Typography
How 23 AI image models render: “Steam curls above baskets of dumplings at a lively night-market stall, lantern light warming its canvas canopy; "GINGER COMET" is chalked in bold white letters on a blackboard beside the serving 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? 132 community votes so far.
Fresh prompt from the daily stream · voting closed 2026-10-06
Expected text: GINGER COMET
23 text-to-image models rendered this typography prompt with the identical text at their default settings and a fixed seed. Nano Banana 2 Lite is the community favourite so far, winning 67% of its 12 head-to-head votes on this prompt. Grok Imagine Image Quality was the fastest at 6.4s.
What to look for: correct spelling, placement and legibility, and type that looks printed or carved rather than pasted on.
- Nano Banana 2 Lite67%Google16.9s · 36 cr Try
- Qwen Image 3.0 Pro62%Alibaba26.4s · 36 cr Try
- ImagineArt 1.5 Pro60%ImagineArt54.0s · 55 cr Try
- Ideogram v457%Ideogram14.4s · 40 cr Try
- Recraft v4 Pro56%Recraft · retired from voting19.1s · 300 cr Try
- 50%16.2s · 50 cr Try
- Krea 2 Large47%Krea39.9s · 80 cr Try
- Muse Image 1.044%Meta12.2s · 12 cr Try
- 6.4s · 80 cr Try
- Seedream 5.0 Pro42%ByteDance43.6s · 49 cr Try
- GPT Image 2.5 Sunburst40%OpenAI48.4s · 40 cr Try
- ImagineArt 240%ImagineArt29.6s · 60 cr Try
- Seedream 5.0 Flash40%ByteDance27.0s · 22 cr Try
- GPT Image 2.5 Flare36%OpenAI21.2s · 40 cr Try
- Kling v3 Omni35%Kuaishou61.5s · 35 cr Try
- GPT Image 233%OpenAI53.3s · 60 cr Try
- FLUX 3 Image29%Black Forest Labs22.7s · 32 cr Try
- Krea 2 Medium27%Krea17.0s · 40 cr Try
- Ideogram v4.522%Ideogram20.8s · 80 cr Try
- Qwen Image 3.018%Alibaba8.0s · 32 cr Try
- Recraft v4Recraft · retired from voting11.2s · 45 cr Try
- Midjourney Niji 7Midjourney · retired from voting152.4s · 160 cr Try
FAQ
- Which AI model renders this prompt best?
- Nano Banana 2 Lite leads this prompt in the BudgetPixel AI Image Arena, winning 67% of its 12 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.