Verified project record

tonybeltramelli/pix2code

pix2code uses deep learning to automatically generate front-end code from a single GUI design screenshot, supporting iOS, Android, and web-based platforms. It trains a deep neural network on datasets of GUI screenshots and compiles the generated code into target platform languages.

Project overview

By automating the translation of visual GUI designs into compilable code across three major platforms, pix2code demonstrates a compelling deep-learning approach to reducing manual front-end development effort.

Project type: AI Coding
Use cases: Learning & Education
Deployment: Refer to project documentation
License: Apache-2.0

Best for

Researchers and educators exploring deep learning approaches to automated GUI-to-code translation.

Key capabilities

Train a deep neural network model end-to-end on datasets of GUI screenshots to generate code.
Compile generated DSL code into Android XML UI, iOS Storyboard, or HTML/CSS.

Limitations and risks

The project is not intended or able to generate code in a real-world context.
This is an experimental project and will not work for specific use cases.
The project will not support other target platforms or languages and will remain in the state described in the original research paper.

Getting started

Setting up the project requires a Python environment with necessary dependencies installed, beginning with running pip install -r requirements.txt.

Evidence and sources

README: We could not emphasize enough that this project is experimental and shared for educational purposes only.
README: Transforming a graphical user interface screenshot created by a designer into computer code is a typical task conducted by a developer in order to build customized software, websi…
README: - Python 2 or 3 - pip
README: we show that deep learning methods can be leveraged to train a model end-to-end to automatically generate code from a single input image with over 77% of accuracy for three differ…
README: ./build_datasets.py ../datasets/ios/all_data ./build_datasets.py ../datasets/android/all_data ./build_datasets.py ../datasets/web/all_data

Reviewed at: 2026-07-18T01:21:37Z