Show HN: Nano PDF – A CLI Tool to Edit PDFs with Gemini's Nano Banana

[GavCo]

The new Gemini 3 Pro Image model (aka Nano Banana) is incredible at generating slides, so I thought it would be fun to build a CLI tool that lets you edit PDF presentations using plain English. The tool converts the page you want to edit into an image, sends it to the model API together with your prompt to generate an edited image, then converts the updated image back and stitches into the original document.

Examples:

- `nano-pdf edit deck.pdf 5 "Update the revenue chart to show Q3 at $2.5M"`

- `nano-pdf add deck.pdf 15 "Create an executive summary slide with 5 bullet points"`

Features:

- Edit multiple pages in parallel

- Add entirely new slides that match your deck's style

- Google Search enabled by default so the model can look up current data

- Preserves text layer for copy/paste and search

It can work with any kind of PDF but I expect it would be most useful for a quick edit to a deck or something similar.

GitHub: https://github.com/gavrielc/Nano-PDF

[tecoholic]

> 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?

[kumarm]

Seems true and really wish the project included some sample PDF output.

My Text to Speech app uses bounding box to display what text in PDF is being read and would not work well PDF's from this project.

[lxe]

This is nuts and I absolutely love this. So you convert the PDF into image, edit the image, then convert the image back into a PDF.

[thenthenthen]

This is the usual workflow dealing with pdfs (unfortunately)

[shevis]

A side effect of replacing entire pages with images is that the file size will expand dramatically. Most PDFs only contain a couple of images

[falcor84]

It might be feasible to have an intermediate AI call take the generated image and slice it into individual text and image elements that it would then render into the pdf page

[moezd]

Behold, the might of LLMs! Instead of ushering the age of AGI as advertised 6 months ago, now it cleans your PDFs for you.

Many thanks to humanity for failing to standardise PDF and this project for paying interest on that tech debt with datacenter levels of energy consumption.

[treetalker]

I'd love to see clearer examples: a video, or original pdf / command / result pdf. Very cool!

[struc_so]

Interesting approach. I've spent a lot of time wrangling PDF internals recently, and the issue is usually maintaining the xref table integrity when you inject new content streams.

Does this approach rewrite the entire file structure on save, or are you appending incremental updates to the EOF? Incremental is safer for corruption, but file size bloats quickly with AI-generated diffs.

[perfectritone]

It's incredible how many hacks there are to make PDFs semi-usable.

[jimmySixDOF]

Is Tesseract still considered the go to here for OCR I would have thought lot of other options are out there now

[itsmevictor]

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.

[mentalgear]

Nice - but consider adding an animated screengrap like: https://github.com/pythops/oryx

[yoavm]

Please don't add an animated gif to your README. Nothing worse than an autoplaying video with no controls, that has 10 frames but takes 5.4MB to download. Github supports normal video files. It allows the user to rewind or pause, and it results in a much smaller file size.

[ThrowawayTestr]

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.

[tkfoss]

Try photopea next time

[iamflimflam1]

The lack of examples makes me very reluctant to commit any time to trying this out - despite it being something that I’m interested in.

Has anyone given any it a go? Does it work?

[stingraycharles]

What? There are examples in the repo and even in OP’s post.

I haven’t tried it, but there are plenty of examples.

[McNulty2]

I like the example of updating latest market data. Updating a deck one-off is tedious. Keeping it updated long-term was never going to happen. But now it can

[toddmorey]

I thought it was kinda funny that Google Slide’s own built in “beautify this slide” button converts the whole slide into an uneditable image.

[albert_e]

AFAIK -- even the "Designer" feature of Microsoft Powerpoint (now folded under Copilot license I believe) gives slide deigns with shapes etc that are not editable. Thankfully the text remains editable. But if we wnat to ever so slightly modify the suggested design my removing or reshaping some if the shapes ... nopes. Feels like they are worried about humans with taste ripping-off the AI output :D

[mlpoknbji]

Somewhat unrelated but can anyone recommend a way to edit the text of a PDF using LLM? Something like AI + acrobat pro?

[ohans]

Really cool! I reckon a nice UI would be a good addition

[informal007]

it will be more excited if i can use this feature in application with GUI, it’s now convenient to check the result after edit the PDF, i need to transfer between CLI and PDF reader

[vood]

Congratulations on the release; that's a really good job.

[John7878781]

Love this.

After several iterations of edits, would the image quality decrease?

[Zopieux]

I am disappointed that this doesn't modify the underlying pdf structure (which is a horror show, I know) but instead relies on fairly lossy OCR back&fourths.

I wish an agent with a validation and rendering tools could instead manipulate the structure to accomplish those edits way less destructively, checking its progress with the tools.