StyleSnatch (Proof of Concept)

I made this for the demo for the Adobe Express Add-ons hackathon. Super simple, not at all polished, just to illustrate how the idea works. In the future I'd like to add more complicated image detection (not just shapes). Ideas are welcome!

Overview

StyleSnatch analyzes images to detect:

• Text content with font and color information
• Shapes with color information
• Layout positioning of elements

The tool outputs:

• JSON file with detailed analysis
• Adobe Express compatible JavaScript code
• Debug visualization image

Prerequisites

• Python 3.11+
• WhatFontIs API Key (for font detection)

Installation

1. Clone the repository
2. Install dependencies:

pip install -r requirements.txt

3. Create a .env file in the project root and add your WhatFontIs API key:

API_KEY=your_api_key_here

Usage

1. Start the analysis server:

python app.py

2. Run the example script with your image:

python example.py

The script will:

• Send the image to the analysis server
• Save analysis results to analysis_results.json
• Generate Adobe Express code in export_adobe_express.txt
• Create a debug visualization in debug_output_live.png

3. Copy the contents of export_adobe_express.txt into Adobe Express playground to recreate the layout.