← 开源
visomaster

VisoMaster

Powerful & Easy-to-Use Video Face Swapping and Editing Software

ApplicationsContent creationPython
在 GitHub 打开
增长势头
+124 小时新增 Star+0.0%
2.10k
Star
368
Fork
+5
本周
4
贡献者
创建于 2025-01-27 · 更新于 2026-10-15 · 今日第 5178 名
主要开发者

visomaster/VisoMaster 排名第 5,178,有 2,098 个星标。

同类别比较

visomaster/VisoMaster 排名第 5,178,此处有 8 个同类条目;fikrikarim/parlor 排名第 5,183。

同类别比较
名称排名指标
beelzebub-labs/beelzebub5,146
语言:
Go
星标数:
2,198
分叉数:
220
简介:
A secure low code deception runtime framework, leveraging AI for System Virtualization.
Jazee6/cloudflare-ai-web5,153
语言:
TypeScript
星标数:
2,187
分叉数:
572
简介:
Cloudflare AI Platform with one-click deployment
zombieyang/sd-ppp5,156
语言:
JavaScript
星标数:
2,182
分叉数:
121
简介:
A Photoshop AI plugin
ozgrozer/ai-renamer5,168
语言:
JavaScript
星标数:
2,133
分叉数:
144
简介:
A Node.js CLI that uses Ollama and LM Studio models (Llava, Gemma, Llama etc.) to intelligently rename files by their contents
fikrikarim/parlor5,183
语言:
Python
星标数:
2,076
分叉数:
277
简介:
On-device, real-time multimodal AI with features similar to GPT-Live
p0n1/epub_to_audiobook5,184
语言:
Python
星标数:
2,075
分叉数:
225
简介:
EPUB to audiobook converter, optimized for Audiobookshelf, WebUI included
microsoft/intelligent-terminal5,189
语言:
C++
星标数:
2,057
分叉数:
165
简介:
A fork of Windows Terminal with native agent integration, right in your command line.
omnimind-ai/OmniBot5,196
语言:
Dart
星标数:
2,046
分叉数:
147
简介:
Your on-phone / mobile AI Agent / Claw, capable of operating terminals and performing a wide range of tasks in the Android world || 你的手机 AI 代理,她可以操作终端,也可以完成 Android 世界的广泛任务
关键参数与规格
关键参数与规格
参数值
语言Python
类别Applications
子类别Content creation
关键词Video production, Voice cloning
星标数2,098
分叉数368
贡献者4
创建日期2025-01-27
更新日期2026-10-15
1 天星标数1
7 天星标数5
排名5,178
上次排名5,345
排名变化167
7 天星标排名5,510
上次 7 天星标排名5,496
7 天星标排名变化-14
总星标排名6,103
上次总星标排名6,099
总星标排名变化-4
README 摘录

VisoMaster VisoMaster is a powerful yet easy-to-use tool for face swapping and editing in images and videos. It utilizes AI to produce natural-looking results with minimal effort, making it ideal for both casual users and professionals. **User-Friendly Interface**: Intuitive and easy to use **Video Markers**: Adjust settings per frame for precise results **TensorRT Support**: Leverages supported GPUs for ultra-fast processing **Many More Advanced Features** 🎉 Automatic Installation (Windows) For Windows users with an Nvidia GPU, we

provide an automatic installer for easy set up. You can get the installer from the releases page or from this link. Choose the correct CUDA version inside the installer based on your GPU Compatibility. After successful installation, go to your installed directory and run the **Start_Portable. bat** file to launch **VisoMaster** **Manual Installation Guide (Nvidia)** Follow the steps below to install and run **VisoMaster** on your system. Clone the Repository** Open a terminal or command prompt and run: **2

