This simple app converts a screenshot to code (HTML/Tailwind CSS, or React or Bootstrap). It uses GPT-4 Vision to generate the code and DALL-E 3 to generate similar-looking images. You can now also enter a URL to clone a live website!
Youtube.Clone.mp4
See the Examples section below for more demos.
🆕 Try it here (bring your own OpenAI key - your key must have access to GPT-4 Vision. See FAQ section below for details). Or see Getting Started below for local install instructions.
- Dec 11 - Start a new project from existing code (allows you to come back to an older project)
- Dec 7 - 🔥 🔥 🔥 View a history of your edits, and branch off them
- Nov 30 - Dark mode, output code in Ionic (thanks @dialmedu), set OpenAI base URL
- Nov 28 - 🔥 🔥 🔥 Customize your stack: React or Bootstrap or TailwindCSS
- Nov 23 - Send in a screenshot of the current replicated version (sometimes improves quality of subsequent generations)
- Nov 21 - Edit code in the code editor and preview changes live thanks to @clean99
- Nov 20 - Paste in a URL to screenshot and clone (requires ScreenshotOne free API key)
- Nov 19 - Support for dark/light code editor theme - thanks @kachbit
- Nov 16 - Added a setting to disable DALL-E image generation if you don't need that
- Nov 16 - View code directly within the app
- Nov 15 - You can now instruct the AI to update the code as you wish. It is helpful if the AI messed up some styles or missed a section.
The app has a React/Vite frontend and a FastAPI backend. You will need an OpenAI API key with access to the GPT-4 Vision API or Google API key for Gemini Pro Vision.
Install package with your preferred python package management app.
pip install https://github.com/theonlyamos/screenshot-to-code/archive/v0.1.0.zipAfter installation, you can run the package from the terminal/command prompt and access the app on http://localhost:7001. Model Configuration can also be found on the settings modal of the web ui.
You can run this with GPT-4 Vision by using the following command line:
screenshottocode --api-key "<Your Api Key>"You can also run this with Gemini Pro Vision by using the following command line instead:
screenshottocode --model gemini --api-key "<Your Api Key>"Using Gemini Pro Vision model is a lot slower than using GPT-4 Vision since Gemini has a maximum output token of 2048. This means the results are fetched iteratively.
For debugging purposes, if you don't want to waste GPT4-Vision credits, you can run the backend in mock mode (which streams a pre-recorded response):
MOCK=true poetry run uvicorn main:app --reload --port 7001- You can configure the OpenAI base URL if you need to use a proxy: Set OPENAI_BASE_URL in the
backend/.envor directly in the UI in the settings dialog
If you have Docker installed on your system, in the root directory, clone the reposition and then run:
echo "OPENAI_API_KEY=sk-your-key" > .env
docker-compose up -d --buildThe app will be up and running at http://localhost:5173. Note that you can't develop the application with this setup as the file changes won't trigger a rebuild.
- I'm running into an error when setting up the backend. How can I fix it? Try this. If that still doesn't work, open an issue.
- How do I get an OpenAI API key? See https://github.com/abi/screenshot-to-code/blob/main/Troubleshooting.md
- How can I provide feedback? For feedback, feature requests and bug reports, open an issue or ping me on Twitter.
NYTimes
| Original | Replica |
|---|---|
 |
 |
Instagram page (with not Taylor Swift pics)
instagram.taylor.swift.take.1.mp4
Hacker News but it gets the colors wrong at first so we nudge it
hacker.news.with.edits.mp4
🆕 Try it here (bring your own OpenAI key - your key must have access to GPT-4 Vision. See FAQ section for details). Or see Getting Started for local install instructions.
