Using VapourSynth with super resolution and interpolation models and speeding them up with TensorRT.

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

CVPR2023 - Activating More Pixels in Image Super-Resolution Transformer Arxiv - HAT: Hybrid Attention Transformer for Image Restoration

Real-time speech recognition using next-gen Kaldi with ncnn without Internet connection. Support iOS, Android, Raspberry Pi, VisionFive2, LicheePi4A etc.

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

The most powerful and modular stable diffusion GUI, api and backend with a graph/nodes interface.

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

Android Database - first and fast, lightweight on-device vector database

libSQL is a fork of SQLite that is both Open Source, and Open Contributions.

A SQLite extension for efficient vector search, based on Faiss!

Work-in-progress vector search SQLite extension that runs anywhere.

Config files for self-hosting the FoloToy Server. Documents: https://docs.folotoy.com

Byzer-retrieval is a distributed retrieval system which designed as a backend for LLM RAG (Retrieval Augmented Generation). The system supports both BM25 retrieval algorithm and vector retrieval al…

Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting yo…

Colab for making Wav2Lip high quality and easy to use

Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translatio…

AI Vtuber是一个由 【ChatterBot/ChatGPT/claude/langchain/chatglm/text-gen-webui/闻达/千问/kimi/ollama】 驱动的虚拟主播【Live2D/UE/xuniren】，可以在 【Bilibili/抖音/快手/微信视频号/拼多多/斗鱼/YouTube/twitch/TikTok】 直播中与观众实时互动 或 直接在本地进行聊…

Streamer-Sales 销冠 —— 卖货主播 LLM 大模型🛒🎁，一个能够根据给定的商品特点从激发用户购买意愿角度出发进行商品解说的卖货主播大模型。🚀⭐内含详细的数据生成流程❗ 📦另外还集成了 LMDeploy 加速推理🚀、RAG检索增强生成 📚、TTS文字转语音🔊、数字人生成 🦸、 Agent 使用网络查询实时信息🌐、ASR 语音转文字🎙️

Stable Diffusion in NCNN with c++, supported txt2img and img2img

AIOS: LLM Agent Operating System

FlashAttention (Metal Port)

Mobile-Agent: The Powerful Mobile Device Operation Assistant Family

AppAgent: Multimodal Agents as Smartphone Users, an LLM-based multimodal agent framework designed to operate smartphone apps.

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

Run any open-source LLMs, such as Llama 2, Mistral, as OpenAI compatible API endpoint in the cloud.

GPT4All: Chat with Local LLMs on Any Device