Fine tuned CLIP or BLIP for automated images labeling and indexing

CLIP, by Open-AI, is a neural network that is able to provide a fairly accurate textual desription of pictures. https://openai.com/blog/clip/ Other flavours of CLIP like BLIP could be used as well.

https://huggingface.co/laion/CLIP-ViT-bigG-14-laion2B-39B-b160k

Even better: a fine tuning of the CLIP network on our own faces/pictures could be helpful for indexing in capture one databases.