diff --git a/CHANGELOG.md b/CHANGELOG.md index f512233..4f9bde3 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -12,12 +12,11 @@ Follows [Keep a Changelog](https://keepachangelog.com/en/1.0.0/) · versioned wi ### Changed - **Searchable model dropdown** for the Active Language Model and Active OCR Model pickers (Engines page): the long native model list is now the same type-to-search dropdown used for voices, with model-specific wording and no avatars. - -### Changed - **Character images: period-safe, uninjured, less uniform.** Costume and appearance text sent to the image model is now rewritten to period garments (Uniform, Weste, Hut, Sporen, Jacke, Schal … became livery tabard, jerkin, felt cap, doublet …) because the extracted sheets contained such words for ~45 characters and the images came out in wartime/cowboy dress; injury clauses (blood, wounds, bandages, burns, limping, torn clothes) are removed clause by clause from appearance, costume and the story-moment text instead of dropping whole sentences; characters with armour or weapons get an individual garment cut and colour scheme (stable per name, colours named in the sheet win) instead of one shared list of gambeson/brigandine/plate. Saved prompts are cleaned the same way at render time. Adult figures are described as eight head-heights tall with a small head, to counter the short, stubby turnaround figures. The stored sheets are unchanged. -- **The turnaround now shows the same person as the profile picture.** Front, side and rear views are drawn one by one by the edit model from the identity portrait (the old text-only triptych invented a new face). Book setting reworded to Dark Eye high-fantasy medieval (was "early Renaissance 1420-1500", which produced musketeer/wartime looks), shields/cloaks no longer added to everyone, soot/dirt removed like injuries, and prop tiles are object-only (they used to show a person). Existing image pairs are unchanged until regenerated. +- **Book setting reworded to Dark Eye high-fantasy medieval** (was "early Renaissance 1420-1500", which produced musketeer/wartime looks), soot/dirt removed like injuries, and prop tiles are object-only (they used to show a person). Existing image pairs are unchanged until regenerated. ### Fixed +- **Reverted the per-view turnaround renders.** Drawing front/side/rear separately with the edit model produced three near-identical front views, mixed styles between panels, cut-off bodies and a wireframe pose guide rendered into the costume. The turnaround is generated as a single three-panel image again, as it was before. - **Character-sheet extraction returned nothing with a reasoning model**: the blocking `/api/character-sheets` call could spend its whole token budget thinking and answer with empty content. It now retries once with thinking switched off (and once more without the switch if the backend rejects it). --- diff --git a/architecture/character-visual-identity.md b/architecture/character-visual-identity.md index a1723c5..0ece1b7 100644 --- a/architecture/character-visual-identity.md +++ b/architecture/character-visual-identity.md @@ -61,6 +61,6 @@ active changes only that form. * **Wording.** Extracted costume text is rewritten at prompt time (`_period_wording`: Uniform, Weste, Hut, Sporen, Jacke, Schal … become surcoat, jerkin, hood, boots, tunic …). Stored sheets are not changed. * **Injuries and dirt.** `_strip_injury_clauses` removes clauses about blood, wounds, bandages, burns, limping, torn clothes, soot and dirt from appearance, costume and the story moment; the rest of the sentence stays. The portrait baseline asks for clean skin and garments. * **Variety.** Characters with armour or weapons get an individual garment cut and colour scheme (`_character_design_variation`, stable per name; colours the sheet names win) instead of one shared list. -* **Same person in portrait and sheet.** The profile picture is a crop of the full-body identity image. The front, side and rear views are drawn one by one with the edit model using that identity image as the only reference (no pose guides), then stitched into the three-panel image the compositor already crops. The old text-only triptych produced a different face. +* **The turnaround stays one T2I triptych.** Drawing front/side/rear one by one with the edit model was tried (2026-09-20) and reverted the next day: it returned three near-identical front views, mixed rendering styles between panels, cropped bodies, and copied the wireframe pose guide into the costume — exactly the failure the triptych was introduced to fix. The portrait/sheet face mismatch is still open and needs a different approach. * **Props** get an object-only period sentence, so a tile no longer turns into a portrait of the character. * Older saved prompts are cleaned the same way at render time. Existing image pairs are unchanged until regenerated.