Summary

Xiaoye AI is an open-source, multimodal AI content creation platform and unified API gateway. It aggregates over 30 AI model providers, including Google Gemini and Volcengine, aiming for enhanced stability and competitive pricing. This platform targets developers and users needing to integrate diverse AI capabilities for image and video generation, simplifying complex multi-model workflows.

How It Works

The system acts as an API intermediary, abstracting AI service provider complexities. It uses a Go backend (Gin, GORM) for API handling and JWT authentication, with a Vue 3 frontend. Key architectural choices include dedicated adapters for AI providers, Alibaba Cloud OSS for storage, and MySQL persistence. This modular design facilitates easy integration of new AI models.

Quick Start & Requirements

• Prerequisites: Go 1.21+, Node.js 18+, MySQL 8.0+, Alibaba Cloud OSS bucket, AI provider API keys.
• Installation: Clone, configure backend (.env), run go run main.go (backend) and npm run dev (frontend).
• Links: Demo: https://muse-ai.nlink.vip/. Site: https://ai.xiaoye.io/.

Highlighted Details

• Multimodal Generation: Supports AI image (up to 4K, reference images) and video (text/image-to-video) generation via models like Gemini and Seedance.
• Prompt Engineering: Includes AI prompt rewriting (DeepSeek) and reverse prompting.
• E-commerce: Template-based batch generation for product images.
• Community & User Features: Integrates points system, email/OAuth accounts, and an "Inspiration Plaza" for content sharing.

Maintenance & Community

Acknowledges support from the "Linux.do community," indicating community-driven development. Future features, like a visual canvas editor, are planned, suggesting ongoing development. No specific maintainer or sponsorship details are provided.

Licensing & Compatibility

Licensed under AGPL-3.0. This strong copyleft license requires that any modified version deployed as a network service must make its source code publicly available to users, imposing significant restrictions on commercial use within proprietary applications.

Limitations & Caveats

The platform is under active development; features like a visual canvas editor are future additions. The AGPL-3.0 license presents a substantial adoption barrier for commercial entities requiring proprietary modifications or closed-source deployment. Setup requires managing multiple external services (database, object storage, AI APIs).