Latest AI Resources

Total 3185 articles posts
Sana:快速生成高分辨率图像,0.6B超小尺寸模型,低配笔记本GPU运行

Sana: fast generation of high-resolution images, 0.6B ultra-small size model, low-profile laptop GPU operation

General Introduction Sana is an efficient high-resolution image generation framework developed by NVIDIA Labs, capable of generating images up to 4096 × 4096 resolution in a matter of seconds.Sana utilizes a linear diffusion transformer and deep compression self-encoder technology to significantly...
2yrs ago
0111.3K
录咖:一站式音视频处理平台|视频生成|AI字幕|提取音频|语音转文字

Record Cafe: One-stop Audio/Video Processing Platform|Video Generation|AI Subtitle|Audio Extraction|Speech to Text

Comprehensive Introduction Record Cafe is a one-stop audio/video processing platform that provides AI video dialog, AI subtitles and AI speech to text services. Functions include recording screen, editing video, converting GIF/audio, etc., and supports cloud storage and sharing. The interface is intuitive and easy to use, and it also supports multi-screen recording and multi-language smart...
2yrs ago
0111.3K
NVIDIA Garak:检测LLM漏洞的开源工具,确保生成式AI的安全性

NVIDIA Garak: Open-source tool to detect LLM vulnerabilities and secure generative AI

Comprehensive Introduction NVIDIA Garak is an open source tool that specializes in detecting vulnerabilities in Large Language Models (LLMs). It checks the model for multiple weaknesses such as illusions, data leakage, hint injection, error message generation, harmful content generation, etc. through static, dynamic and adaptive probing...
2yrs ago
0111.3K
Slidesgo:免费PPT模板下载,辅助AI生成演示文稿,提供教育版工具

Slidesgo: free PPT templates to download, assist AI to generate presentations, provide educational version of the tool

General Introduction Slidesgo is a platform that provides a large number of free and customizable Google Slides and PowerPoint presentation templates. Users can pick templates in different styles or colors based on needs, such as business, education or medical topics. The site offers icons, letter...
2yrs ago
0111.2K
Leffa:高保真模特虚拟试穿与人物姿势调整,Meta开源的可控人物图像生成模型

Leffa: High-fidelity model virtual fitting and character pose adjustment, Meta open source controllable character image generation model

Comprehensive Introduction Leffa is a unified framework for generating controllable character images, enabling precise manipulation of character appearance (e.g., virtual fitting) and pose (e.g., pose transfer). The framework significantly reduces distortion of fine-grained details by directing the target query to focus on the correct reference key in the attention layer, with ...
2yrs ago
0111.2K
PSHuman:生成逼真3D人像模型,使用一张照片生成3D人建模

PSHuman: Generate realistic 3D portrait models, use a photo to generate 3D human modeling

Comprehensive Introduction PSHuman is a single-image 3D portrait reconstruction tool based on multi-view diffusion technology. The tool is capable of generating detailed geometric structures and realistic 3D portrait models from a single photo of a clothed person.PSHuman's core technology includes cross-scale multi-view diffusion, which is capable of...
2yrs ago
0111.2K
佐糖:在线图片处理工具,一键抠图、去水印、照片修复、人像编辑

Zosugar: online photo processing tools, one-click keying, watermark removal, photo restoration, portrait editing

Comprehensive Introduction ZuoSugar (PicWish) is an intelligent AI image processing platform, providing a wealth of online photo editing tools, supporting the use of all platforms. Users can easily complete one-click keying, watermark removal, blurry photos become clear, lossless zoom, image cropping, image compression and black and white photo...
2yrs ago
0111.2K
MegaTTS3:合成中英文语音的轻量模型

MegaTTS3: A Lightweight Model for Synthesizing Chinese and English Speech

Comprehensive Introduction MegaTTS3 is an open source speech synthesis tool developed by ByteDance in cooperation with Zhejiang University, focusing on generating high-quality Chinese and English speech. Its core model is only 0.45B parameters , lightweight and efficient , support for mixed Chinese and English speech generation and speech cloning . The project is hosted on ...
1yrs ago
0111K
RAG Web UI:构建智能文档问答系统,简单构建私有Web端知识库

RAG Web UI: Building an Intelligent Documentation Q&A System and Simply Building a Private Web-Side Knowledge Base

Comprehensive Introduction RAG Web UI is an intelligent dialog system based on RAG (Retrieval Augmented Generation) technology. It helps organizations and individuals build intelligent Q&A systems based on their own knowledge base. By combining document retrieval and large language modeling, RAG Web UI provides accurate and reliable...
2yrs ago
0111K
WeaveFox:前端智能研发平台,能够根据设计图直接生成源代码

