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

A one-stop, open-source, high-quality data extraction tool, supports PDF/webpage/e-book extraction.一站式开源高质量数据提取工具，支持PDF/网页/多格式电子书提取。

Mattermost is an open source platform for secure collaboration across the entire software development lifecycle..

Question and Answer based on Anything.

A WebUI for Efficient Fine-Tuning of 100+ LLMs (ACL 2024)

中文医疗对话模型扁鹊(BianQue)

Hallo: Hierarchical Audio-Driven Visual Synthesis for Portrait Image Animation

Kolors Team

Call all LLM APIs using the OpenAI format. Use Bedrock, Azure, OpenAI, Cohere, Anthropic, Ollama, Sagemaker, HuggingFace, Replicate, Groq (100+ LLMs)

Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

一个用于CosyVoice的api接口项目

Run your own AI cluster at home with everyday devices 📱💻 🖥️⌚

Lifelike Audio-Driven Portrait Animations through Editable Landmark Conditioning

MARS5 speech model (TTS) from CAMB.AI

Bring portraits to life!

腾讯柠檬清理是针对macOS系统专属制定的清理工具。主要功能包括重复文件和相似照片的识别、软件的定制化垃圾扫描、可视化的全盘空间分析、内存释放、浏览器隐私清理以及设备实时状态的监控等。重点聚焦清理功能，对上百款软件提供定制化的清理方案，提供专业的清理建议，帮助用户轻松完成一键式清理。

Open source free capture HTTP(S) traffic software ProxyPin, supporting full platform systems

thinkphp saas 基础包

🎉🎉🎉 MineAdmin是基于Hyperf框架 和 Vue3+Vite5 开发的前后端分离权限管理系统，自适应多终端。特色：后端 crud 生成 + 前端低代码 json 化配置

Colab for making Wav2Lip high quality and easy to use

保存微信历史版本

Real time interactive streaming digital human

[ICCV'23] Efficient Region-Aware Neural Radiance Fields for High-Fidelity Talking Portrait Synthesis

Real time streaming talking head

RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference,…

NEW - YOLOv8 🚀 in PyTorch > ONNX > OpenVINO > CoreML > TFLite

ddddocr训练工具

A collection of awesome-lists for AI, creativity and art. AI、创意和艺术领域的精选合集。https://latentbox.com