1.6 KiB
1.6 KiB
Three-up boards: photo | concept | capture
Each strip lines up the three image sources for one venue state so the evidence
chain stays visible: the licensed real photo is the evidence, the generated
frame is the proposal (geometry anchored on the photo; see the
concepts board and each frame's .refgen.json), and
the game capture is the proof of the current build. Where the concept and
the photo disagree, the photo wins for shape; the capture shows the gap the
facade-realism work has to close.
Composed with tools/three_up.py compose (labels baked in; the photo panel's
attribution lives in the caption and the refs sidecars).
| Board | Caption |
|---|---|
 |
El Capitan facade, day. Photo: CC BY 2.0, woo, 2009 via refs/hollywood. Concept: photo-anchored generation. Capture: current build with the ashlar limestone field (limestone_ashlar, anchored on the same photo). |
 |
El Capitan block, night. Photo: CC BY-SA 3.0 (reviewed; redistribution only, no derived assets) via refs/hollywood. Concept: photo-anchored night restage. Capture: current build. |
 |
Joke Shop frontage, day. Photo: local-only research frame (tmp/research/comedy-store, gitignored). Concept: photo-anchored (gemini + gpt). Capture: current build with the dark_stucco wall tile. |
