AI Personal Learning
and practical guidance
Beanbag Marscode1
Total 914 articles

Tags: ai open source projects Page 44

simple-one-api: one-click integration of multiple free big model APIs, unified external OpenAI interfaces

Comprehensive Introduction simple-one-api is an open source project designed to simplify the integration of multiple big model APIs. It supports the Thousand Sails Big Model Platform, Xunfei Starfire Big Model, Tencent Mixed Element, and MiniMax and Deep-Seek models compatible with the OpenAI interface. The project requires only an executable file , configure...

VoAPI:高颜值的AI模型转发接口管理系统,官网每日提供免费API额度-首席AI分享圈

VoAPI: High-value AI model forwarding interface management system, the official website provides free API quota on a daily basis

Comprehensive Introduction VoAPI is a new high-color and high-performance AI model interface management and distribution system, which is mainly used for personal or enterprise internal management and distribution channels. Developed based on NewAPI, the system provides rich functional modules and optimized user interface, aiming to improve user experience and operation efficiency...

StreamingT2V:从文本到长视频的动态且可扩展的生成技术-首席AI分享圈

StreamingT2V: A Dynamic and Scalable Generation Technique from Text to Long Video

Comprehensive Introduction StreamingT2V is a public project developed by the Picsart AI research team focused on generating coherent, dynamic and scalable long videos based on textual descriptions. This technology uses an advanced autoregressive approach that guarantees temporal consistency of the video, closely corresponds to the description text, and maintains high frame quality...

Retrieval based Voice Conversion WebUI:基于检索的语音转换框架|模拟真人歌声-首席AI分享圈

Retrieval based Voice Conversion WebUI: A Framework for Retrieval-based Voice Conversion | Simulating Real-life Singing Voices

Comprehensive Introduction Retrieval based Voice Conversion WebUI is a simple and easy-to-use VITS-based voice conversion framework, which can realize voice conversion between any speakers, including song covers and real-time voice changing. It features low latency, excellent voice changing effect, small amount of data training...

VoiceCraft:开源零样本语音克隆与文本转语音工具-首席AI分享圈

VoiceCraft: open source zero-sample speech cloning and text-to-speech tool

Comprehensive Introduction VoiceCraft is an open source speech editing and zero-sample speech synthesis tool based on the Neural Codec language model. It employs an innovative coded sequence generation method that enables insertion, deletion and replacement operations on existing speech sequences to generate natural and coherent edited speech. At the same time, ...

CoAI.Dev (Chat Nio):AI聚合应用 一站式 B/C 端解决方案,支持弹性计费和订阅计划模式-首席AI分享圈

CoAI.Dev (Chat Nio): One-stop B/C solution for AI aggregation apps with flexible billing and subscription plan model support

General Introduction CoAI.Dev (formerly Chat Nio) is a chat platform that integrates multiple AI models and supports distributed streaming, image generation, cross-device conversation synchronization and sharing. It implements a subscription and Token billing system, Key transit service and multi-model support, and also includes connected search and AI...

ChatOllama:基于Nuxt 3和Ollama的本地实时聊天应用UI-首席AI分享圈

ChatOllama: Native real-time chat application UI based on Nuxt 3 and Ollama

Comprehensive introduction ChatOllama is an open source online chat application project based on a large language model (LLM) , supporting numerous language models and knowledge base management. Users can use the platform for model management ( list display , download , delete ) , chat with the model and other functions . The project utilizes the Nuxt 3 framework ...

MinerU:PDF文档提取转换为多模态Markdown格式,支持电子书OCR扫描-首席AI分享圈

MinerU: PDF document extraction and conversion to multimodal Markdown format, support e-book OCR scanning

Comprehensive Introduction MinerU is an open source data extraction tool developed by the OpenDataLab team at the Shanghai Artificial Intelligence Laboratory, focusing on efficiently extracting content from complex PDF documents, web pages, and eBooks. It can convert multimodal PDF documents containing images, formulas, tables and other elements into easy-to-analyze M...

Tap4 AI WebUI:开源轻量级AI工具导航项目-首席AI分享圈

Tap4 AI WebUI: open source lightweight AI tool navigation project

Comprehensive introduction Tap4 AI WebUI is an open source lightweight AI tool navigation website project , designed to help users easily build their own AI tool catalog . The project uses Next.js and Supabase technology stack , support for multi- language SEO optimization , to provide AI tools classification filtering , search and detailed display functions ...

CodeFormer:图像与视频面部复原,老照片修复,提供一键部署版-首席AI分享圈

CodeFormer: image and video facial restoration, old photo restoration, offers one-click deployment version

CodeFormer General Introduction CodeFormer is a codebase for robust blind face repair, developed by a team of researchers at S-Lab, Nanyang Technological University and presented at NeurIPS 2022. The project utilizes the Codebook Lookup Transformer technology, which aims to improve...

en_USEnglish