A head is a tiny classifier trained on the SigLIP embeddings already stored on your images — your positives plus your negatives (rejections). One is built per general/character concept with at least {{ minPositives }} tagged images. Retrain after a tagging session to fold in your latest accepts/rejects; scoring is live, so the rail reflects a retrain on the next image you open.
No heads yet. Tag a handful of images for the concepts you care about, then train — each concept with ≥ {{ minPositives }} tags becomes a head.
| Concept | Cat | +tags | AP | P | R | ⚡ |
|---|---|---|---|---|---|---|
| {{ h.name }} | {{ h.category }} | {{ h.n_pos }} | {{ pct(h.ap) }} | {{ pct(h.precision) }} | {{ pct(h.recall) }} |
|
Graduated heads (⚡, with ≥ {{ autoMinPosInput }} examples) apply their tag on their own where they clear {{ Math.round((autoPrecisionInput || 0) * 100) }}% precision. Every auto-tag is reversible; removing one teaches the head it misfired.
Auto-hide banner chrome from the gallery once a head has
learned it (≥ {{ minPositives }} examples) and clears
{{ Math.round((presentationThresholdInput || 0) * 100) }}% confidence.
(wip and editor screenshot are handled by the
process auto-tagger below.) If a hidden image also looks like real content
(≥ {{ Math.round((presentationConflictInput || 0) * 100) }}% on a content
tag), it's flagged for review instead of buried. Every auto-hide is reversible.
Auto-tag wip and editor screenshot process art
once a head has learned them (≥ {{ minPositives }} examples) and clears
{{ Math.round((processThresholdInput || 0) * 100) }}% confidence. These stay
visible in the gallery — the tag just keeps them out of
training and the Explore rabbit-hole. Off by default. If a tagged image also
looks like real content (≥ {{ Math.round((processConflictInput || 0) * 100) }}%
on a content tag), it's flagged for review. Learns only from your titles +
manual tags, never its own guesses — so it can't run away. Every tag reversible.
| Concept | applied | misfires | rate | missed |
|---|---|---|---|---|
| {{ c.name }} | {{ c.n_auto_applied }} | {{ c.n_misfires }} | {{ ratePct(c.misfire_rate) }} | {{ c.n_underfires }} |