lukas-blecher/LaTeX-OCR
pix2tex: Using a ViT to convert images of equations into LaTeX code. observed · 2026-10-21
Health v2 · maintenance only
23/100
- Activity 0
- Release rhythm 8
- Longevity 100
How is this computed?
round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-10-21. Adoption (stars, forks) is never an input.
- gap_med: n/a
- age_days: 2139
- days_rel: n/a
- days_push: 640
- n_releases_24m: 0
Adoption not part of the score
16595 stars · 1305 forks observed · 2026-10-21
What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded
pix2tex (LaTeX-OCR) is a PyTorch-based vision transformer model that converts images of math formulas into LaTeX code. It ships as a pip-installable Python package with a CLI tool, a PyQt5 screenshot GUI, and an API for programmatic use.
Use cases
- convert a screenshot of an equation to LaTeX code
- extract LaTeX from images of math formulas
- OCR for mathematical notation in PDFs
- transcribe rendered equations back into editable LaTeX
- digitize math formulas from papers or notes
When to choose
- you need to turn images of printed math formulas into LaTeX automatically
- you want a ready-to-use pip package with CLI and GUI rather than training your own model
- you work with typeset (not handwritten) equations and want a free open-source tool
When to avoid
- you need reliable recognition of handwritten formulas, which the model handles poorly
- you need guaranteed-perfect LaTeX output for critical documents without manual review
- you cannot install PyTorch or run a GPU/CPU-heavy Python environment
Facets
library · maturity stable
ocr machine-learning image-processing deep-learning machine-learning computer-vision education developer-tools python cross-platform cli latex math-ocr vision-transformer im2latex pytorch formula-recognition pix2tex natural-language-processing desktop
2 sources
- readme: https://github.com/lukas-blecher/LaTeX-OCR · fetched 2026-10-21 · 8cc096647068
- homepage: https://lukas-blecher.github.io/LaTeX-OCR/ · fetched 2026-10-12 · f7d5d544de94
Member repositories
| Repository | Role | Health v2 |
|---|---|---|
| lukas-blecher/LaTeX-OCR | main | 23 |
For agents
markdown · JSON · MCP: product_card(name="lukas-blecher/LaTeX-OCR")
Data as of 2026-10-19T08:05:51.212177+00:00 · Report a problem