yigecom Goto Github PK

ai-vtuber

AI Vtuber是一个由 【ChatterBot/ChatGPT/claude/langchain（本地/llm）/chatglm/text-generation-webui/闻达】 驱动的虚拟主播【Live2D】，可以在 【Bilibili/抖音/快手/斗鱼】 直播中与观众实时互动 或 直接在本地进行聊天。它使用自然语言处理和文本转语音技术【edge-tts/VITS/elevenlabs/bark-gui】生成对观众问题的回答并可以选择【so-vits-svc/DDSP-SVC】变声；通过特定指令协同Stable Diffusion进行画图展示。并且可以自定义文案进行循环播放。

backend

PlayEdu 后台管理前端程序

binggu.github.io

冰谷

bisheng

Bisheng is an open LLM devops platform for next generation AI applications.

chatgptbox

Integrating ChatGPT into your browser deeply, everything you need is here

cursor

An AI-powered code editor based on VSCode 🤖

diffbir

Towards Blind Image Restoration with Generative Diffusion Prior

dify

One API for plugins and datasets, one interface for prompt engineering and visual operation, all for creating powerful AI applications.

disc-medllm

Repository of DISC-MedLLM, it is a comprehensive solution that leverages Large Language Models (LLMs) to provide accurate and truthful medical response in end-to-end conversational healthcare services.

fay

Fay是一个完整的开源项目，包含Fay控制器及数字人模型，可灵活组合出不同的应用场景：虚拟主播、现场推销货、商品导购、语音助理、远程语音助理、数字人互动、数字人面试官及心理测评、贾维斯、Her。 开源项目，非产品试用！！！

flowise

Drag & drop UI to build your customized LLM flow

flowiseai-railway

frontend

PlayEdu PC 前端项目

gfpgan

GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.

ketang

laf

Laf is a cloud development platform offering ready-to-use resources like cloud functions, databases, and storage. It empowers developers to quickly unleash their creativity.

llmstack

No-code platform to build generative AI apps, chatbots and agents with your data

magic-edit

MagicEdit: High-Fidelity Temporally Coherent Video Editing

migu.github.io

mimic-iii-vm

Download and load MIMIC-III into a PostgreSQL DB on an Ubuntu VM

my-migu

notion-zh_cn

notion 中文化

opendream

An extensible, easy-to-use, and portable diffusion web UI 👨‍🎨

opengpt

Create your own ChatGPT App in seconds.

paddleavatar

你是否曾经幻想过与自己的虚拟人交互？现在，使用PaddleAvatar，您可以将自己的图像、音频和视频转化为一个逼真的数字人视频，与其进行人机交互。 PaddleAvatar是一种基于PaddlePaddle深度学习框架的数字人生成工具，基于Paddle的许多套件，它可以将您的数字图像、音频和视频合成为一个逼真的数字人视频。除此之外，PaddleAvatar还支持进一步的开发，例如使用自然语言处理技术，将数字人视频转化为一个完整的人机交互系统，使得您能够与虚拟的自己进行真实的对话和互动。 使用PaddleAvatar，您可以将数字人视频用于各种场合，例如游戏、教育、虚拟现实等等。PaddleAvatar为您提供了一个自由创作的数字世界，让您的想象力得到了充分的释放！

panohead

Code Repository for CVPR 2023 Paper "PanoHead: Geometry-Aware 3D Full-Head Synthesis in 360 degree"

playedu

rope

GUI-focused roop

thin-plate-spline-motion-model

[CVPR 2022] Thin-Plate Spline Motion Model for Image Animation.

webapp-conversation