Linjiahua

llama_index

LlamaIndex is a data framework for your LLM applications

Vary

[ECCV2024] Official code implementation of Vary: Scaling Up the Vision Vocabulary of Large Vision Language Models.

PhotoMaker

PhotoMaker [CVPR 2024]

facechain

FaceChain is a deep-learning toolchain for generating your Digital-Twin.

kohya_ss

Make-A-Character

Official repo for Make-A-Character: High Quality Text-to-3D Character Generation within Minutes

awesome-chatgpt-prompts

This repo includes ChatGPT prompt curation to use ChatGPT better.

streaming-llm

[ICLR 2024] Efficient Streaming Language Models with Attention Sinks

FastChat

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

instructor

structured outputs for llms

CodeFormer

[NeurIPS 2022] Towards Robust Blind Face Restoration with Codebook Lookup Transformer

slidev

Presentation Slides for Developers

autogen

A programming framework for agentic AI. Discord: https://aka.ms/autogen-dc. Roadmap: https://aka.ms/autogen-roadmap

KwaiAgents

A generalized information-seeking agent system with Large Language Models (LLMs).

Wav2Lip

This repository contains the codes of "A Lip Sync Expert Is All You Need for Speech to Lip Generation In the Wild", published at ACM Multimedia 2020. For HD commercial model, please try out Sync Labs

video-retalking

[SIGGRAPH Asia 2022] VideoReTalking: Audio-based Lip Synchronization for Talking Head Video Editing In the Wild

SadTalker-Video-Lip-Sync

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。

lobe-tts

🎤 Lobe TTS - A high-quality & reliable TTS/STT library for Server and Browser

SadTalker

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

sd-webui-controlnet

WebUI extension for ControlNet

PowerInfer

High-speed Large Language Model Serving on PCs with Consumer-grade GPUs

swift

ms-swift: Use PEFT or Full-parameter to finetune 300+ LLMs or 50+ MLLMs. (Qwen2, GLM4v, Internlm2.5, Yi, Llama3, Llava-Video, Internvl2, MiniCPM-V, Deepseek, Baichuan2, Gemma2, Phi3-Vision, ...)

DigitalLife

megablocks-public

stable-diffusion-webui

Stable Diffusion web UI

magic-animate

[CVPR 2024] MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model

so-vits-svc

SoftVC VITS Singing Voice Conversion

pyvideotrans

Translate the video from one language to another and add dubbing. 将视频从一种语言翻译为另一种语言，并添加配音

xuance

XuanCe: A Comprehensive and Unified Deep Reinforcement Learning Library

easy-rl

强化学习中文教程（蘑菇书🍄），在线阅读地址：https://datawhalechina.github.io/easy-rl/