Show HN: Generate User Interface Components with GPT-3
5 by designhat | 0 comments on Hacker News.
I’m building an experimental tool that can generate a UI component from a high-level text description, i.e. “Design a card for viewing goals in a goal tracking application”. Basically, stable diffusion but for user interface components instead of images. This tool is at best a proof of concept. It currently only generates a single type of component (small cards that have basic info about an object), but the goal is to be able to design entire applications (either in one fell swoop or by piecing together components that the tool generates). The components it generates can be exported as react code. You can also have it modify an existing design. The tool isn't useful yet but it's somewhat fun to play around with. Having it generate a component rather than an entire screen made the problem easier but I'm not sure if there are any users that this would appeal to. I could see it appealing to developers who lack design and CSS skills and want to quickly build a decent looking frontend for their app. Looking forward to hearing what you guys think of this project and the generative AI for UI space in general. If you're interested in collaborating on a startup or open-source project in this space, email designhat dot ai at gmail dot com
5 by designhat | 0 comments on Hacker News.
I’m building an experimental tool that can generate a UI component from a high-level text description, i.e. “Design a card for viewing goals in a goal tracking application”. Basically, stable diffusion but for user interface components instead of images. This tool is at best a proof of concept. It currently only generates a single type of component (small cards that have basic info about an object), but the goal is to be able to design entire applications (either in one fell swoop or by piecing together components that the tool generates). The components it generates can be exported as react code. You can also have it modify an existing design. The tool isn't useful yet but it's somewhat fun to play around with. Having it generate a component rather than an entire screen made the problem easier but I'm not sure if there are any users that this would appeal to. I could see it appealing to developers who lack design and CSS skills and want to quickly build a decent looking frontend for their app. Looking forward to hearing what you guys think of this project and the generative AI for UI space in general. If you're interested in collaborating on a startup or open-source project in this space, email designhat dot ai at gmail dot com