> Converts an image to a single-page PDF with a hidden text layer using Tesseract. This is the 'State Preservation' step.
Does this mean the text only pdf page is transformed into an image that covers the full page, but the text is still under there. So, any machine based extraction would still get the text, but would probably loose all the bounding box information and regular users cannot just use their mouse to select text anymore?
How cool! It's frustrating how tedious many PDF workflows still are. I've been building something similar in this space[0], but web-based where you visually specify the area to edit. The biggest issue for now is the cost per edit as the Pro version amounts to roughly $0.15/image. However, with some finessing, the original Nano Banana seems to do a great job as well. Have you explored UI-based approaches yourself by any chance?
Very nice! I wonder whether that could be used to get LLMs to annotate pdfs. Say an "agentic" CLI like Claude Code or Gemini-cli reviews a pdf and finds typos, could it use this to annotate the pdf like underlining them in red or something of that sort? That could be nice.
I recently tried to change a single word in a PDF and nearly tore my hair out (thank you LibreOffice) I'll definitely keep this in mind for next time, thank you.
Does this mean the text only pdf page is transformed into an image that covers the full page, but the text is still under there. So, any machine based extraction would still get the text, but would probably loose all the bounding box information and regular users cannot just use their mouse to select text anymore?
[0]https://docusera.com/