Clip Interrogator Versions Save

Image to prompt with BLIP and CLIP

v0.6.0

1 year ago
  • Support for more caption models. In addition to blip-base and blip-large there is now blip2-2.7b (15.5GB), blip2-flan-t5-xl (15.77GB), git-large-coco (1.58GB). See run_gradio.py for example.
  • Newly exposed class LabelTable and functions list_caption_models, list_clip_models, load_list
  • See README for example how to rank your own list of terms using LabelTable

v0.5.4

1 year ago
  • Improved low VRAM support. Use new apply_low_vram_defaults method on Config object
  • Improved download of safetensors cache files
  • Dropped support of the .pkl cache files in favor of safetensors format