仓库/Skill 库

Transformers：面向文本、视觉、音频及多模态 SOTA 机器学习模型的模型定义框架，同时支持推理与训练。🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

潜空间文本到图像扩散模型。A latent text-to-image diffusion model

OpenAI Whisper 模型的 C/C++ 移植版本。Port of OpenAI's Whisper model in C/C++

开源桌面应用，面向本地 LLM。支持文本、视觉、tool-calling，提供 OpenAI/Anthropic 兼容 API。100% 隐私保护。Open-source desktop app for local LLMs. Text, vision, tool-calling, OpenAI/Anthropic-compatible API. 100% private.

🐸💬 —— 一个历经研究与生产环境考验的 Text-to-Speech 深度学习工具包。🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

🔊 文本提示生成式音频模型🔊 Text-Prompted Generative Audio Model

面向实时和流媒体、跨平台可定制的 ML 解决方案。Cross-platform, customizable ML solutions for live and streaming media.

开箱即用的 OCR，支持 80+ 种语言及所有主流书写系统，包括拉丁文、中文、阿拉伯文、天城文、西里尔文等。Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.

一款免费、开源且可扩展的语音转文字应用程序，完全离线运行。A free, open source, and extensible speech-to-text application that works completely offline.

DeepSpeech 是一个开源嵌入式（离线、端侧）语音转文字引擎，可在从 Raspberry Pi 4 到高性能 GPU 服务器的设备上实时运行。DeepSpeech is an open source embedded (offline, on-device) speech-to-text engine which can run in real time on devices ranging from a Raspberry Pi 4 to high power GPU servers.

LabelImg 现已成为 Label Studio 社区的一部分。由 Tzutalin 创建的热门图像标注工具已不再积极开发，但你可以查看 Label Studio——这款开源数据标注工具支持图像、文本、超文本、音频、视频和时序数据。LabelImg is now part of the Label Studio community. The popular image annotation tool created by Tzutalin is no longer actively being developed, but you can check out Label Studio, the open source data labeling tool for images, text, hypertext, audio, video and time-series data.

围绕 PyTorch 在视觉、文本、强化学习等领域的一组示例。A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.

OpenUI 可让你凭想象力描述 UI，并实时看到渲染效果。OpenUI let's you describe UI using your imagination, then see it rendered live.

工业级可控、高效的零样本文本转语音系统An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System

为研究人员和开发者构建的可扩展生成式 AI 框架，面向 LLM、多模态和语音 AI（自动语音识别与文字转语音）。A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

✨✨多模态大语言模型最新进展。:sparkles::sparkles:Latest Advances on Multimodal Large Language Models

Toonflow 是开源一站式 AI 短剧创作工具，将小说、剧本快速转化为动画短剧。集成 AI 编剧、智能分镜、角色与视频生成，跨平台桌面端轻量部署，助力创作者低成本批量产出视觉内容。Toonflow is an open-source AI tool that turns stories and scripts into animated short dramas. Features AI scriptwriting, storyboarding, character and video generation. A cross-platform desktop app for efficient content creation.

在 Krita 中使用 AI 生成图像的精简界面。支持 Inpaint 与 Outpaint，可选文本提示，无需调参。Streamlined interface for generating images with AI in Krita. Inpaint and outpaint with optional text prompt, no tweaking required.

通过修改一行代码即可将 GPT 替换为任意 LLM。Xinference 让你在云端、本地或笔记本上运行开源、语音和多模态模型，全部通过统一的生产就绪推理 API。Swap GPT for any LLM by changing a single line of code. Xinference lets you run open-source, speech, and multimodal models on cloud, on-prem, or your laptop — all through one unified, production-ready inference API.

轻松微调、评估和部署 Gemma 4、Qwen3.5、Qwen3.6、gpt-oss、DeepSeek-R1 或任意开源 LLM / VLM。Easily fine-tune, evaluate and deploy Qwen, Gemma, or any open weight LLM!

LTX-2 音视频生成模型的官方 Python 推理与 LoRA 训练包。Official Python inference and LoRA trainer package for the LTX-2 audio–video generative model.

