The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

The official gpt4free repository | various collection of powerful language models | gpt-4o and deepseek v3 & r1

A list of useful payloads and bypass for Web Application Security and Pentest/CTF

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

Making large AI models cheaper, faster and more accessible

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

Easily train a good VC model with voice data <= 10 mins!

Open-sourced codes for MiniGPT-4 and MiniGPT-v2 (https://minigpt-4.github.io, https://minigpt-v2.github.io/)

The official Python library for the OpenAI API

Code for the paper "Language Models are Unsupervised Multitask Learners"

OpenAI Baselines: high-quality implementations of reinforcement learning algorithms

Bring portraits to life!

[CVPR 2023] SadTalker：Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation

Private chat with local GPT with document, images, video, etc. 100% private, Apache 2.0. Supports oLLaMa, Mixtral, llama.cpp, and more. Demo: https://gpt.h2o.ai/ https://gpt-docs.h2o.ai/

An educational resource to help anyone learn deep reinforcement learning.

🤖 史上最强云手机远程桌面逆向抓包HOOK自动化取证能力集一体的安卓 RPA 框架，下一代移动数据自动化机器人。

OpenChat: Advancing Open-source Language Models with Imperfect Data

An all-in-one hacking tool to remotely exploit Android devices using ADB and Metasploit-Framework to get a Meterpreter session.

H2O LLM Studio - a framework and no-code GUI for fine-tuning LLMs. Documentation: https://docs.h2o.ai/h2o-llmstudio/

中文古诗自动作诗机器人，x炸天，基于tensorflow1.10 api，正在积极维护升级中，快star，保持更新！

EchoMimic: Lifelike Audio-Driven Portrait Animations through Editable Landmark Conditioning

Minimal and Clean Reinforcement Learning Examples

Dataset of GPT-2 outputs for research in detection, biases, and more

A WebUI for ChatGLM-6B

本项目基于SadTalkers实现视频唇形合成的Wav2lip。通过以视频文件方式进行语音驱动生成唇形，设置面部区域可配置的增强方式进行合成唇形（人脸）区域画面增强，提高生成唇形的清晰度。使用DAIN 插帧的DL算法对生成视频进行补帧，补充帧间合成唇形的动作过渡，使合成的唇形更为流畅、真实以及自然。

这是作者的系列网络安全自学教程，主要是关于网安工具和实践操作的在线笔记，希望对大家有所帮助，学无止境，加油。

K8Ladon大型内网渗透自定义插件化扫描神器，包含信息收集、网络资产、漏洞扫描、密码爆破、漏洞利用，程序采用多线程批量扫描大型内网多个IP段C段主机，目前插件包含: C段旁注扫描、子域名扫描、Ftp密码爆破、Mysql密码爆破、Oracle密码爆破、MSSQL密码爆破、Windows/Linux系统密码爆破、存活主机扫描、端口扫描、Web信息探测、操作系统版本探测、Cisco思科设备扫描等…

SwissArmyTransformer is a flexible and powerful library to develop your own Transformer variants.

该资源为系统安全和逆向分析实验，包括作者从零学习恶意代码分析、病毒逆向分析的工具及样本，基础性文章，希望对您有所帮助~

Android security insights in full spectrum.