Getting started with PixlStash
Six short clips covering your first import to exporting a training dataset.
Drag, drop, done
Import single images, whole folders, ZIP or TAR archives in one go. PixlStash deduplicates and starts tagging your library the moment files land.
Put names to faces
PixlStash detects faces for every picture. Assign pictures to a person and PixlStash will build up a profile for that person letting you sort by likeness to find all the other pictures of them.
Bulk-tag in seconds
The PixlStash tagger runs automatically. Review AI predictions, accept or reject with a click, and apply new tags across any selection without leaving the grid.
Get rid of the rubbish
A composite quality score weighs aesthetics and anomaly tags to help you clear the worst images. Filter and sort by smart score to find the real duds.
Find anything by description
CLIP-powered semantic search understands natural language. Type "walking in the park" or "close-up smiling" and get relevant results immediately — no exact tag match needed.
Dataset-ready in one click
Export the current view as a ZIP of images paired with tag or description captions. Choose full images or face crops, pick caption mode, and hand off a clean dataset to your trainer.