LuqP2/Image-MetaHub

Local-first AI image organizer and generative media library manager for ComfyUI, A1111, InvokeAI & more. Search huge output folders by prompt, model, LoRA, metadata or visual similarity.

What it solves

Image MetaHub is a local-first media organizer designed for users who have large libraries of AI-generated images, videos, and audio files. It solves the problem of managing thousands of generations across different tools (like ComfyUI, Automatic1111, and InvokeAI) without needing to move files or upload them to a cloud service, while preserving the technical metadata (prompts, models, seeds) used to create them.

How it works

The app scans local folders in place and extracts embedded generation metadata from various AI tools. It caches this data for fast searching and filtering. It also includes an optional on-device model for local visual similarity search, allowing users to find related images even when metadata is missing. For advanced users, it integrates directly with running instances of ComfyUI and Automatic1111 to send workflows and parameters back for regeneration.

Who it’s for

AI artists and power users who generate large volumes of media and need a professional curation tool to track production history, organize assets via tags and ratings, and find specific generations based on technical parameters.

Highlights

  • Multi-Tool Metadata Parsing: Supports a wide range of generators including ComfyUI, Automatic1111, InvokeAI, Midjourney, and DALL-E.
  • Local Visual Search: Find similar images using an on-device model without outbound telemetry.
  • Deep ComfyUI Integration: Send compatible generations back into ComfyUI as working workflows and track generation progress in real-time.
  • Advanced Curation: Features include prompt clustering, TF-IDF auto-tagging, image lineage detection (for img2img/inpaint), and a built-in image editor.
  • Comparison Tools: Side-by-side comparison of up to 4 images with synchronized zoom, pan, and metadata diffing.
  • Analytics Explorer: Tracks generation performance, VRAM usage, and timing for images saved via the MetaHub Save Node.

Related

  • Project
    zanllp/infinite-image-browsing

    A high-performance image browser and manager for AI-generated media that provides metadata-based search, semantic clustering, and support for multiple AI generation platforms.

  • Project
    MindWorkAI/AI-Studio

    MindWork AI Studio is a free cross‑platform desktop app that lets users chat with many LLM providers (cloud or local), use pre‑built assistants, run tool‑enabled RAG, and manage settings centrally for enterprises. It runs on low‑cost hardware, supports voice transcription, and is released under a functional source license that becomes MIT after two years.

  • Project
    github/app

    The GitHub Copilot app is a desktop client that lets you run Copilot‑powered AI agents in isolated git worktrees or cloud environments, manage issues/PRs across repos, and automate prompts. It provides visual “canvases” for agent output, parallel sessions, and an “Agent Merge” flow to auto‑merge PRs after checks. Installable on Windows, macOS, and Linux; requires a Copilot plan or your own model key.

  • Project
    RoseKhlifa/Image-Studio

    Image Studio is an open‑source, cross‑platform desktop client (Windows/macOS/Linux/Android) built with Go + React (Wails) that lets you generate and edit images via any OpenAI‑compatible API. It supports streaming responses over SSE or WebSocket to avoid proxy timeouts, works with the standard Images API, offers batch img2img, custom aspect ratios, and integrates with a prompt‑import helper. Configuration is manual (base URL, API key, model ID) and the project is AGPL‑v3 licensed.

  • Project
    SegFault42/HeliosGen

    HeliosGen is an open‑source desktop app (macOS released, Windows/Linux pending) that provides a visual, node‑based canvas for building and running AI image and video generation pipelines. It works locally, sending requests to the kie.ai API (or optionally a Codex CLI) and stores all data on the user’s machine. Features include multi‑model support, reference images, parallel/sequential execution, and a real‑time history. The app is built with Tauri 2 (Rust) and a Next.js/React front‑end, uses SQLite for local persistence, and is MIT‑licensed.