. Create and Activate a Conda Environment** **3. Download Models and Other Dependencies** 1. Download all the files from this page and copy it to the ***dependencies/*** folder. **Note**: You do not need to download the Source code (zip) and Source code (tar. Run the Application** Once everything is set up, start the application by opening the **Start. For missing models, double-check that all models are placed in the correct directories. Join Discord Support The Project ## This project was made

possible by the combined efforts of **@argenspin** and **@Alucard24** with the support of countless other members in our Discord community. If you wish to support us for the continued development of **Visomaster**, you can donate to either of us (or Both if you're double Awesome :smiley: ) **argenspin** ### BuyMeACoffee BTC: bc1qe8y7z0lkjsw6ssnlyzsncw0f4swjgh58j9vrqm84gw2nscgvvs5s4fts8g ETH: 0x967a442FBd13617DE8d5fDC75234b2052122156B **Alucard24** ### BuyMeACoffee PayPal BTC: 15ny8vV3ChYsEuDta6VG3aKdT6Ra7duRAc Disclaimer: ## **VisoMaster** is a hobby project that we are making available to the community as a thank you to all of the contributors

ahead of us. We've copied the disclaimer from Swap-Mukham here since it is well-written and applies 100% to this repo. We would like to emphasize that our swapping software is intended for responsible and ethical use only. We must stress that users are solely responsible for their actions when using our software. Intended Usage: This software is designed to assist users in creating realistic and entertaining content, such as movies, visual effects, virtual reality experiences, and other creative

applications. We encourage users to explore these possibilities within the boundaries of legality, ethical considerations, and respect for others' privacy. Ethical Guidelines: Users are expected to adhere to a set of ethical guidelines when using our software. These guidelines include, but are not limited to: Not creating or sharing content that could harm, defame, or harass individuals. Obtaining proper consent and permissions from individuals featured in the content before using their likeness. Avoiding the use of this technology for deceptive

purposes, including misinformation or malicious intent. Respecting and abiding by applicable laws, regulations, and copyright restrictions. Privacy and Consent: Users

常见问题

记录了多少星标和分叉?

visomaster/VisoMaster 有 2,098 个星标和 368 个分叉。

仓库排名是多少?

visomaster/VisoMaster 排名第 5,178。

记录的语言和类别是什么?

visomaster/VisoMaster 有 2,098 个星标,语言为 Python,类别为 Applications。

哪个仓库排名最接近?

visomaster/VisoMaster 与 fikrikarim/parlor 比较,后者排名第 5,183,有 2,076 个星标。

README

VisoMaster

VisoMaster is a powerful yet easy-to-use tool for face swapping and editing in images and videos. It utilizes AI to produce natural-looking results with minimal effort, making it ideal for both casual users and professionals.


Features

🔄 Face Swap

  • Supports multiple face swapper models
  • Compatible with DeepFaceLab trained models (DFM)
  • Advanced multi-face swapping with masking options for each facial part
  • Occlusion masking support (DFL XSeg Masking)
  • Works with all popular face detectors & landmark detectors
  • Expression Restorer: Transfers original expressions to the swapped face
  • Face Restoration: Supports all popular upscaling & enhancement models

🎭 Face Editor (LivePortrait Models)

  • Manually adjust expressions and poses for different face parts
  • Fine-tune colors for Face, Hair, Eyebrows, and Lips using RGB adjustments

🚀 Other Powerful Features

  • Live Playback: See processed video in real-time before saving
  • Face Embeddings: Use multiple source faces for better accuracy & similarity
  • Live Swapping via Webcam: Stream to virtual camera for Twitch, YouTube, Zoom, etc.
  • User-Friendly Interface: Intuitive and easy to use
  • Video Markers: Adjust settings per frame for precise results
  • TensorRT Support: Leverages supported GPUs for ultra-fast processing
  • Many More Advanced Features 🎉

Automatic Installation (Windows)

  • For Windows users with an Nvidia GPU, we provide an automatic installer for easy set up.
  • You can get the installer from the releases page or from this link.
  • Choose the correct CUDA version inside the installer based on your GPU Compatibility.
  • After successful installation, go to your installed directory and run the Start_Portable.bat file to launch VisoMaster

Manual Installation Guide (Nvidia)

Follow the steps below to install and run VisoMaster on your system.

