Why do you want it to generate web pages from images? I'm having trouble understanding the workflow here. You see a component you like on another website and want to obtain the code from it? Or if you have a design already, why not just use a Figma to Code tool?
If you want to see how something like this might work, I made a fun project where I added a single board computer (SBC) into a keyboard. When you press the 'AI' button, the SBC would send inputs to the LLM on the SBC and output keystrokes to the PC. Demo below if you're curious.
What were you trying to get it to do? It was working alright for me but I was mostly doing quick HTML/CSS templating. I just paste in boilerplates and get it to make tailwind styles changes
Ah yup I'll post updates on my blog at lunecake.com and on HN. I haven't thought about open sourcing it so far but it's definitely something I'll consider in the future.
Oh that's neat. I made something somewhat similar recently: https://dopplerai.com/. It's a simple API that handles embeddings, vector database interactions and abstracts over Langchain. Each embedding belong to a user.