Stars
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…
An AI-Powered Speech Processing Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Enhancement, Separation, and Target Speaker Extraction, etc.
🤙 Easy replacement for LaTeX Beamer! 🥂 custom Marp templates with a selection of over a dozen themes
Production ready LLM model compression/quantization toolkit with hw accelerated inference support for both cpu/gpu via HF, vLLM, and SGLang.
[CVPR 2025] EchoMimicV2: Towards Striking, Simplified, and Semi-Body Human Animation
ComfyUI adaptation of IDM-VTON for virtual try-on.
Character Animation (AnimateAnyone, Face Reenactment)
MiniCPM-o 2.6: A GPT-4o Level MLLM for Vision, Speech and Multimodal Live Streaming on Your Phone
Code for Paper "UniAnimate: Taming Unified Video Diffusion Models for Consistent Human Image Animation".
Official inference repo for FLUX.1 models
A modular graph-based Retrieval-Augmented Generation (RAG) system
Collection of publicly available IPTV channels from all over the world
Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.
Industry leading face manipulation platform
Ingest, parse, and optimize any data format ➡️ from documents to multimedia ➡️ for enhanced compatibility with GenAI frameworks
OCR, layout analysis, reading order, table recognition in 90+ languages
Firefly: 大模型训练工具,支持训练Qwen2.5、Qwen2、Yi1.5、Phi-3、Llama3、Gemma、MiniCPM、Yi、Deepseek、Orion、Xverse、Mixtral-8x7B、Zephyr、Mistral、Baichuan2、Llma2、Llama、Qwen、Baichuan、ChatGLM2、InternLM、Ziya2、Vicuna、Bloom等大模型
Llama3、Llama3.1 中文仓库(随书籍撰写中... 各种网友及厂商微调、魔改版本有趣权重 & 训练、推理、评测、部署教程视频 & 文档)
RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.
Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs
A streamlined and customizable framework for efficient large model evaluation and performance benchmarking
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficie…
Open-Sora: Democratizing Efficient Video Production for All
纯c++的全平台llm加速库,支持python调用,chatglm-6B级模型单卡可达10000+token / s,支持glm, llama, moss基座,手机端流畅运行