Prerequisites

Before proceeding, ensure you have the following installed on your system:


Installation Steps

1. Clone the Repository

Open a terminal or command prompt and run:

git clone https://github.com/visomaster/VisoMaster.git
cd VisoMaster

2. Create and Activate a Conda Environment

conda create -n visomaster python=3.10.13 -y
conda activate visomaster

3. Install CUDA and cuDNN

conda install -c nvidia/label/cuda-12.4.1 cuda-runtime
conda install -c conda-forge cudnn

4. Install Additional Dependencies

conda install scikit-image
pip install -r requirements_cu124.txt

5. Download Models and Other Dependencies

  1. Download all the required models
python download_models.py
  1. Download all the files from this page and copy it to the dependencies/ folder.

Note: You do not need to download the Source code (zip) and Source code (tar.gz) files

6. Run the Application

Once everything is set up, start the application by opening the Start.bat file. On Linux just run python main.py.

Troubleshooting

  • If you face CUDA-related issues, ensure your GPU drivers are up to date.
  • For missing models, double-check that all models are placed in the correct directories.

Join Discord

Support The Project

This project was made possible by the combined efforts of @argenspin and @Alucard24 with the support of countless other members in our Discord community. If you wish to support us for the continued development of Visomaster, you can donate to either of us (or Both if you're double Awesome :smiley: )

argenspin

  • BuyMeACoffee
  • BTC: bc1qe8y7z0lkjsw6ssnlyzsncw0f4swjgh58j9vrqm84gw2nscgvvs5s4fts8g
  • ETH: 0x967a442FBd13617DE8d5fDC75234b2052122156B

Alucard24

Disclaimer:

VisoMaster is a hobby project that we are making available to the community as a thank you to all of the contributors ahead of us. We've copied the disclaimer from Swap-Mukham here since it is well-written and applies 100% to this repo.

We would like to emphasize that our swapping software is intended for responsible and ethical use only. We must stress that users are solely responsible for their actions when using our software.

Intended Usage: This software is designed to assist users in creating realistic and entertaining content, such as movies, visual effects, virtual reality experiences, and other creative applications. We encourage users to explore these possibilities within the boundaries of legality, ethical considerations, and respect for others' privacy.

Ethical Guidelines: Users are expected to adhere to a set of ethical guidelines when using our software. These guidelines include, but are not limited to:

Not creating or sharing content that could harm, defame, or harass individuals. Obtaining proper consent and permissions from individuals featured in the content before using their likeness. Avoiding the use of this technology for deceptive purposes, including misinformation or malicious intent. Respecting and abiding by applicable laws, regulations, and copyright restrictions.

Privacy and Consent: Users are responsible for ensuring that they have the necessary permissions and consents from individuals whose likeness they intend to use in their creations. We strongly discourage the creation of content without explicit consent, particularly if it involves non-consensual or private content. It is essential to respect the privacy and dignity of all individuals involved.

Legal Considerations: Users must understand and comply with all relevant local, regional, and international laws pertaining to this technology. This includes laws related to privacy, defamation, intellectual property rights, and other relevant legislation. Users should consult legal professionals if they have any doubts regarding the legal implications of their creations.

Liability and Responsibility: We, as the creators and providers of the deep fake software, cannot be held responsible for the actions or consequences resulting from the usage of our software. Users assume full liability and responsibility for any misuse, unintended effects, or abusive behavior associated with the content they create.

By using this software, users acknowledge that they have read, understood, and agreed to abide by the above guidelines and disclaimers. We strongly encourage users to approach this technology with caution, integrity, and respect for the well-being and rights of others.

Remember, technology should be used to empower and inspire, not to harm or deceive. Let's strive for ethical and responsible use of deep fake technology for the betterment of society.

排名相邻
同类项目