todo: Configure the CLIP model with the selected caption and clip model names.
Opened this issue · 0 comments
Escanor-LionSin commented
clip_model_name = 'ViT-L-14/openai'
caption_model_name = 'blip-large'
Opened this issue · 0 comments
clip_model_name = 'ViT-L-14/openai'
caption_model_name = 'blip-large'