Which is the best way for image to text extraction? Current AI modesl only summarises the image.

I used llava-1.5-7b-hf but doesn't help.
1 Reply
Chaika
Chaika4mo ago
it's been asked for before, specific ocr models: https://discord.com/channels/595317990191398933/1105477009964027914/1231013859993714708 No way to do custom models atm
Want results from more Discord servers?
Add your server