CalamitousFelicitousness 8d67debdfd fix(caption): use cache_dir for BLIP and Moondream model downloads ...

- Add _load_blip_model helper with explicit cache_dir so downloads
  go to hfcache_dir instead of default HF cache
- Pre-load BLIP model/processor before creating Interrogator config
  to control download location and avoid redundant loads
- Set clip_model_path on config for CLIP model cache location
- Add cache_dir to Moondream model and tokenizer loading

2026-02-11 02:50:06 +00:00

..

caption.py

feat(caption): add Florence detection parsing, SDPA bypass, and offload support

2026-02-11 02:48:11 +00:00

deepbooru_model.py

refactor: rename interrogate module to caption

2026-02-11 02:47:41 +00:00

deepbooru.py

refactor(caption): code review fixes for offload, inference, and maintainability

2026-02-11 02:48:11 +00:00

deepseek.py

fix(caption): safetensors-only downloads, model load fixes, UI default, prefill tests

2026-02-11 02:48:11 +00:00

joycaption.py

fix(caption): safetensors-only downloads, model load fixes, UI default, prefill tests

2026-02-11 02:48:11 +00:00

joytag.py

fix(caption): safetensors-only downloads, model load fixes, UI default, prefill tests

2026-02-11 02:48:11 +00:00

moondream3.py

fix(caption): safetensors-only downloads, model load fixes, UI default, prefill tests

2026-02-11 02:48:11 +00:00

openclip.py

fix(caption): use cache_dir for BLIP and Moondream model downloads

2026-02-11 02:50:06 +00:00

tagger.py

refactor(caption): code review fixes for offload, inference, and maintainability

2026-02-11 02:48:11 +00:00

vqa_detection.py

feat(caption): add Florence detection parsing, SDPA bypass, and offload support

2026-02-11 02:48:11 +00:00

vqa.py

fix(caption): use cache_dir for BLIP and Moondream model downloads

2026-02-11 02:50:06 +00:00

waifudiffusion.py

refactor(caption): code review fixes for offload, inference, and maintainability

2026-02-11 02:48:11 +00:00