Extract caption naturalizer policy

2026-06-27 01:38:00 +02:00
parent 5efa073bfb
commit 36ce394462
5 changed files with 163 additions and 61 deletions
@@ -302,10 +302,13 @@ Keep here:

 - natural sentence caption assembly;
 - training-caption trigger behavior;
- style-tail policy.
- metadata-family action labels from `action_family` and `position_family`.
+- style-tail policy from `caption_policy.py`.
+- metadata-family action labels from `action_family` and `position_family` via
+  `caption_policy.py`.
 - shared formatter input parsing from `formatter_input.py`.
 - shared cast descriptor parsing and label replacement from `krea_cast.py`.
+- caption detail-level/style-policy normalization, clothing cleanup, and
+  composition cleanup from `caption_policy.py`.

 Improve later:

@@ -97,6 +97,7 @@ Core helper ownership:
 | `row_normalization.py` | Final prompt-row and pair metadata normalization: trigger prepending, extra-positive append, negative merge/dedupe, caption-part joining, and embedded soft/hard row sanitation. |
 | `formatter_input.py` | Shared formatter input parsing: text cleanup, metadata/source JSON detection, trigger-prefix stripping, shared prompt field-label inventory, `Avoid:` splitting, prompt-field extraction, and metadata row-value fallback. |
 | `sdxl_presets.py` | SDXL style presets, quality presets, default negative prompt, and metadata-family tag hints used by the SDXL formatter and node choice lists. |
+| `caption_policy.py` | Caption naturalizer policy data and helpers: style tails, item labels, metadata-family caption labels, detail/style-policy normalization, clothing cleanup, and composition cleanup. |

 ## Node IO Map