以四個空間探索油麻地的生成影像：Video Embedding、Pixel Information、Text Embedding，以及 BEAMS。
Video / Pixel / Text 各有 3D、2D Grid 與 2D Scatter；BEAMS 另有 Keyword 與 Video 分類視圖。
點選節點進入焦點模式：左側放大焦點影片，右側排列四個最相關影片。按 Esc 或點空白處離開。
使用滑鼠探索，或切換 Orbit 自動旋轉模式。
Space first — a space defines what “nearby” means; a layout only changes how that space is projected on screen.
Video Embedding — clips are positioned from CLIP video coordinates. Nearby clips look or feel semantically similar.
Pixel Information — clips are positioned from ten standardized still-frame ImagePlot features. Nearby clips share visual surface properties such as brightness, saturation, hue, edges, and contrast; this is not CLIP similarity.
Text Embedding — keywords live in a separate BGE text-embedding space. Matching-video thumbnails stay in the HUD.
BEAMS — Belief, Everyday life, Arts, Memories, Subjective experience. Keyword is the five-category taxonomy grid; Video places matching thumbs under each keyword.
Layouts — 3D preserves the selected 3D coordinates; 2D Grid packs items into readable cells using the selected space’s 2D projection; 2D Scatter shows that projection directly. Embedding spaces use 3D / Grid / Scatter; BEAMS uses Keyword / Video.
77 ImagePlot dimensions — the full feature sidecar is an analysis artifact. Pixel HUD shows only five readable fields: brightness median, saturation median, mean hue, edge density, and local contrast.
Similarity — white links use the active space’s similarity graph above the Related threshold. Pixel links are feature-space similarity, not semantic similarity.
Provenance — Source is AI or Human. Pipeline is the AI image→video chain when present.
Focus — tap a node to center a HUD-aware hero and show three related nodes from top to bottom on the right. Connector length and white similarity numbers communicate closeness. Tap the center, empty space, or Escape to leave; tap a neighbor to transfer focus.