Show HN: Screenshot 2 Text GPT (with vision not OCR)

Heykuki News

3 points

2 years ago

GPT4V tends to rely on OCR instead of Vision to extract text. I found this to be less accurate.

This is basically a prompt that forces vision's use for text extraction.

1 comment

Show HN: Screenshot 2 Text GPT (with vision not OCR) | Heykuki News