Spaces:

ArtShumov
/

Whyx-PROmpTea

Running

App Files Files Community

Whyx-PROmpTea / tests

Ctrl+K

Ctrl+K

1 contributor

History: 12 commits

ArtShumov's picture

fix: pose tag naming + swap DWPose detector to YOLOv8m-pose for anime

4fb75d4 19 minutes ago

__init__.py

132 Bytes
feat(prod): rewrite pipeline + NoobAI + ensemble tagger (3xWD14+DeepDanbooru-ready) + 1000 artists + negative templates + history ext + scoring config 5 days ago
test_captioner.py

2.31 kB
feat(caption): Qwen2.5-VL-3B captioner option (Anima-style NL captions); per-call kind dispatch in Captioner facade, kind in tagger cache key, transformers>=4.53 3 days ago
test_control_preview.py

4.53 kB
fix(pose): letterbox preprocessing for reliable anime detection; primary-person selection; quality gate; yolov8m-pose @ 1024 default 3 days ago
test_core.py

2.59 kB
feat(prod): rewrite pipeline + NoobAI + ensemble tagger (3xWD14+DeepDanbooru-ready) + 1000 artists + negative templates + history ext + scoring config 5 days ago
test_ensemble.py

4.39 kB
feat(tagger): weighted 3x WD14 + JoyTag smart ensemble, richer pose analysis, NL caption tied to Smart mode 3 days ago
test_handlers.py

2.41 kB
feat(prod): rewrite pipeline + NoobAI + ensemble tagger (3xWD14+DeepDanbooru-ready) + 1000 artists + negative templates + history ext + scoring config 5 days ago
test_i18n_parity.py

670 Bytes
feat(prod): rewrite pipeline + NoobAI + ensemble tagger (3xWD14+DeepDanbooru-ready) + 1000 artists + negative templates + history ext + scoring config 5 days ago
test_joytag.py

2.01 kB
feat(tagger): smart ensemble — WD14 EVA02-Large v3 + JoyTag fusion, YOLO pose tags, optional VLM captions 3 days ago
test_nl_only.py

3.65 kB
feat(tagger): NL-only caption mode (no WD14/pose passes); yolov8s-pose default with original-coord keypoints; ControlNet Preview panel (skeleton black/overlay, Canny, PNG download); caption cache in Captioner facade 3 days ago
test_pose_tags.py

6.51 kB
fix: pose tag naming + swap DWPose detector to YOLOv8m-pose for anime 19 minutes ago
test_regressions_ui.py

1.08 kB
feat(prod): rewrite pipeline + NoobAI + ensemble tagger (3xWD14+DeepDanbooru-ready) + 1000 artists + negative templates + history ext + scoring config 5 days ago
test_tagger_arg_alignment.py

4.1 kB
refactor(ui): merge pose toggles into single checkbox + method radio (YOLO / Whole-body DWPose) about 1 hour ago
test_variation_smart.py

4.56 kB
feat(variator): smart tag ordering, per-category token budget, semantic min-tag topup, familiarity + scene constraints, intent-aware negatives, suggestion engine about 12 hours ago
test_wholebody_pose.py

10 kB
fix: pose tag naming + swap DWPose detector to YOLOv8m-pose for anime 19 minutes ago