Pix2Text
An Open-Source Python3 tool with SMALL models for recognizing layouts, tables, math formulas (LaTeX), and text in images, converting them into Markdown format. A free alternative to Mathpix, empowering seamless conversion of visual content into text-based representations. 80+ languages are supported.
File Explorer
Download Latest Version (.zip)- ch_tra.jpg
- en1.jpg
- english.jpg
- formula.jpg
- formula2.png
- formula3.png
- formula4.jpg
- formula5.jpg
- formula6.jpg
- general.jpg
- hw-formula1.png
- hw-formula2.png
- hw-formula3.png
- math-formula-42.png
- mixed.jpg
- page.png
- page2.png
- test-doc.pdf
- val_0646.jpg
- vietnamese.jpg
- zh1.jpg
- zh6.jpg
- arch-flow.jpg
- breezedeus.ico
- breezedeus.png
- html.jpg
- output-ch_sim.jpg
- output-ch_tra.jpg
- output-en.jpg
- output-en1.jpg
- output-vietnamese.jpg
- p2t-logo.png
- wx-qr-code.JPG
- zsxq-qr-code.jpg
- 0-0-FIGURE.jpg
- 1-0-FIGURE.jpg
- output.md
- latex_ocr.md
- pix_to_text.md
- table_ocr.md
- text_formula_ocr.md
- buymeacoffee.md
- command.md
- contact.md
- demo.md
- examples.md
- examples_en.md
- faq.md
- index.md
- index_en.md
- install.md
- models.md
- RELEASE.md
- requirements.txt
- train.md
- usage.md
- __init__.py
- base_detector_subfield.py
- ctdet_subfield.py
- detector_factory.py
- __init__.py
- shapelyNMS.py
- __init__.py
- dlav0_subfield.py
- __init__.py
- data_parallel.py
- decode.py
- model.py
- scatter_gather.py
- utils.py
- __init__.py
- ddd_utils.py
- debugger.py
- evaluation_bk.py
- image.py
- post_process.py
- utils.py
- __init__.py
- doc_xl_layout_parser.py
- huntie_subfield.py
- opts.py
- wrapper.py
- __init__.py
- __version__.py
- app.py
- cli.py
- consts.py
- doc_yolo_layout_parser.py
- formula_detector.py
- hf_downloader.py
- latex_ocr.py
- layout_parser.py
- ocr_engine.py
- page_elements.py
- pix_to_text.py
- render.py
- serve.py
- table_ocr.py
- table_postprocess.py
- text_formula_ocr.py
- utils.py
- vlm_api.py
- vlm_table_ocr.py
- __init__.py
- screenshot_daemon.py
- try_pix2text_mfr.py
- try_service.py
- test_doc_xl_layout_parser.py
- test_doclayout_yolo.py
- test_latex_ocr.py
- test_mfd.py
- test_pix2text.py
- test_post_processors.py
- test_sort_boxes.py
- test_table_ocr.py
- test_text_formula_ocr.py
- test_utils_img.py
- test_vlm.py
- .gitignore
- .readthedocs.yaml
- CLAUDE.md
- LICENSE
- Makefile
- mkdocs.yml
- pix2text_v1_0.ipynb
- pix2text_v1_1.ipynb
- README.md
- README_cn.md
- requirements.in
- requirements.txt
- setup.py
# Installation Guide
git clone https://github.com/breezedeus/Pix2Text
Downloads the entire project code from GitHub to your computer.
cd Pix2Text
Moves into the project folder you just downloaded.
2. Official Install Script
Easy Recommended- Python 3 Python is required to use pip.
pip install pix2text
Installs the package published on PyPI directly β no need to clone the source.
pip install pix2text[multilingual]
Installs the package published on PyPI directly β no need to clone the source.
pip install pix2text -i https://mirrors.aliyun.com/pypi/simple
Installs the package published on PyPI directly β no need to clone the source.
Pulled directly from this repo's README.
3. Python
Easypip install pix2text
Installs the package published on PyPI directly β no need to clone the source.
pip install pix2text[multilingual]
Installs the package published on PyPI directly β no need to clone the source.
pip install pix2text -i https://mirrors.aliyun.com/pypi/simple
Installs the package published on PyPI directly β no need to clone the source.
Pulled directly from this repo's README.
4. Make
Medium- Git Needed to download the project code from GitHub.
- Make Usually pre-installed on Linux/macOS. On Windows, install separately (e.g. via MSYS2 or WSL).
make
Compiles the code based on the generated build configuration to produce an executable.