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

    A self-hosted wardrobe management app that uses AI to automatically tag clothing from photos and provide daily outfit recommendations based on weather and occasion.

  • Project
    tryonlabs/opentryon

    OpenTryOn (opentryon) is an open‑source Python toolkit that aggregates dozens of fashion‑focused AI models (virtual try‑on, image/video generation, multimodal understanding, background removal, etc.) and exposes them via a unified CLI, a Python library, an MCP server, and a Next.js web UI (TryOn Studio). It supports both cloud APIs and local GPU models, includes research diffusion code, and is documented on a dedicated site.

  • Project
    earthtojake/text-to-cad

    text‑to‑cad is a plugin and skill set that lets LLM agents generate, edit, view and export 3‑D CAD models locally, supporting formats like STEP, STL, GLB and providing manufacturing checks, robot description files, and G‑code slicing. It works with Claude, Gemini, Codex, Cursor, Grok and any agent that can use the `skills.sh` framework.

  • Project
    kadevin/ilab-conjure

    A local-first AI image generation workbench that unifies GPT Image and Gemini into a single interface with prompt templates, asset libraries, and a built-in image editor.

  • Project
    zhouxiaoka/autoclip

    An open-source tool that automatically converts long videos into short-form clips for social media, generating the video, cover, and captions using AI.