An updated version of virtual model making

Last update: Dec 09, 2022

Related tags

Overview

Model-Swap-Face v2

这个项目是基于stylegan2 pSp制作的，比v1版本Model-Swap-Face在推理速度和图像质量上有一定提升。主要的功能是将虚拟模特进行环球不同区域的风格转换，目前转换器提供西欧模特、东亚模特和北非模特三种主流的风格样式，可帮我们实现生产资料零成本化以及广告制作的高效化；此外项目还提供了去位姿编码器以获得模特的正脸肖像。投射器的版权所有：www.seeprettyface.com。此块内容目前还没有花很多精力搞，先当做一种资源分享给大家。

效果预览

Inference框架

使用方法

环境配置

参照pSp文档进行环境配置。

下载模型

模型下载地址参见pretrained_models文件夹中的txt文档，主要包括的模型如下：
encoder.pt -- 含位姿编码器
encoder_without_pos.pt -- 去位姿编码器
projector_EastAsian.pt -- 东亚模特投射器
projector_WestEuropean.pt -- 西欧模特投射器
projector_NorthAfrican.pt -- 北非模特投射器
shape_predictor_68_face_landmarks.dat -- 人脸检测
79999_iter.pth -- 人脸mask分割

运行代码

将图片放在input文件夹下，然后编辑scripts/inference.py，运行如下代码：
python scripts/inference.py
结果会保存在output文件夹下

了解更多

我周末的时候喜欢思考一些新的应用场景和模式，欢迎访问我的网站了解更多。

An updated version of virtual model making

Related tags

Overview

Model-Swap-Face v2

效果预览

Inference框架

使用方法

环境配置

下载模型

运行代码

了解更多

Owner

seeprettyface.com

Unofficial keras(tensorflow) implementation of MAE model from Masked Autoencoders Are Scalable Vision Learners

Flow is a computational framework for deep RL and control experiments for traffic microsimulation.

ML models and internal tensors 3D visualizer

Deep Q-Learning Network in pytorch (not actively maintained)

Mmdet benchmark with python

O-CNN: Octree-based Convolutional Neural Networks for 3D Shape Analysis

Code for ICMI2020 and ICMI2021 papers: "Studying Person-Specific Pointing and Gaze Behavior for Multimodal Referencing of Outside Objects from a Moving Vehicle" and "ML-PersRef: A Machine Learning-based Personalized Multimodal Fusion Approach for Referencing Outside Objects From a Moving Vehicle"

A library for preparing, training, and evaluating scalable deep learning hybrid recommender systems using PyTorch.

A U-Net combined with a variational auto-encoder that is able to learn conditional distributions over semantic segmentations.

Research code for Arxiv paper "Camera Motion Agnostic 3D Human Pose Estimation"

[ICML 2021] “ Self-Damaging Contrastive Learning”, Ziyu Jiang, Tianlong Chen, Bobak Mortazavi, Zhangyang Wang

“英特尔创新大师杯”深度学习挑战赛赛道3：CCKS2021中文NLP地址相关性任务

(3DV 2021 Oral) Filtering by Cluster Consistency for Large-Scale Multi-Image Matching

Continuous Conditional Random Field Convolution for Point Cloud Segmentation

DaReCzech is a dataset for text relevance ranking in Czech

Jarvis Project is a basic virtual assistant that uses TensorFlow for learning.

The easiest tool for extracting radiomics features and training ML models on them.

Implementation of ProteinBERT in Pytorch

AIR^2 for Interaction Prediction

Implementation of Heterogeneous Graph Attention Network

An updated version of virtual model making

Related tags

Overview

Model-Swap-Face v2

效果预览

Inference框架

使用方法

环境配置

下载模型

运行代码

了解更多

Owner

seeprettyface.com

Unofficial keras(tensorflow) implementation of MAE model from Masked Autoencoders Are Scalable Vision Learners

Flow is a computational framework for deep RL and control experiments for traffic microsimulation.

ML models and internal tensors 3D visualizer

Deep Q-Learning Network in pytorch (not actively maintained)

Mmdet benchmark with python

O-CNN: Octree-based Convolutional Neural Networks for 3D Shape Analysis

Code for ICMI2020 and ICMI2021 papers: "Studying Person-Specific Pointing and Gaze Behavior for Multimodal Referencing of Outside Objects from a Moving Vehicle" and "ML-PersRef: A Machine Learning-based Personalized Multimodal Fusion Approach for Referencing Outside Objects From a Moving Vehicle"

A library for preparing, training, and evaluating scalable deep learning hybrid recommender systems using PyTorch.

A U-Net combined with a variational auto-encoder that is able to learn conditional distributions over semantic segmentations.

Research code for Arxiv paper "Camera Motion Agnostic 3D Human Pose Estimation"

[ICML 2021] “ Self-Damaging Contrastive Learning”, Ziyu Jiang, Tianlong Chen, Bobak Mortazavi, Zhangyang Wang

“英特尔创新大师杯”深度学习挑战赛 赛道3：CCKS2021中文NLP地址相关性任务

(3DV 2021 Oral) Filtering by Cluster Consistency for Large-Scale Multi-Image Matching

Continuous Conditional Random Field Convolution for Point Cloud Segmentation

DaReCzech is a dataset for text relevance ranking in Czech

Jarvis Project is a basic virtual assistant that uses TensorFlow for learning.

The easiest tool for extracting radiomics features and training ML models on them.

Implementation of ProteinBERT in Pytorch

AIR^2 for Interaction Prediction

Implementation of Heterogeneous Graph Attention Network

“英特尔创新大师杯”深度学习挑战赛赛道3：CCKS2021中文NLP地址相关性任务