Show HN: Nano PDF – A CLI Tool to Edit PDFs with Gemini's Nano Banana
12 days ago
- #AI
- #PDF-editing
- #CLI-tool
- CLI tool for editing PDF slides using natural language prompts powered by Google's Gemini 3 Pro Image ('Nano Banana') model.
- Features include natural language editing (e.g., updating graphs, changing chart types), adding new slides matching the deck's style, and non-destructive editing preserving text layers via OCR re-hydration.
- Multi-page and parallel processing for efficiency with configurable resolution (4K/2K/1K) to balance quality and cost.
- Installation via pip, requiring a paid Google Gemini API key with billing enabled.
- Commands include editing single or multiple pages, inserting new AI-generated slides, and options like using document context, specifying style references, and setting output filenames.
- Examples provided for fixing typos, updating branding, financial data, and adding agenda slides.
- Dependencies include Python 3.10+, poppler, and tesseract, with installation instructions for macOS, Windows, and Linux.
- Tips for optimal use include specifying style references, ensuring high resolution for OCR, and adjusting resolution for faster processing.
- Development version can be installed from GitHub, with the tool licensed under MIT.