==1.14.0
+scipy==1.13.1
 setuptools==51.0.0
-Shapely==2.0.5
-skimage==0.0
-Sphinx==7.4.7
-sphinx_rtd_theme==2.0.0
-tabulate==0.9.0
-termcolor==2.4.0
+scikit-image==0.24.0
 torch==2.1.2
 torchvision==0.16.2
 tqdm==4.66.4
 transformers==4.27.3
 xformers==0.0.23.post1
+Ninja==1.11.1.1