You just need to draw the web interface you want in the sketching software, such as simple buttons or text boxes, basic wireframes.
It then uses tldraw and the GPT-4 Vision API to generate an HTML page based on the wireframe you draw.
The main principle is to convert the current canvas SVG into a PNG image, which is then sent to GPT-4 Vision, which is instructed to return a single HTML file containing Tailwind CSS.
GitHub：https://github.com/SawyerHood/draw-a-ui
Original text: https://twitter.com/i/status/1723537400461430794