Wardrobe is an AI-powered system designed to automatically extract, organize, and style personal clothing items from user photos. It targets individuals seeking to digitize and manage their wardrobe, offering automated cataloging and outfit generation capabilities. The primary benefit is a streamlined process for creating a digital fashion inventory and exploring new outfit combinations.

How It Works

The project leverages OpenAI's APIs for its core functionality. It uses the OpenAI Responses API to detect individual garments within uploaded photos and the OpenAI Images API to generate clean, cutout product images. Optionally, it can create modeled editorial previews. All processed data, including original images, generated assets, and a JSON database, is stored locally within the data/ directory, ensuring user control over their information. The system also includes integrated Codex skills for both importing clothes and generating styled outfits.

Quick Start & Requirements

To get started, clone the repository (git clone https://github.com/tandpfun/wardrobe.git), navigate into the directory (cd wardrobe), and install dependencies (npm install). Before running, copy the environment example (cp .env.example .env) and configure your OPENAI_API_KEY within the .env file. A reference PNG photo of yourself is also required at data/model-reference.png. Run the development server with npm run dev. Prerequisites include Node.js 22+ and an active OpenAI API key. The web UI is accessible at localhost:5173.

Highlighted Details

• Features two integrated Codex skills: one for importing clothes and generating modeled photos, and another for creating styled outfits and lookbooks.
• Utilizes AI for garment detection, product cutout extraction, and optional modeled previews.
• Maintains all data, including originals, jobs, generated images, and the database, locally in the data/ directory.
• Web UI supports drag-and-drop, editing, review, regeneration, and approval workflows.

Maintenance & Community

No specific details regarding maintainers, community channels (like Discord/Slack), or roadmap were found in the provided README.

Licensing & Compatibility

The project is released under the MIT License, which is permissive and generally allows for commercial use and integration into closed-source projects.

Limitations & Caveats

The importer functionality remains disabled until an OPENAI_API_KEY is provided in the .env file and a data/model-reference.png is present. The system's core operations are dependent on external OpenAI API services, which may incur costs and are subject to OpenAI's terms of service.