ansht3/svg_visalization ? reverse-engineered prompt
Reverse engineered prompt
Build me a web app where I can type a short description like “draw a stick man smiling” and then watch it get drawn on a blank white canvas, stroke by stroke, like someone is sketching it by hand.
If possible, use an AI image generator on the server for the real version, but also include an offline demo mode so it works without any API key. The important part is that the final result is not just a fading picture, it should turn the generated black and white drawing into real SVG paths and animate each stroke one at a time.
I want a simple page with a prompt box, a Draw button, and a toggle for demo mode. Please make it so the app handles missing API keys cleanly, and if you need to check current docs online while wiring up the image generation, go ahead.
Are you gonna build this?
make sure you review the code using coderabbit