Typography
How 20 AI image models render: “Beside a cliffside lighthouse, a salt-speckled logbook lies open on a chart table; "TIDEMARK LANTERN" is handwritten in looping dark-blue ink across a cream note tucked beneath the compass, with no other legible writing.”
Same prompt, sent verbatim, at each model's default settings and a fixed seed. Judge: is the text exactly right, spelled correctly, well set? 191 community votes so far.
Fresh prompt from the daily stream · voting closed 2026-10-24
Expected text: TIDEMARK LANTERN
20 text-to-image models rendered this typography prompt with the identical text at their default settings and a fixed seed. FLUX 3 Image Klein is the community favourite so far, winning 77% of its 13 head-to-head votes on this prompt. Grok Imagine Image Quality was the fastest at 5.5s.
What to look for: correct spelling, placement and legibility, and type that looks printed or carved rather than pasted on.
- FLUX 3 Image Klein77%Black Forest Labs27.5s · 12 cr Try
- Ideogram v4.567%Ideogram12.2s · 80 cr Try
- Nano Banana 2.164%Google29.2s · 31 cr Try
- Ideogram v462%Ideogram27.2s · 40 cr Try
- GPT Image 2.5 Sunburst60%OpenAI18.6s · 40 cr Try
- Krea 2 Medium53%Krea27.8s · 40 cr Try
- Muse Image 1.053%Meta18.7s · 12 cr Try
- Seedream 5.0 Pro53%ByteDance39.9s · 49 cr Try
- GPT Image 2.5 Flare50%OpenAI26.3s · 40 cr Try
- Nano Banana 2 Lite50%Google18.7s · 36 cr Try
- FLUX 3 Image50%Black Forest Labs19.8s · 65 cr Try
- 47%14.1s · 50 cr Try
- 5.5s · 80 cr Try
- Seedream 5.0 Flash46%ByteDance25.8s · 22 cr Try
- Kling v3 Omni38%Kuaishou44.2s · 35 cr Try
- Krea 2 Large29%Krea28.8s · 80 cr Try
- Midjourney V8.225%Midjourney112.6s · 160 cr Try
- Qwen Image 3.024%Alibaba7.5s · 32 cr Try
- Qwen Image 3.0 Pro12%Alibaba10.3s · 36 cr Try
FAQ
- Which AI model renders this prompt best?
- FLUX 3 Image Klein leads this prompt in the BudgetPixel AI Image Arena, winning 77% of its 13 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.