A modern, web-based client for Google's Gemini 3 Pro model, this project provides an intuitive workbench for AI image generation. It targets artists, designers, and power users seeking an efficient, feature-rich interface for creating high-resolution images, enhancing creative workflows with batch processing and contextual memory.

How It Works

This project utilizes native JavaScript, CSS3, and HTML5 to create a client-side interface for Gemini 3 Pro. It employs IndexedDB for persistent local storage of conversation history and the File System Access API for direct, local saving of generated images, avoiding browser storage limitations. Key architectural decisions include support for concurrent batch image generation and high-resolution (up to 4K) rendering, aiming to significantly boost creative efficiency and user experience.

Quick Start & Requirements

• Primary install/run command: Clone the repository (git clone https://github.com/Tansuo2021/gemini-3-pro-image-preview.git) and start a local HTTP server (e.g., python -m http.server 8000).
• Non-default prerequisites: A modern browser (Chrome 86+, Edge 86+, Firefox, Safari) and a Gemini API Key or a compatible OpenAI API Key are required.
• Estimated setup time: Minimal, primarily involving cloning and server startup, followed by API key configuration.
• Relevant pages: GitHub repository: https://github.com/Tansuo2021/gemini-3-pro-image-preview

Highlighted Details

• Supports multiple resolutions (1K, 2K, 4K) and 11 aspect ratios, with reference image upload and batch generation.
• Integrated tools include an XHS Inspiration Lab for content creation, Banana Prompt for prompt lookup, a meme generator, and an image slicer for nine-grid layouts.
• Features API channel management supporting multiple providers (Gemini native, OpenAI compatible) with automatic load balancing.
• Conversation context memory is configurable (3, 5, 10, or 20 history items) for continuous AI-assisted creation.
• Automatic local saving of generated images via the File System Access API (Chrome/Edge 86+).

Maintenance & Community

This project is maintained by Tansuo2021. No specific community channels (e.g., Discord, Slack) or details on sponsorships or partnerships are provided in the README.

Licensing & Compatibility

The project is licensed under the MIT License, which is permissive for commercial use and integration with closed-source projects.

Limitations & Caveats

The automatic local image saving feature relies on the File System Access API, which is only supported in Chrome and Edge (version 86+); Firefox and Safari do not support this functionality. The core functionality is dependent on the availability and configuration of external API keys.