📚SparkAi Free Public Version

🚀Feature Introduction

• Supports user registration and login: WeChat QR code, email, and mobile number.
• AI large model support: Integrates with OpenAI GPT-3.5/GPT-4.0 models and some domestic AI models (Baidu Wenxin Yiyan, Microsoft Azure, Alibaba Cloud Tongyi Qianwen, Tsinghua ChatGLM, iFlytek Spark).
• DallE Painting: Supports DallE2 and DallE3.
• AI Painting: MJ text-to-image, image-to-image, and local editing/redrawing.
• TTS Voice Recognition: Whisper & TTS for voice recognition dialogue.
• AI Agents: Custom preset prompt applications and support for custom AI agent applications.
• ...and more

🛠️Installation and Deployment

• Click here for the Detailed Graphic Installation and Deployment Tutorial
• Install Pagoda Panel (version 9.2.0 or above). Go to the official Pagoda Panel website and download the official version script for installation.
• After installation, log in to the Pagoda Panel, click on Docker in the menu bar. If it's your first time, you will be prompted to install the Docker service. Click "Install Now" and follow the prompts.
• Once installation is complete, search for SparkAi in the app store, find SparkAI-ChatGPT-AiWeb, click install, and configure the basic options to complete the installation.

🌟Commercial License Version (Additional Supported Features)

• Membership Mall System: Provides three currency types: regular model points, advanced model points, and painting points. Supports custom deduction modes and quotas for various products. Supports custom model fee deduction types and multiple billing methods: time-limited, unlimited, and custom combo packages (free / points (per use) billing).
• Payment System: Supports official WeChat Pay, EasyPay, CodePay, HupiJiao Pay, etc. Supports synchronous order status checks, order search, and management.
• Distribution System: Supports A + B distribution model. The backend allows for custom commission rates and individual user settings. Supports setting withdrawal thresholds and multiple withdrawal methods (Alipay, WeChat, bank card, etc.).
• Visitor System: Allows partial access without logging in, enabling a guest mode to experience the site's features.
• Full Model Support: Supports OpenAI's official API and any chat-format relay system for custom model integration (i.e., supports all OpenAI models, third-party large models, and all domestic models).
• Fully Custom Model Integration: All models use the OpenAI input format. When OpenAI releases a new language model, it can be added immediately in the backend without requiring system updates. This also applies to third-party model relay systems, ensuring quick access to the latest models from OpenAI, third parties, and domestic providers. Dialogue models can be custom-categorized, named, sorted, and have some functions customized.
• Professional Painting System (Dynamic Full-Function Midjourney Painting): Text-to-image, image-to-image, image blending, consistent character/style reference images, AI face swapping, and image mixing.
• AI Video Generation: Supports text-to-video/image-to-video (Pika AI video).
• GPTs Agent System: Supports integration of all GPTs applications from the official OpenAI store.
• New Plugin System: A new plugin system with multiple built-in plugins that can be enabled through configuration. Supports image recognition, PDF document analysis, dialogue-based Midjourney, SD painting, and plugin integration with FastGPT knowledge bases.
• TTS Voice Dialogue: Supports voice mode dialogue, automatic voice reply playback, six different voice options, and real-time reading without taking up storage space.
• Dynamic Menu System: Customize menus by enabling/disabling, adding new ones, setting custom icons, and menu types. Supports embedding third-party sites and separate settings for mobile and PC.
• Networking Mode: Allows the model to be extended to search and summarize real-time web content.
• Creator Center: Displays creator information for artworks (more features to be developed).
• Major UI Refactoring: The UI has been completely redesigned and updated.
• ...and more