screenshot-to-code

Drop in a screenshot and convert it to clean code (HTML/Tailwind/React/Vue)

open-sourceagent-frameworks
Visit WebsiteView on GitHub
72.1k
Stars
+6008
Stars/month
0
Releases (6m)

Overview

Screenshot-to-code is an AI-powered development tool that transforms visual designs into functional code with remarkable efficiency. With over 72,000 GitHub stars, this tool bridges the gap between design and development by accepting screenshots, mockups, or Figma designs as input and generating clean, production-ready code in multiple frameworks. The tool supports a comprehensive range of output formats including HTML with Tailwind CSS, React components, Vue.js applications, Bootstrap layouts, and even SVG graphics. Powered by state-of-the-art AI models including Gemini 3, Claude Opus 4.5, and GPT-5 series, it delivers high-quality code generation that closely matches the visual input. The architecture consists of a React/Vite frontend paired with a FastAPI backend, making it accessible both as a self-hosted solution and through a paid hosted service. What sets screenshot-to-code apart is its experimental video support, allowing developers to record screen interactions and convert them into functional prototypes. This capability is particularly valuable for recreating complex user interfaces and interactions. The tool significantly accelerates the development process by eliminating the tedious manual conversion of designs to code, making it invaluable for rapid prototyping, design system implementation, and frontend development workflows.

Pros

  • + Multi-framework support with clean output in HTML/Tailwind, React, Vue, Bootstrap, and SVG formats
  • + Integration with leading AI models (Gemini 3, Claude Opus 4.5, GPT-5) ensuring high-quality code generation
  • + Experimental video-to-code feature enables conversion of screen recordings into functional prototypes

Cons

  • - Requires API keys from paid AI services (OpenAI, Anthropic, or Google), adding ongoing operational costs
  • - Quality heavily dependent on AI model performance, with open-source alternatives like Ollama producing poor results
  • - Limited to visual conversion - cannot understand complex business logic or backend functionality

Use Cases

Getting Started

1. Clone the repository and set up the FastAPI backend with `poetry install` and add your AI provider API keys to .env file 2. Install frontend dependencies with `yarn` and start the development server with `yarn dev` 3. Open localhost:5173, upload a screenshot or design mockup, select your preferred framework, and generate clean code instantly