I'm working on a project that needs to dynamically generate simple icons and diagrams. I've tried GPT-4 and Claude - they can output SVG code but the results are hit or miss, especially for anything beyond basic shapes.
Has anyone found a reliable workflow for this? I'm wondering if there are specialized models, better prompting techniques, or if I should just use a traditional graphics library and skip the LLM route entirely. What's actually working in production for you?
It's actually easier to do bitmaps which is why the visual models create those. You can describe any painting with a few words about content and style but that doesn't give you the SVG syntax needed to represent those things as shapes.
reply