tryonlabs/opentryon

Open-source APIs, SDKs, and models for building virtual try-on and fashion AI applications. Generate models, edit garments, create photoshoots, and build personalized fashion experiences.

What it solves

OpenTryOn is an open-source AI toolkit designed for fashion technology. It provides a unified interface to access a wide variety of virtual try-on, image and video generation, and multimodal understanding models, eliminating the need to integrate multiple separate APIs or local model weights separately.

How it works

The toolkit operates as a unified registry of models. It allows users to interact with these models through three primary interfaces: a Command Line Interface (CLI), a Python API, and an MCP (Model Context Protocol) server that exposes models as tools for AI agents like Claude or Cursor.

Who it’s for

This toolkit is built for fashion tech developers, AI researchers, and creators who need to integrate virtual try-on and fashion-specific image/video generation into their applications.

Highlights

  • Comprehensive Model Support: Integrates virtual try-on (VTO) models like FLUX VTO and Google Vertex VTO, as well as image/video generation tools (Sora, Luma, Kling AI).
  • Multimodal Understanding: Includes support for models like Qwen and Kimi for describing outfits and analyzing fashion images.
  • Flexible Deployment: Supports both API-based and local GPU-powered models.
  • Agent-Ready: The MCP server allows AI agents to invoke these fashion-tech tools directly.
  • Research Integration: Includes TryOnDiffusion research code for training and inference.

Related

  • Project
    ParisNeo/lollms-webui

    A unified local web interface for accessing hundreds of LLMs and multimodal AI models for text, image, video, and music generation.

  • Project
    Haervwe/open-webui-tools

    A comprehensive collection of 20+ tools, function pipes, and filters for Open WebUI that adds academic research, multi-modal generation, and autonomous agent capabilities.

  • Project
    OEvortex/llm4free

    A Python toolkit that provides a unified, OpenAI-compatible interface for 40+ free and paid AI models, including text, image, and voice generation.

  • Project
    ostris/ai-toolkit

    An all-in-one training suite for diffusion models that allows users to fine-tune image, video, and audio models on consumer-grade hardware via a GUI or CLI.

  • Project
    openonion/connectonion

    A template-first toolkit for building and deploying production-ready AI agents, providing built-in infrastructure for hosting, debugging, and tool integration.