💬 An extensive collection of exceptional resources dedicated to the captivating world of talking face synthesis! ⭐ If you find this repo useful, please give it a star! 🤩

Quantized Attention that achieves speedups of 2.1-3.1x and 2.7-5.1x compared to FlashAttention2 and xformers, respectively, without lossing end-to-end metrics across various models.

利用AI大模型，一键解说并剪辑视频； Using AI models to automatically provide commentary and edit videos with a single click.

Structured Text Generation

🧸 Lobe Vidol - Making Virtual Idols Accessible for EveryOne

为GPT/GLM等LLM大语言模型提供实用化交互接口，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, m…

Vector (and Scalar) Quantization, in Pytorch

Create Live Photos from a photo+video pair compatible with Apple Photos

分流完善的 OpenClash 订阅转换模板，搭配保姆级 OpenClash 设置教程，无需套娃其他插件即可实现完美分流、DNS无污染无泄漏，且快速的国内外上网体验。

Inference code to "Adversarially-Guided Portrait Matting"

Convert VMD motion data to a readable text file.

real time face swap and one-click video deepfake with only a single image

Collection of recent shadow removal works, including papers, codes, datasets, and metrics.

🎥 Python and OpenCV-based scene cut/transition detection program & library.

Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance

[CSUR] A Survey on Video Diffusion Models

Tools to Design or Visualize Architecture of Neural Network

SSH-Snake is a self-propagating, self-replicating, file-less script that automates the post-exploitation task of SSH private key and host discovery.

Performance-portable, length-agnostic SIMD with runtime dispatch

Use any web browser or WebView as GUI, with your preferred language in the backend and modern web technologies in the frontend, all in a lightweight portable library.

A curated list of recent diffusion models for video generation, editing, restoration, understanding, etc.

VividTalk: One-Shot Audio-Driven Talking Head Generation Based on 3D Hybrid Prior

About Project Page for Outfit Anyone

Large scale image dataset visiualization tool.

build-once run-anywhere c library

Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation

NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.

2021年最新整理， C++ 学习资料，含C++ 11 / 14 / 17 / 20 / 23 新特性、入门教程、推荐书籍、优质文章、学习笔记、教学视频等

The official GitHub page for the survey paper "A Survey of Large Language Models".