Typography
How 22 AI image models render: “At a quiet harbor, a weathered wooden ferry rests beside slick pilings, ropes coiled on deck as gulls wheel overhead; "TIDELINE LANTERN" is painted in faded ivory letters along the blue hull.”
Same prompt, sent verbatim, at each model's default settings and a fixed seed. Judge: is the text exactly right, spelled correctly, well set? 112 community votes so far.
Fresh prompt from the daily stream · voting closed 2026-10-03
Expected text: TIDELINE LANTERN
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 71% of its 14 head-to-head votes on this prompt. Grok Imagine Image Quality was the fastest at 4.6s.
What to look for: correct spelling, placement and legibility, and type that looks printed or carved rather than pasted on.
- GPT Image 2.5 Sunburst71%OpenAI422.6s · 40 cr Try
- Qwen Image 3.0 Pro69%Alibaba9.8s · 36 cr Try
- Nano Banana 2 Lite64%Google45.0s · 36 cr Try
- ImagineArt 1.5 Pro58%ImagineArt71.3s · 55 cr Try
- Seedream 5.0 Pro56%ByteDance51.4s · 49 cr Try
- GPT Image 2.5 Flare54%OpenAI267.8s · 40 cr Try
- 53%17.8s · 50 cr Try
- GPT Image 245%OpenAI117.8s · 60 cr Try
- Ideogram v443%Ideogram13.3s · 40 cr Try
- Qwen Image 3.038%Alibaba6.7s · 32 cr Try
- 4.6s · 80 cr Try
- Krea 2 Large33%Krea34.1s · 80 cr Try
- Recraft v4 Pro30%Recraft19.6s · 300 cr Try
- Muse Image 1.022%Meta9.0s · 12 cr Try
- Kling v3 Omni17%Kuaishou27.2s · 35 cr Try
- Krea 2 Medium11%Krea14.0s · 40 cr Try
- ImagineArt 28%ImagineArt102.3s · 60 cr Try
- Recraft v4Recraft · retired from voting10.3s · 45 cr Try
- Seedream 5.0 FlashByteDance27.1s · 22 cr Try
- Midjourney Niji 7Midjourney · retired from voting188.2s · 160 cr Try
- Ideogram v4.5Ideogram12.8s · 80 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 71% of its 14 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.