How 20 AI image models render: “In an infinite library where floating staircases defy gravity, a young woman carries a candle through endless shelves. Her shadow has quietly detached itself from her feet and now wanders independently among the towering bookcases, secretly opening glowing books filled with forgotten memories. Each open page reveals miniature worlds: flying origami birds, drifting clocks, and tiny ghostly figures. The woman's candlelight creates impossible reflections, revealing dozens of alternative shadows with distinct personalities. Dreamlike surrealism, warm golden candlelight set against deep blue darkness, intricate details, magical realism, painterly.”

Same prompt, sent verbatim, at each model's default settings and a fixed seed. Judge: design originality, readable silhouette, lighting drama. 61 community votes so far.

Community prompt by @chris70 · voting closed 2026-09-24

20 text-to-image models rendered this concept art & fantasy prompt with the identical text at their default settings and a fixed seed. Nano Banana 2 Lite is the community favourite so far, winning 80% of its 5 head-to-head votes on this prompt. Grok Imagine Image Quality was the fastest at 6.3s.

What to look for: sense of scale, atmosphere and light, and designs that read clearly at a glance.

FAQ

Which AI model renders this prompt best?

Nano Banana 2 Lite leads this prompt in the BudgetPixel AI Image Arena, winning 80% of its 5 blind head-to-head votes. Vote on the arena page to add your judgement.

Were the prompts adjusted per model?

No. Every model received the exact same prompt, unmodified, at its default settings, with no negative prompt or style suffix. Some models rewrite prompts internally, and that is part of what is being compared.

Can I run this prompt myself?

Yes. Each tile’s “Try” link opens the BudgetPixel workshop with this prompt and that model preselected.