Qifan Wu's starred repositories
tile-merger
A tile merger, for merging multiple images into a single image. Written in C# for the .NET framework for Windows operating systems.
StabilityMatrix
Multi-Platform Package Manager for Stable Diffusion
fashionstar-gimbal-2dof-stm32f103-openmv
STM32 OpenMV 云台
1ZLAB_Face_Track_Robot
二自由度云台实现人脸追踪。 首先是使用一款名字叫做IP摄像头的APP 采集手机摄像头的图像,在手机上建立一个视频流服务器。在局域网下,PC通过IP还有端口号获取图像。使用OpenCV的人脸检测的API获取人脸在画面中的位置,根据人脸位置距离画面中心的x轴与y轴的偏移量(offset) ,通过P比例控制(PID控制中最简单的一种)控制二自由度云台上臂与下臂的旋转角度,将角度信息通过串口通信UART发送给ESP32单片机(不限于ESP32,STM32,Arduino都可以)解析执行对应的操作,从而使得人脸尽可能处在画面的正中间。
unity-AI-Chat-Toolkit
使用unity实现AI聊天相关功能。目前这个库包含了对chatgpt、chatglm等大语言模型的api调用的代码实现以及实现了微软Azure以及百度AI的语音服务功能,语音服务均采用web api实现,支持Windows/WebGL/Android等平台
open-webui
User-friendly WebUI for AI (Formerly Ollama WebUI)
generative-ai-android
The official Android library for the Google Gemini API
Mr.-Ranedeer-AI-Tutor
A GPT-4 AI Tutor Prompt for customizable personalized learning experiences.
streaming-llm
[ICLR 2024] Efficient Streaming Language Models with Attention Sinks
ColossalAI
Making large AI models cheaper, faster and more accessible
SwiftInfer
Efficient AI Inference & Serving
LLaMA-Factory
Efficiently Fine-Tune 100+ LLMs in WebUI (ACL 2024)
threestudio
A unified framework for 3D content generation.
audiocraft
Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable music generation LM with textual and melodic conditioning.
AnimateAnyone
Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation
Retrieval-based-Voice-Conversion-WebUI
Easily train a good VC model with voice data <= 10 mins!