Standard: generate 3 batches per group (54 images total) for ArrivalAll.
This commit is contained in:
@@ -213,13 +213,13 @@ This doubles the C options without extending A/B, focusing extra attempts where
|
||||
|
||||
**Issue:** ArrivalAll composites often fail to include all courtesans (or duplicate some). Selection becomes a two-stage filter: (1) correct count + all present, then (2) composition quality.
|
||||
|
||||
**Solution:** Generate **2-3 separate batches** (different runhexes) for each ArrivalAll set to increase odds of usable images.
|
||||
**Solution:** Generate **three separate batches** (different runhexes) for each ArrivalAll set to increase odds of usable images.
|
||||
|
||||
**Generation:**
|
||||
- **ArrivalAllMen_A1-C6** (batch 1, runhex X)
|
||||
- **ArrivalAllMen_A1-C6** (batch 2, runhex Y)
|
||||
- **ArrivalAllMen_A1-C6** (batch 3, runhex Z) ← optional third batch
|
||||
- **ArrivalAllMen_A1-C6** (batch 3, runhex Z)
|
||||
|
||||
(Same for Ladies and Singles.)
|
||||
|
||||
This gives 36-54 images per group instead of 18, dramatically improving the chance of getting keepers with correct count and good composition.
|
||||
This gives **54 images per group** (3 batches × 18) instead of 18, dramatically improving the chance of getting keepers with correct count and good composition.
|
||||
|
||||
@@ -403,3 +403,6 @@ Missing ArrivalAll composites will cause packaging to fail or produce incomplete
|
||||
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.**
|
||||
|
||||
**Multi-batch generation (standard):**
|
||||
Generate **three separate batches** (different runhexes) for each ArrivalAll group (54 images per group total). Composites often fail to include all courtesans or duplicate some; three batches dramatically improve odds of finding keepers with correct count and good composition.
|
||||
|
||||
Reference in New Issue
Block a user