Typography
How 22 AI image models render: “A hanging wooden shop sign that reads "MARLOW & FINCH — BOOKBINDERS" in gold serif letters, carved, above a blue door.”
Same prompt, sent verbatim, at each model's default settings and a fixed seed. Judge: is the text exactly right, spelled correctly, well set? 188 community votes so far.
Core suite prompt · voting closed 2026-09-16
Expected text: MARLOW & FINCH — BOOKBINDERS
22 text-to-image models rendered this typography prompt with the identical text at their default settings and a fixed seed. GPT Image 2.5 Sunburst is the community favourite so far, winning 84% of its 19 head-to-head votes on this prompt. Grok Imagine Image Quality was the fastest at 6.0s.
What to look for: correct spelling, placement and legibility, and type that looks printed or carved rather than pasted on.
- GPT Image 2.5 Sunburst84%OpenAI23.9s · 80 cr Try
- Nano Banana 2 Lite75%Google11.9s · 36 cr Try
- Recraft v474%Recraft · retired from voting10.9s · 45 cr Try
- Ideogram v468%Ideogram16.7s · 40 cr Try
- Qwen Image 3.0 Pro60%Alibaba8.7s · 36 cr Try
- GPT Image 2.5 Flare56%OpenAI31.4s · 40 cr Try
- GPT Image 255%OpenAI · retired from voting104.7s · 60 cr Try
- ImagineArt 1.5 Pro55%ImagineArt · retired from voting73.8s · 55 cr Try
- Krea 2 Large53%Krea48.9s · 80 cr Try
- Recraft v4 Pro50%Recraft · retired from voting16.2s · 300 cr Try
- Qwen Image 3.044%Alibaba13.7s · 32 cr Try
- Muse Image 1.042%Meta10.5s · 12 cr Try
- 39%13.7s · 50 cr Try
- ImagineArt 239%ImagineArt · retired from voting26.4s · 60 cr Try
- 6.0s · 80 cr Try
- Seedream 5.0 Pro25%ByteDance27.0s · 49 cr Try
- Midjourney Niji 724%Midjourney · retired from voting97.2s · 160 cr Try
- Krea 2 Medium16%Krea31.1s · 40 cr Try
- Kling v3 Omni11%Kuaishou27.0s · 35 cr Try
- Midjourney v7Midjourney · retired from voting124.8s · 160 cr Try
FAQ
- Which AI model renders this prompt best?
- GPT Image 2.5 Sunburst leads this prompt in the BudgetPixel AI Image Arena, winning 84% of its 19 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.