I use LLMs to create photos and comics. But they can generate any kind of illustration. So why limit ourselves?
My problem is imagination: I know little about art. So, I asked ChatGPT, Claude, and DeepSeek:
Suggest 10 unusual illustration styles that are not popular in social media yet but are visually striking. I would like to have an LLM create images in that style. For each of those, show me an (and link to) an online image in that style.
Finally, summarize a sample prompt fragment I can use to tell an LLM to generate an image in that style.
Here are 27 styles generated by gpt-image-𝟭 and gemini-2.5-flash-image-preview (“nano-banana”): https://sanand0.github.io/llmartstyle/?category=art
Instead of sticking to the usual comic style, I’ll experiment with these new ones in my posts.
Painters turned photographers. Now… AIrtists? Should I take a modern art course? (Taught by ChatGPT, of course!)
Code: https://github.com/sanand0/llmartstyle
