tandpfun/wardrobe

Your clothes, extracted and organized with gpt-image.

What it solves

Wardrobe simplifies the process of digitizing a personal clothing collection. It automates the extraction of individual garments from photos and organizes them into a local database, allowing users to create a digital wardrobe and generate modeled editorial previews of their clothes.

How it works

The system uses the OpenAI Responses API to detect garments in photos and the OpenAI Images API to create clean product cutouts. It stores all data, including originals and generated images, locally in a data directory. Users can manage their collection via a Web UI or through specialized Codex skills that automate the importing of clothes and the generation of modeled outfit ideas.

Who it’s for

Individuals who want to organize their clothing digitally and experiment with outfit combinations using AI-generated modeled previews.

Highlights

  • Automated Extraction: Detects and cuts out garments from photos automatically.
  • Modelled Previews: Generates editorial-style photos of the clothes being worn by a reference model.
  • Local Storage: Keeps the JSON database and all images stored locally.
  • Agentic Workflow: Includes Codex skills for agents to handle the import and outfit generation process.

Related

  • Project
    Anyesh/wardrowbe

    Self‑hosted web app that photographs your clothes, uses a multimodal LLM (Ollama, OpenAI, etc.) to tag items and generate daily outfit suggestions based on weather and occasion. Docker‑compose (or K8s) deployment, PostgreSQL + Redis backend, Next.js frontend, fully internationalised and privacy‑first.

  • Project
    tryonlabs/opentryon

    An open-source AI toolkit for fashion technology that provides a unified interface for virtual try-on, image/video generation, and multimodal fashion understanding.

  • Project
    earthtojake/text-to-cad

    A library of agent skills that enables AI to generate, inspect, and prepare CAD models and robot-description files for simulation and fabrication.

  • Project
    kadevin/ilab-conjure

    A local-first AI image generation workbench that unifies GPT Image and Gemini, featuring a comprehensive library for reference images, prompt templates, and task history.

  • Project
    zhouxiaoka/autoclip

    An AI-powered video clipping tool that automatically downloads videos from YouTube and Bilibili, analyzes content via LLMs to extract highlights, and generates short-form collections.