1580158
/
automatic
mirror of https://github.com/vladmandic/automatic
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
automatic/modules/caption
History
CalamitousFelicitousness 2f30e466e1 fix(caption): tagger batch only processes first uploaded file 
Align tagger batch file collection with the working VQA/OpenCLIP
pattern. The previous implementation used Path wrapping and resolve()
deduplication which broke multi-file uploads from the Gradio File
component. Now all four batch modes (VQA, OpenCLIP, WaifuDiffusion,
DeepBooru) use the same f.name file collection approach.
 		2026-03-07 02:26:48 +00:00
..
caption.py cleanup logger 2026-02-19 11:09:13 +01:00
deepbooru.py fix(caption): tagger batch only processes first uploaded file 2026-03-07 02:26:48 +00:00
deepbooru_model.py modernize typing 2026-02-19 09:15:37 +01:00
deepseek.py cleanup logger 2026-02-19 11:09:13 +01:00
gemini.py add gemini to prompt enhance 2026-03-02 11:01:17 +01:00
joycaption.py cleanup logger 2026-02-19 11:09:13 +01:00
joytag.py cleanup logger 2026-02-19 11:09:13 +01:00
models_def.py update gemini models 2026-03-04 07:31:36 +01:00
moondream3.py cleanup logger 2026-02-19 11:09:13 +01:00
openclip.py ruff lint 2026-02-19 11:13:44 +01:00
tagger.py cleanup logger 2026-02-19 11:09:13 +01:00
vqa.py update gemini models 2026-03-04 07:31:36 +01:00
vqa_detection.py feat(caption): add Florence detection parsing, SDPA bypass, and offload support 2026-02-11 02:48:11 +00:00
waifudiffusion.py fix(caption): tagger batch only processes first uploaded file 2026-03-07 02:26:48 +00:00