selfhost.directory

The index of self-hostable projects — ranked, categorized and served with live updates.
Own your data and stop giving it to big tech.

GitHub
LLMII (ImageIndexer) logo

Self-host LLMII (ImageIndexer)

Local AI image tagger writing metadata to photo files

BetaOpen SourceGPL-3.0
Updated2 months ago
LanguagePython
Setup difficultyModerate
Stars
397
CPU
Discrete GPU recommended (Apple Metal, Nvidia CUDA, or AMD Vulkan)
Requires
Exiftool, Python
Install with Linux
LLMII GUI showing image processing interface

What is LLMII (ImageIndexer)?

LLMII is a cross-platform desktop tool for photographers who want AI-powered image tagging without cloud uploads. It bundles KoboldCPP as a local inference backend, downloads a vision-language model on first run, and uses ExifTool to embed generated captions and keywords into each image's metadata or an XMP sidecar. The GUI lets you choose one-step or two-step processing, adjust sampler settings, skip folders, reprocess failures, and review results in an image viewer. All processing happens locally on Windows, macOS, or Linux; a discrete GPU with 8 GB VRAM is recommended for usable speed. Licensed GPL-3.0 with no paid tiers.

Should you self-host LLMII (ImageIndexer)?

LLMII (ImageIndexer) scores 43/100 on selfhost.directory (how scoring works) and ranks #35 of 41 in Photo Management. It has 397 GitHub stars.

There was no stable release in the past 12 months, so check the repository's recent activity before you rely on it.

Setup is moderate: expect some configuration beyond a single command. It is GPL-3.0-licensed and written mostly in Python.

Its closest alternative on selfhost.directory is Ente (81/100, 29 693 stars). It scores higher overall, so compare the two before you pick. See LLMII (ImageIndexer) vs Ente side by side.

Features

  • Automatic model download
  • Cross-platform
  • Fully local processing
  • GPU Acceleration
  • Graphical user interface
  • Highly Configurable
  • Image review viewer
  • Local AI image analysis
  • Metadata Embedding
  • Multi-format Support
  • Multiple model support
  • One or two-step processing
  • Pretend mode
  • Resume capability
  • Sidecar file option

LLMII (ImageIndexer) README

How to install LLMII (ImageIndexer)

Install LLMII (ImageIndexer) with Linux

  1. Clone the repository or download and extract the ZIP file
  2. Install Python 3.8+ (e.g., sudo apt-get install python3 python3-pip)
  3. Install ExifTool (e.g., sudo apt-get install libimage-exiftool-perl)
  4. Run ./llmii.sh
  5. If KoboldCPP fails to run, make the binary executable:

chmod +x ./resources/koboldcpp-linux-x64

Tested on Ubuntu; other distros should work with equivalent packages

More in Image Processing

Rate this project

Click to rate — no account needed.

0 comments

Posting as guest
Loading comments…