automatic

mirror of https://github.com/vladmandic/automatic synced 2026-08-31 17:41:06 +02:00

Files

T

CalamitousFelicitousness e2cdbe47fa fix(caption): safetensors-only downloads, model load fixes, UI default, prefill tests

- Add use_safetensors=True to all 16 model from_pretrained calls to
  avoid downloading redundant .bin files alongside safetensors
- Add device property to JoyTag VisionModel so move_model can relocate
  it to CUDA (fixes 'ViT object has no attribute device')
- Fix Pix2Struct dtype mismatch by casting float inputs to model dtype
  while preserving integer tensor types
- Patch AutoConfig.register with exist_ok=True during Ovis loading to
  handle duplicate aimv2 registration on model reload
- Detect Qwen VL fine-tune architecture from config model_type instead
  of repo name, fixing ToriiGate and similar third-party fine-tunes
- Change UI default task from Short Caption to Normal Caption, and
  preserve it on model switch instead of resetting to Use Prompt
- Add dual-prefill testing across 5 VQA test methods using a shared
  _check_prefill helper
- Fix pre-existing ruff W605 in strip_think_xml_tags docstring

2026-02-11 02:48:11 +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