backend/app/models/tag.py

@@ -43,6 +43,12 @@ class TagKind(StrEnum):
     # to keep historic tag rows queryable.
 
 
+# The seeded system tags (migration 0075). PRESENTATION tags additionally
+# hide from whole-image similarity results — they cluster on UI chrome, not
+# content. `wip` is real art: only the training pipelines exclude it.
+SYSTEM_TAG_NAMES = ("wip", "banner", "editor screenshot")
+PRESENTATION_SYSTEM_TAGS = ("banner", "editor screenshot")
+
 image_tag = Table(
     "image_tag",
     Base.metadata,

backend/app/services/gallery_service.py

@@ -23,7 +23,7 @@ from sqlalchemy.ext.asyncio import AsyncSession
 from sqlalchemy.orm import aliased
 
 from ..models import Artist, ImageProvenance, ImageRecord, Post, Source, Tag
-from ..models.tag import image_tag
+from ..models.tag import PRESENTATION_SYSTEM_TAGS, image_tag
 from .pagination import decode_cursor, encode_cursor
 from .tag_query import (
     fandom_join_alias,
@@ -693,9 +693,23 @@ class GalleryService:
         eff = _effective_date_col()
         stmt = select(ImageRecord, Post.post_date, eff.label("eff"))
         stmt = _outer_join_primary_post(stmt)
+        # Presentation images (banner / editor-screenshot system tags, #128)
+        # cluster on UI chrome rather than content, so near any one of them
+        # they'd fill the grid. Excluded from CANDIDATES only — the anchor
+        # itself may be a banner, and `wip` stays surfaced (real art; only
+        # the training pipelines exclude it).
+        presentation = (
+            select(image_tag.c.image_record_id)
+            .join(Tag, Tag.id == image_tag.c.tag_id)
+            .where(
+                Tag.is_system.is_(True),
+                Tag.name.in_(PRESENTATION_SYSTEM_TAGS),
+            )
+        )
         stmt = stmt.where(
             ImageRecord.siglip_embedding.is_not(None),
             ImageRecord.id != image_id,
+            ImageRecord.id.not_in(presentation),
         )
         stmt = _apply_scope(
             stmt, tag_ids=tag_ids, post_id=None,

tests/test_gallery_similar.py

@@ -4,6 +4,7 @@ precomputed SigLIP image embeddings. No query-time ML inference."""
 from datetime import UTC, datetime, timedelta
 
 import pytest
+from sqlalchemy import select
 
 from backend.app.models import ImageRecord, Tag, TagKind
 from backend.app.models.tag import image_tag
@@ -72,6 +73,31 @@ async def test_similar_missing_source_returns_none(db):
     assert await svc.similar(99999, limit=10) is None
 
 
+@pytest.mark.asyncio
+async def test_similar_excludes_presentation_tagged_images(db):
+    """banner / editor-screenshot system tags (#128) hide from similar
+    RESULTS — they cluster on UI chrome, not content. A banner anchor still
+    gets results; `wip`-tagged images stay in (real art)."""
+    src = await _img(db, 1, _vec(1, 0))
+    bannered = await _img(db, 2, _vec(1, 0.02))   # nearest, but a banner
+    wipped = await _img(db, 3, _vec(1, 0.3))
+    plain = await _img(db, 4, _vec(1, 0.6))
+    banner_tag = (await db.execute(select(Tag).where(
+        Tag.is_system.is_(True), Tag.name == "banner"))).scalar_one()
+    wip_tag = (await db.execute(select(Tag).where(
+        Tag.is_system.is_(True), Tag.name == "wip"))).scalar_one()
+    await db.execute(image_tag.insert().values(
+        image_record_id=bannered.id, tag_id=banner_tag.id, source="manual"))
+    await db.execute(image_tag.insert().values(
+        image_record_id=wipped.id, tag_id=wip_tag.id, source="manual"))
+    svc = GalleryService(db)
+    res = await svc.similar(src.id, limit=10)
+    assert [i.id for i in res] == [wipped.id, plain.id]
+    # A presentation-tagged ANCHOR still answers — only candidates hide.
+    res_from_banner = await svc.similar(bannered.id, limit=10)
+    assert {i.id for i in res_from_banner} == {src.id, wipped.id, plain.id}
+
+
 @pytest.mark.asyncio
 async def test_similar_composes_with_tag_filter(db):
     src = await _img(db, 1, _vec(1, 0))