diff --git a/docs/prompt-architecture-improvement-plan.md b/docs/prompt-architecture-improvement-plan.md index e067e21..990290a 100644 --- a/docs/prompt-architecture-improvement-plan.md +++ b/docs/prompt-architecture-improvement-plan.md @@ -194,8 +194,8 @@ Already isolated: by default, while SDXL can opt into legacy unknown key tags for compatibility. - final row and pair text normalization lives in `row_normalization.py`, covering trigger prepending, extra-positive append, negative merge/dedupe, - caption-part joining, and embedded soft/hard row sanitation before metadata - leaves generation. + caption-part joining, embedded soft/hard row output synchronization, and row + sanitation before metadata leaves generation. ### Pair / Adapter Layer @@ -230,6 +230,9 @@ Already isolated: - final pair output assembly lives in `pair_output.py`, including soft/hard prompt strings, trigger preservation, negatives, captions, and root metadata shape; the final cleanup step is delegated to `row_normalization.py`. + Embedded soft/hard rows are synchronized to the final pair prompt, caption, + and negative outputs during normalization so serialized pair metadata does + not carry stale standalone row text. ### Krea2 Formatter Path @@ -437,7 +440,8 @@ Medium-term: Near-term: -- Normalize pair metadata with one helper. +- Normalize pair metadata with one helper, including embedded row prompt, + caption, and negative synchronization. - Confirm pair prompts, captions, and soft/hard rows carry the same sanitized scene/camera/clothing fields. - Keep same-room pair continuity synchronized in both assembled prompt text and diff --git a/docs/prompt-pool-routing-map.md b/docs/prompt-pool-routing-map.md index dec13a1..7707e76 100644 --- a/docs/prompt-pool-routing-map.md +++ b/docs/prompt-pool-routing-map.md @@ -96,7 +96,7 @@ Core helper ownership: | `scene_camera_adapters.py` | Location-aware camera/scene prose such as coworking lounge camera layout. | | `krea_cast.py` | Shared formatter cast descriptor parsing, cast labels, cast prose, natural cast descriptor text, and label replacement used by Krea2 and caption routes. | | `prompt_hygiene.py` | Generic prompt, caption, and negative-prompt cleanup. | -| `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. | +| `row_normalization.py` | Final prompt-row and pair metadata normalization: trigger prepending, extra-positive append, negative merge/dedupe, caption-part joining, embedded soft/hard row output synchronization, and embedded row sanitation. | | `formatter_input.py` | Shared formatter input parsing: text cleanup, metadata/source JSON detection, trigger-prefix stripping, shared prompt field-label inventory, fallback field-label stripping, `Avoid:` splitting, prompt-field extraction, and metadata row-value fallback. | | `sdxl_presets.py` | SDXL formatter profiles, 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: caption profiles, style tails, item labels, metadata-family caption labels, detail/style-policy normalization, clothing cleanup, and composition cleanup. | @@ -494,7 +494,7 @@ plain prompt text. When debugging, inspect these fields before editing pools. | `options` | `SxCP Insta/OF Options` | Formatters/debug | Soft/hard level, cast mode, continuity, camera modes, expression settings. | | `shared_descriptor` | `pair_cast.py` | Pair formatters | Primary creator descriptor. | | `shared_cast_descriptors` | `pair_cast.py` | Pair formatters | Full cast descriptor list. | -| `softcore_row`, `hardcore_row` | Pair route | Pair formatters | Full normal metadata rows for each side. | +| `softcore_row`, `hardcore_row` | Pair route | Pair formatters | Full normal metadata rows for each side; their prompt, caption, and negative fields are synchronized to the final pair outputs during pair normalization. | | `softcore_prompt`, `hardcore_prompt` | `pair_output.py` | Direct output/fallback | Raw pair prompts before formatter rewrite. | | `softcore_negative_prompt`, `hardcore_negative_prompt` | `pair_output.py` | Formatter