Typography
How 22 AI image models render: “Inside a quiet clockmaker’s workshop, brass gears and tiny tools gleam beneath green-shaded lamps; "ORRERY HOUSE" is engraved in crisp serif letters on a dark walnut sign above the repair counter.”
Same prompt, sent verbatim, at each model's default settings and a fixed seed. Judge: is the text exactly right, spelled correctly, well set? 106 community votes so far.
Fresh prompt from the daily stream · voting closed 2026-10-04
Expected text: ORRERY HOUSE
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 Flare is the community favourite so far, winning 88% of its 8 head-to-head votes on this prompt. Grok Imagine Image Quality was the fastest at 4.9s.
What to look for: correct spelling, placement and legibility, and type that looks printed or carved rather than pasted on.
- GPT Image 2.5 Flare88%OpenAI143.3s · 40 cr Try
- ImagineArt 275%ImagineArt24.1s · 60 cr Try
- ImagineArt 1.5 Pro67%ImagineArt52.7s · 55 cr Try
- Krea 2 Large60%Krea28.7s · 80 cr Try
- Ideogram v460%Ideogram13.4s · 40 cr Try
- GPT Image 2.5 Sunburst58%OpenAI149.3s · 40 cr Try
- Nano Banana 2 Lite58%Google38.1s · 36 cr Try
- Recraft v457%Recraft · retired from voting14.0s · 45 cr Try
- Recraft v4 Pro56%Recraft22.2s · 300 cr Try
- 4.9s · 80 cr Try
- Seedream 5.0 Flash50%ByteDance31.6s · 22 cr Try
- GPT Image 247%OpenAI105.7s · 60 cr Try
- 45%17.1s · 50 cr Try
- Muse Image 1.040%Meta19.7s · 12 cr Try
- Kling v3 Omni36%Kuaishou27.4s · 35 cr Try
- Krea 2 Medium36%Krea14.4s · 40 cr Try
- Seedream 5.0 Pro29%ByteDance30.1s · 49 cr Try
- Qwen Image 3.0 Pro25%Alibaba9.7s · 36 cr Try
- Qwen Image 3.00%Alibaba6.9s · 32 cr Try
- Ideogram v4.5Ideogram14.7s · 80 cr Try
- Midjourney Niji 7Midjourney · retired from voting127.9s · 160 cr Try
FAQ
- Which AI model renders this prompt best?
- GPT Image 2.5 Flare leads this prompt in the BudgetPixel AI Image Arena, winning 88% of its 8 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.