sapiens

High-resolution models for human tasks.

Liger-Kernel

Efficient Triton Kernels for LLM Training

NarratoAI

利用AI大模型，一键解说并剪辑视频； Using AI models to automatically provide commentary and edit videos with a single click.

moshi

Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.

VideoLingo

Netflix-level subtitle cutting, translation, alignment, and even dubbing - one-click fully automated AI video subtitle team | Netflix级字幕切割、翻译、对齐、甚至加上配音，一键全自动视频搬运AI字幕组

RagaAI-Catalyst

Python SDK for Agent AI Observability, Monitoring and Evaluation Framework. Includes features like agent, llm and tools tracing, debugging multi-agentic system, self-hosted dashboard and advanced analytics with timeline and execution graph view

graphiti

这是一个专为 AI 智能体设计的框架，用于构建和查询实时、具有时间感知能力的知识图谱。它能够持续集成用户交互、结构化或非结构化等动态数据，形成连贯且可查询的知识图谱。支持增量数据更新、高效检索和历史查询，适用于开发交互式、上下文感知的 AI 应用。

BitNet

Official inference framework for 1-bit LLMs

flux

Official inference repo for FLUX.1 models

Jobs_Applier_AI_Agent_AIHawk

AIHawk aims to easy job hunt process by automating the job application process. Utilizing artificial intelligence, it enables users to apply for multiple jobs in a tailored way.

OpCore-Simplify

A tool designed to simplify the creation of OpenCore EFI

ControlNetPlus

ControlNetPlus ControlNet++: 适用于图像生成和编辑的一体化ControlNet！ ***我们设计了一种新架构，可在条件文本到图像生成中支持10多种控制类型，并能生成与midjourney视觉上相媲美的高分辨率图像***。该网络基于原始ControlNet架构，我们提出了两个新模块：1. 扩展原始ControlNet以使用相同的网络参数支持不同的图像条件。2. 在不增加计算负担的情况下支持多个条件输入，这对于希望详细编辑图像的设计师尤其重要。不同条件使用相同的条件编码器，无需增加额外的计算或参数。我们在SDXL上进行了彻底的实验，在控制能力和美学评分方面均表现出色