Vito Sansevero d051fc2a5c fix(tagging): measured GPU rate, and an ended image-tags job shows no time left (#379) ...

The live check measured WD14 on CUDA at 0.167 s per image (100 images in
16.7 s with the model load), so the review estimate uses 0.17 s. A finished
or cancelled Auto-tag/Add tags job kept "Processing file N of N · about X
min left"; it now ends with "<verb> <state> · N files processed".

Part of #379

2026-10-27 11:20:20 -07:00

..

api

fix(tagging): measured GPU rate, and an ended image-tags job shows no time left (#379)

2026-10-27 11:20:20 -07:00

__init__.py

style: apply Black formatter (line-length=88) to all Python files

2026-02-07 08:30:09 -08:00

autotag.py

fix(tagging): Tag output images tags each image, not its prompt (#379, PR 1)

2026-10-27 05:35:22 -07:00

config_store.py

fix(config): serialized config store and registry admission (#289)

2026-10-22 21:39:01 -07:00

config.py

fix(tagging): save WD14 confidences only on the 0.05 grid every page shows (#369) (#373)

2026-10-27 03:26:34 -07:00

lora_import.py

fix(lora): cache LoraManager's layout and close the #355 follow-ups (#362) (#364)

2026-10-27 05:00:55 -07:00

lora_layout_cache.py

fix(lora): cache LoraManager's layout and close the #355 follow-ups (#362) (#364)

2026-10-27 05:00:55 -07:00

lora_manager_layout.py

fix(lora): cache LoraManager's layout and close the #355 follow-ups (#362) (#364)

2026-10-27 05:00:55 -07:00

lora_utils.py

fix(lora): cache LoraManager's layout and close the #355 follow-ups (#362) (#364)

2026-10-27 05:00:55 -07:00

model_gate.py

feat(annotations): image tag routes, model gate and scored suggestions (#278)

2026-10-22 10:36:58 -07:00

tagging_defaults.py

fix(tagging): measured GPU rate, and an ended image-tags job shows no time left (#379)

2026-10-27 11:20:20 -07:00