Getting started with PixlStash
Nine short clips covering your first import, exporting a training dataset, and driving PixlStash from ComfyUI.
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 a few clicks
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.
Connect your other apps
Create a scoped API token to use PixlStash from other applications. Tokens can be narrowed to specific resources and permissions, so you hand out exactly the access each integration needs.
Search faces from ComfyUI
Use the PixlStash ComfyUI nodes to search your library for pictures matching a face, then pull them straight into your workflow to edit them — no manual exporting in between.
Outpaint PixlStash images
A ready-made ComfyUI node and workflow lets you load an image, outpaint it, extending it beyond its original borders and saving the result back to PixlStash.