WeaveFox: a front-end intelligence development platform that generates source code directly from design drawings

Comprehensive Introduction WeaveFox is an AI front-end intelligent R&D platform launched by Ant Group, aiming to improve the efficiency and quality of front-end development through AI technology. The platform is based on Ant's self-developed Bailing multimodal large model, which is able to generate front-end source code directly based on design drawings, and supports multiple clients and technology stacks...
2yrs ago
0110.9K
Awex - 蚂蚁集团开源的高性能权重交换框架

Awex - Ant Group open source high performance weight exchange framework

Awex is the Ant Group open source high performance weight exchange framework, designed for large-scale parameter synchronization in reinforcement learning. It can complete terabytes of parameter exchange in seconds, significantly improving the efficiency of training and inference.Awex has a very fast synchronization performance, in a thousand card cluster, trillion parameter models can be completed within 6 seconds of the full amount of...
10mos ago
0110.8K
NodeRAG:基于异构图的精准信息检索与生成工具

NodeRAG: A Heterogeneous Graph-Based Tool for Accurate Information Retrieval and Generation

A Comprehensive Introduction NodeRAG is an open source Retrieval Augmented Generation (RAG) system hosted on GitHub and developed by Terry-Xu-666. It optimizes information retrieval and generation through heterogeneous graph structures, significantly improving retrieval accuracy and contextual relevance.Nod...
1yrs ago
0110.8K
AutoAgent:通过自然语言快速创建并部署AI智能体的框架

AutoAgent: a framework for rapid creation and deployment of AI intelligences through natural language

General Introduction AutoAgent is an open source AI intelligences framework developed by the Data Intelligence Laboratory of the University of Hong Kong (HKUDS) and hosted on GitHub.It allows users to rapidly create and deploy customized AI intelligences by describing their requirements in purely natural language, without any programming base...
1yrs ago
0110.8K
GeekAI:自部署商业化多功能AI助手,完整接入多模型API运营后台

GeekAI: Self-deployed commercialized multi-functional AI assistant with complete access to multi-model API operation backend

Comprehensive introduction GeekAI is a full set of open source solutions for AI assistants based on AI big language model API implementation. The project comes with an operations management backend , out of the box , integrated with ChatGPT, Azure, ChatGLM, Xunfei Starfire, Wenxin Yiyin and many other p...
2yrs ago
0110.8K
ScrapeGraphAI:一个提示词搞定网页抓取,无需编写规则智能网页内容提取工具

ScrapeGraphAI: A single cue word for web crawling, no need to write rules intelligent web content extraction tools

Comprehensive Introduction ScrapeGraphAI is an innovative Python web crawling library that cleverly combines Large Language Modeling (LLM) and Direct Graph Logic to create crawling pipelines for websites and local documents. The uniqueness of this tool lies in its perfect level of simplicity and power...
2yrs ago
0110.7K
Dream API:oneapi/newapi中转API,针对个人用户提供免费公益API

Dream API: oneapi/newapi transit API, providing free public service API for individual users.

Introduction After recommending many free large model API services in the Chief AI Sharing Circle, I suddenly found an important issue: there are official free small size scales; there are reverse API models; but there has been no free "official conversion" API. The reason why it has not been recommended is that the free "official conversion" API is not available. The reason why I haven't recommended it is that free "official conversion" is not available for large models.
2yrs ago
0110.7K
Galaxy.ai:集成1700+AI工具库的多功能平台,用于了解市场中各类生成式AI工具(付费)

Galaxy.ai: a multifunctional platform integrating 1700+ AI tool libraries for understanding all types of generative AI tools in the market (paid)

Comprehensive Introduction Galaxy.ai is a platform that integrates a wide range of AI tools designed to provide users with comprehensive AI solutions. Whether it's text generation, image processing, video production or speech synthesis, Galaxy.ai is able to satisfy a wide range of user needs. The platform offers...
2yrs ago
0110.7K
Memary:利用知识图谱增强Agent长期记忆的开源项目

Memary: an open-source project to enhance Agent long-term memory using knowledge graphs

General Introduction Memary is an innovative open source project focused on providing long-term memory management solutions for autonomous intelligences. The project helps intelligences break through the limitations of traditional context windows to achieve smarter interaction experiences through knowledge graphs and specialized memory modules.Memary adopts...
2yrs ago
0110.6K
小悟空:字节跳动推出的多功能AI助手,简单易上手的AI助理

Little Wukong: a versatile, easy-to-use AI assistant from ByteDance

Comprehensive introduction "Little Wukong" is a multi-functional AI dialog assistant and personal assistant tool launched by ByteDance. It integrates more than 200 AI tools, covering a wide range of aspects such as creation generation, learning and enhancement, workplace assistance, professional consultation, virtual character dialog, and leisure and entertainment. Little Wukong is designed...
2yrs ago
0110.6K
ChatFree(ChatAnywhere-2):使用GPT API创建的本地Copilot,支持任意窗口中补全对话

ChatFree (ChatAnywhere-2): Native Copilot created using the GPT API to support complementary conversations in any window.