面向 Apple Silicon 的端侧语音 AI。On-device Speech AI for Apple Silicon

一个覆盖文本、图像、视频与音频任务的统一多模态评估工具包。One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks

基于 PaddlePaddle 的高性能 LLM 与 VLM 推理部署工具包。High-performance Inference and Deployment Toolkit for LLMs and VLMs based on PaddlePaddle

开源 LLM/VLM 负载均衡器与服务平台，用于规模化自托管 LLM（和 VLM）🏓🦙 作为 llm-d、Docker Model Runner 等项目的替代方案，组件更少、部署更简单，基于 ggml 生态构建。支持 CPU 和 GPU。Open-source LLM/VLM load balancer and serving platform for self-hosting LLMs (and VLMs) at scale 🏓🦙 Alternative to projects like llm-d, Docker Model Runner, etc but with less moving parts and simple deployments built around ggml ecosystem. Runs on CPU and GPU.

面向 LLM、VLM、DiT 和 REC 模型的高性能推理引擎，针对多种 AI 加速器进行了优化。该项目托管于 OpenAtom 基金会。A high-performance inference engine for LLM, VLM, DiT and REC models, optimized for diverse AI accelerators. It is hosted in OpenAtom Foundation.

兼容 OpenAI 和 Anthropic 协议的 Apple Silicon 服务端。可运行 LLM 和视觉语言模型（Llama、Qwen-VL、LLaVA），支持 continuous batching、MCP 工具调用与多模态。原生 MLX 后端，速度达 400+ tok/s，兼容 Claude Code。OpenAI and Anthropic compatible server for Apple Silicon. Run LLMs and vision-language models (Llama, Qwen-VL, LLaVA) with continuous batching, MCP tool calling, and multimodal support. Native MLX backend, 400+ tok/s. Works with Claude Code.

高性能推理引擎，支持 LLM、VLM、DiT 和 REC 模型，针对多种 AI 加速器优化A high-performance inference engine for LLM, VLM, DiT and REC models, optimized for diverse AI accelerators.

为 Bilibili、YouTube 及本地视频提供 AI 视频摘要和知识库.AI video summarizer and knowledge base for Bilibili, YouTube and local videos.

决定你的 AI 编码 Agent 阅读哪些内容，并保留凭证。每次裁剪都可逐字节恢复，从不杜撰结果，所有数据从你自己的语料库回放。Decides what your AI coding agent reads, and keeps receipts. Every cut is recoverable byte for byte, it never invents a result, and the numbers are replayed from your own corpus.

ImageTrans 插件集合。Plugins for ImageTrans

[COLMW'26] AdaFlash：通过 On-Policy 蒸馏扩散 Drafters 实现的自适应投机解码[COLMW'26] AdaFlash: Adaptive Speculative Decoding via On-Policy Distilled Diffusion Drafters

可自托管且功能丰富的视频库Self-hostable and feature-rich video library

在 LIBERO 与 RoboTwin2.0 上，基于状态融合解码与冻结视频骨干网络训练面向机器人操作的轻量级世界动作模型。Train lightweight world action models for robot manipulation using state-fusion decoding and frozen video backbones on LIBERO and RoboTwin2.0.

自托管、多用户转录平台：录制或上传音频。支持说话人标记、带时间戳的转录、跨录音识别说话人、摘要、提取行动项，并可使用自有 OpenAI 兼容 LLM 与转录内容对话。你的音频、你的服务器、你的模型。已在笔记本 RTX4070、台式机 RTX3090 与 RTX5090 上测试。Self-hosted, multi-user transcription platform: record or upload audio. Speaker-labeled, timestamped transcripts, Recognize speakers across recordings, Summarize, extract action items and chat over your transcripts with your own OpenAI-compatible LLM. Your Audio, your Server, your Model. Tested on Laptop RTX4070, Desktop RTX3090 and RTX5090

AI 教材数字化与互动辅导平台：PDF/扫描教材经 MinerU OCR 结构化出题，文本 + 视觉双模型审校与确定性质量门禁；学生端七种题型互动、分层提示与错题多轮陪练闭环；FastAPI + PostgreSQL JSONB + React 19