Kyle Morris

Carrot - GPT3 for computer vision

Carrot is a model built by Plaintain Labs and hosted on Banana.dev
The inspiration came from seeing general purpose text models like GPT3 and asking "can we do this for computer vision too?"

Add a comment

Replies

Best
Derek Pankaew
This is AWESOME. Is there any chance I can input an image of a bank statement, and have it extract the text from the bank statement?
Erik Dunteman
@derekpankaew the model has some OCR capabilities which has impressed us (especially the math example), but the OCR isn't consistent enough where I'd lean on it for financial matters
Anton Cherkasov
It's impressive! Congrats on the launch!
Nicholas
Woah