General Introduction ChatFree is an open source project that aims to free users' AI apps from the constraints of browsers to run locally. Created using GPT API, Copilot is designed to support a wide range of office software such as Office, Word, WPS, and more. The project was developed by ...
2yrs ago
0110.6K
Needle:接入私人数据源的AI搜索与工作自动化平台

Needle: an AI search and job automation platform with access to private data sources

General Introduction Needle is an artificial intelligence platform designed for enterprises to enhance their productivity through efficient information search and automated workflows. The platform is capable of connecting various data sources within an organization to provide unified search and data management capabilities. Users can simply...
2yrs ago
0110.4K
Boolpic:免费图片编辑和优化工具,去除背景,添加滤镜和动画,图像压缩和放大

Boolpic: free photo editing and optimization tool, remove background, add filters and animations, image compression and enlargement

General Introduction Boolpic is a free AI-driven image editing tool designed to help users efficiently process and optimize images. The platform offers a variety of powerful features including background removal, image effects and filters, image animation, image compression and resizing, etc.Boolpic's...
2yrs ago
0110.4K
逗哥配音:专注短视频解说、创作的智能配音神器

Teaser Dubbing: Intelligent dubbing tool that focuses on short video narration and creation

Comprehensive Introduction Tease Dubbing is a popular AI dubbing software with over 5 million users. The software utilizes advanced AI intelligent dubbing technology to provide professional and realistic dubbing effects, which is applicable to a variety of scenarios such as short videos, advertisement production, education and training. Teaser Dubbing is committed to providing users with fast...
2yrs ago
0110.2K
Class Companion: K12教师设计的课后作业管理系统,为学生提供AI辅导和作业批改

Class Companion: an after-school homework management system designed by K12 teachers to provide AI tutoring and homework correction for students

General Description Class Companion is an online education platform designed for teachers and students that uses artificial intelligence technology to provide instant feedback and personalized tutoring. The platform supports a wide range of subjects and grade levels, helping teachers save time, improve teaching efficiency, and provide students with more practic...
2yrs ago
0110.2K
Ultravox:实时端到端语音对话的音频多模态大模型,GPT-4o语音交互的开源实现

Ultravox: an audio multimodal macromodel for real-time end-to-end voice dialog, an open source implementation of GPT-4o voice interaction

Comprehensive Introduction Ultravox is an innovative multimodal Large Language Model (LLM) designed for real-time speech processing. Unlike traditional speech recognition systems, Ultravox eliminates the need for a separate Audio Speech Recognition (ASR) stage, and is able to directly convert audio into high-dimensional space in...
2yrs ago
0110.2K
析言GBI(XiYan-SQL):Text-to-SQL智能数据分析,轻松实现ChatBI

Analytics GBI (XiYan-SQL): Text-to-SQL Intelligent Data Analytics for ChatBI with Ease

Comprehensive Introduction Analyzing Words GBI is an intelligent data analysis product based on big models launched by AliCloud Hundred Refine. The product utilizes advanced natural language processing technology to help users query and analyze data through natural language without having to master complex SQL syntax. Analytics GBI supports multiple data sources, including...
2yrs ago
0109.9K
Media.io:多功能在线媒体处理工具,在线视频、音频、图像编辑器

Media.io: Multi-functional online media processing tool, online video, audio, image editor

General Introduction Media.io is a powerful online AI video editing and media file processing platform. It helps users to enhance, convert, compress, etc. videos, audios and pictures. In addition to the basic editing functions, there are also features like video cartoonization, AI song cover generation, audio desc...
1yrs ago
0109.6K
Fish Agent:端到端AI语音克隆助手,实时语音对话助理,Fish Speech衍生项目

Fish Agent: end-to-end AI voice cloning assistant, real-time voice conversation assistant, Fish Speech spin-off project

Comprehensive Introduction Fish Speech Derivative Project Fish Agent is a revolutionary end-to-end AI speech cloning system developed based on the V0.1 3B model architecture. As a fully end-to-end speech clone processing system, its most important feature is the use of innovative speechless...
2yrs ago
0109.4K