Lock composite-reference method for ArrivalAll (validated 2026-03-24)
BetterLeaks / scan (push) Successful in 54s
BetterLeaks / scan (push) Successful in 54s
Method: create 16:9 grid composite from Dressed images (pairs first for efficiency, then singles). Use composite as reference for /images/edits. Text-only multi-person prompts fail (invent random faces). Composite-reference produces proper face fidelity.
This commit is contained in:
@@ -359,3 +359,47 @@ Before packaging, verify:
|
||||
- **If tier has both genders:** ArrivalAllMen_A1-C6 and ArrivalAllLadies_A1-C6 also exist
|
||||
|
||||
Missing ArrivalAll composites will cause packaging to fail or produce incomplete tier-root overview images.
|
||||
|
||||
---
|
||||
|
||||
## ArrivalAll Composite-Reference Method (VALIDATED)
|
||||
|
||||
**Problem:** Text-only prompts with multiple names produce random invented faces.
|
||||
**Solution:** Create a **16:9 grid composite** from Dressed images, use as reference for /images/edits.
|
||||
|
||||
### Composite Building Strategy
|
||||
|
||||
**Optimize with pairs/triples first:**
|
||||
1. Select **pair/triple Dressed images** that collectively cover as many singles as possible
|
||||
2. Add **orphan singles** (not in any pair/triple) as individual Dressed images
|
||||
3. **Result:** Fewer total images while covering all courtesans
|
||||
|
||||
**Example (Comfortable tier):**
|
||||
- 3 pair images (Eira/Milla, Kara/Nora, Liv/Freya) = 6 ladies
|
||||
- 2 male singles (Cillian, Eiríkur)
|
||||
- **Total:** 5 reference images covering 8 people
|
||||
|
||||
### Generation Steps
|
||||
|
||||
1. **Create three grid composites** (using PIL/Pillow):
|
||||
- comfortable_men_dressed_grid_16x9.jpg
|
||||
- comfortable_ladies_dressed_grid_16x9.jpg
|
||||
- comfortable_all_singles_dressed_grid_16x9.jpg
|
||||
|
||||
2. **Generate ArrivalAll sets** using /images/edits:
|
||||
- ArrivalAllMen_A1-C6 (18 images, using men grid)
|
||||
- ArrivalAllLadies_A1-C6 (18 images, using ladies grid)
|
||||
- ArrivalAllSingles_A1-C6 (18 images, using all grid)
|
||||
|
||||
3. **Human selection:** Pick best per letter (A/B/C, with/without stairs)
|
||||
|
||||
4. **Package as tier-root finals:**
|
||||
- Arrival (Men, Lobby type A).jpg
|
||||
- Arrival (Ladies, Lobby type B, with stairs).jpg
|
||||
- Arrival (All, Lobby type C).jpg
|
||||
|
||||
### Validated Result
|
||||
|
||||
Composite-reference method produces **proper face fidelity** for group overview images. Text-only multi-person prompts fail catastrophically (invent random faces).
|
||||
|
||||
**This is the standard method for all future ArrivalAll generation.**
|
||||
|
||||
Reference in New Issue
Block a user