#75 · Primary category: Computer Vision
Edit-Banana
Edit Banana: A framework for converting statistical formats into editable.
Project last updated:08/25/26
GitHub Stars
5.5K
Forks
358
Contributors
5
License
AGPL-3.0
Why we included this project
Static diagram files are a recurring annoyance: a chart, schematic, or architecture sketch arrives as a PNG, and someone has to trace it back into an editable format by hand. Edit-Banana handles that by converting an uploaded image into a DrawIO (XML) document whose individual elements can be selected and edited afterwards. It combines a fine-tuned SAM 3 segmentation model with multimodal LLM scanning and local OCR, including formula recognition into LaTeX, which lets it keep the original layout, colors, and logical relationships instead of producing a rough approximation. That makes it a practical tool for anyone who regularly reworks figures in DrawIO, technical writers rebuilding documentation, or analysts updating charts from reports. One honest caveat: the repository trails the web service, so the online demo at editbanana.net is the best way to gauge current reconstruction quality before committing to a local deployment.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
opencv
Open Source Computer Vision Library
RuView
π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video.
PaddleOCR
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
MinerU
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
tesseract
Tesseract Open Source OCR Engine (main repository)