https://github.com/smthemex/ComfyUI_CSD_MT
CSD_MT is a method about Content-Style Decoupling for Unsupervised Makeup Transfer without Generating Pseudo Ground Truth, this node can use it in comfyUI
https://github.com/smthemex/ComfyUI_CSD_MT
Last synced: 2 months ago
JSON representation
CSD_MT is a method about Content-Style Decoupling for Unsupervised Makeup Transfer without Generating Pseudo Ground Truth, this node can use it in comfyUI
- Host: GitHub
- URL: https://github.com/smthemex/ComfyUI_CSD_MT
- Owner: smthemex
- License: mit
- Created: 2025-02-05T09:13:44.000Z (2 months ago)
- Default Branch: main
- Last Pushed: 2025-02-05T09:22:13.000Z (2 months ago)
- Last Synced: 2025-02-05T10:24:44.230Z (2 months ago)
- Size: 304 KB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- awesome-comfyui - **ComfyUI_CSD_MT** - MT) is a method about 'Content-Style Decoupling for Unsupervised Makeup Transfer without Generating Pseudo Ground Truth', you can use it in comfyUI. (All Workflows Sorted by GitHub Stars)
README
# ComfyUI_CSD_MT
[CSD_MT](https://github.com/Snowfallingplum/CSD-MT) is a method about 'Content-Style Decoupling for Unsupervised Makeup Transfer without Generating Pseudo Ground Truth', you can use it in comfyUI.
# Tips
* This method need little space and VRAM(or CPU),all the models is about 200M(4 weights),and best quality size is 256*256
* 这个方法所用4个模型加起来不到200M,所需显存或CPU可以忽略不记,当然,图片输出最佳质量是256*256.
# 1. Installation
In the ./ComfyUI/custom_node directory, run the following:
```
git clone https://github.com/smthemex/ComfyUI_CSD_MT.git
```
---
# 2. Requirements
```
pip install -r requirements.txt
```
* When install dlib get error,use wheel to install it,download wheel from this [address](https://github.com/z-mahmud22/Dlib_Windows_Python3.x)
* 如果按照dlib库失败，从此链接下载对应你python版本的轮子，用以下命令安装：
```
pip install dlib-19.24.1-cp311-cp311-win_amd64.whl
```
# 3.Model
* 3.1 download 3 checkpoints (79999_iter.pth,CSD_MT.pth,lms.dat) from [google](https://drive.google.com/drive/folders/1pvSgkpsb7k6Ph1_oCmFkMQZPgL7PaTO0) or [baidu](https://pan.baidu.com/share/init?surl=C7K4xk5W0X65yUQh41AmfQ) password:1d3e.从百度云或者Google下载三个模型
* 3.2 download 'resnet18-5c106cde.pth' from [here](https://download.pytorch.org/models/resnet18-5c106cde.pth) 从链接下载resnet18-5c106cde.pth模型，不要改名字.
```
-- ComfyUI/models/CSDMT
|-- 79999_iter.pth
|-- CSD_MT.pth
|--resnet18-5c106cde.pth #没有也会自动下载
-- ComfyUI/custom_node/ComfyUI_CSD_MT/quick_start/faceutils/dlibutils
|--lms.dat
```
# 4.Example
# 5.Citation
```
@inproceedings{sun2024content,
title={Content-Style Decoupling for Unsupervised Makeup Transfer without Generating Pseudo Ground Truth},
author={Sun, Zhaoyang and Xiong, Shengwu and Chen, Yaxiong and Rong, Yi}
journal={Proceedings of the IEEE/CVF conference on computer vision and pattern recognition},
year={2024}
}
```