negatives | Separate negatives for each side. | | `softcore_partner_styling` | `pair_cast.py` | Krea/SDXL pair branch | Partner softcore clothing and pose when same-cast softcore is enabled. | diff --git a/row_normalization.py b/row_normalization.py index 4e6fd96..aed8c4d 100644 --- a/row_normalization.py +++ b/row_normalization.py @@ -101,9 +101,28 @@ def sanitize_metadata_row_text(row: dict[str, Any], *, active_trigger: str = "") return row +def synchronize_pair_row_outputs(pair: dict[str, Any]) -> dict[str, Any]: + mapping = ( + ("softcore_row", "softcore_prompt", "softcore_caption", "softcore_negative_prompt"), + ("hardcore_row", "hardcore_prompt", "hardcore_caption", "hardcore_negative_prompt"), + ) + for row_key, prompt_key, caption_key, negative_key in mapping: + row = pair.get(row_key) + if not isinstance(row, dict): + continue + if prompt_key in pair: + row["prompt"] = pair.get(prompt_key, "") + if caption_key in pair: + row["caption"] = pair.get(caption_key, "") + if negative_key in pair: + row["negative_prompt"] = pair.get(negative_key, "") + return pair + + def normalize_pair_metadata(pair: dict[str, Any], *, active_trigger: str = "") -> dict[str, Any]: trigger = str(active_trigger or "").strip() triggers = _trigger_tuple(trigger) + synchronize_pair_row_outputs(pair) for key in ("softcore_prompt", "hardcore_prompt"): if key in pair: pair[key] = sanitize_prompt_text(pair.get(key, ""), triggers=triggers) diff --git a/tools/prompt_smoke.py b/tools/prompt_smoke.py index 2f99f99..55ac18d 100644 --- a/tools/prompt_smoke.py +++ b/tools/prompt_smoke.py @@ -852,6 +852,14 @@ def smoke_row_normalization_policy() -> None: _expect_trigger_once("row_normalization.pair.hardcore_prompt", pair.get("hardcore_prompt"), Trigger) _expect_trigger_once("row_normalization.pair.softcore_row.prompt", pair["softcore_row"].get("prompt"), Trigger) _expect_trigger_once("row_normalization.pair.hardcore_row.caption", pair["hardcore_row"].get("caption"), Trigger) + _expect( + pair["softcore_row"].get("prompt") == pair.get("softcore_prompt"), + "Pair normalization left stale soft row prompt text", + ) + _expect( + pair["hardcore_row"].get("caption") == pair.get("hardcore_caption"), + "Pair normalization left stale hard row caption text", + ) _expect_no_duplicate_comma_items("row_normalization.pair.soft_negative", pair.get("softcore_negative_prompt")) _expect_no_duplicate_comma_items("row_normalization.pair.hard_row_negative", pair["hardcore_row"].get("negative_prompt")) @@ -1491,6 +1499,18 @@ def _expect_pair(pair: dict[str, Any], name: str) -> None: _expect_trigger_once(f"{name}.hardcore_prompt", pair.get("hardcore_prompt"), Trigger) _expect_trigger_once(f"{name}.softcore_caption", pair.get("softcore_caption"), Trigger) _expect_trigger_once(f"{name}.hardcore_caption", pair.get("hardcore_caption"), Trigger) + _expect(pair["softcore_row"].get("prompt") == pair.get("softcore_prompt"), f"{name}.softcore_row prompt drifted from pair prompt") + _expect(pair["hardcore_row"].get("prompt") == pair.get("hardcore_prompt"), f"{name}.hardcore_row prompt drifted from pair prompt") + _expect(pair["softcore_row"].get("caption") == pair.get("softcore_caption"), f"{name}.softcore_row caption drifted from pair caption") + _expect(pair["hardcore_row"].get("caption") == pair.get("hardcore_caption"), f"{name}.hardcore_row caption drifted from pair caption") + _expect( + pair["softcore_row"].get("negative_prompt") == pair.get("softcore_negative_prompt"), + f"{name}.softcore_row negative drifted from pair negative", + ) + _expect( + pair["hardcore_row"].get("negative_prompt") == pair.get("hardcore_negative_prompt"), + f"{name}.hardcore_row negative drifted from pair negative", + ) _expect_no_duplicate_comma_items(f"{name}.softcore_negative", pair.get("softcore_negative_prompt")) _expect_no_duplicate_comma_items(f"{name}.hardcore_negative", pair.get("hardcore_negative_prompt")) _expect_formatter_outputs(pair, name, target="softcore")