Typography
How 22 AI image models render: “At a neighborhood greenhouse café, sunlight filters through hanging herbs above a tiled counter; "THISTLE & THIMBLE" is painted in hand-lettered cream script across a deep green wooden menu board.”
Same prompt, sent verbatim, at each model's default settings and a fixed seed. Judge: is the text exactly right, spelled correctly, well set? 173 community votes so far.
Fresh prompt from the daily stream · voting closed 2026-10-10
Expected text: THISTLE & THIMBLE
22 text-to-image models rendered this typography prompt with the identical text at their default settings and a fixed seed. Nano Banana 2.1 is the community favourite so far, winning 78% of its 9 head-to-head votes on this prompt. Grok Imagine Image Quality was the fastest at 6.1s.
What to look for: correct spelling, placement and legibility, and type that looks printed or carved rather than pasted on.
- Nano Banana 2.178%Google9.8s · 40 cr Try
- GPT Image 2.5 Flare75%OpenAI36.1s · 40 cr Try
- 64%19.4s · 50 cr Try
- Ideogram v464%Ideogram15.4s · 40 cr Try
- GPT Image 257%OpenAI86.7s · 42 cr Try
- FLUX 3 Image57%Black Forest Labs36.8s · 32 cr Try
- Nano Banana 2 Lite56%Google84.9s · 36 cr Try
- Muse Image 1.055%Meta21.7s · 12 cr Try
- 6.1s · 80 cr Try
- GPT Image 2.5 Sunburst50%OpenAI50.6s · 40 cr Try
- Ideogram v4.547%Ideogram14.7s · 80 cr Try
- Qwen Image 3.0 Pro47%Alibaba11.4s · 36 cr Try
- Krea 2 Medium44%Krea15.2s · 40 cr Try
- Qwen Image 3.040%Alibaba7.1s · 32 cr Try
- Kling v3 Omni38%Kuaishou27.0s · 35 cr Try
- ImagineArt 1.5 Pro33%ImagineArt · retired from voting58.1s · 55 cr Try
- Seedream 5.0 Flash29%ByteDance28.8s · 22 cr Try
- Seedream 5.0 Pro28%ByteDance30.6s · 49 cr Try
- ImagineArt 225%ImagineArt28.6s · 60 cr Try
- Krea 2 Large20%Krea39.5s · 80 cr Try
- Recraft v4 ProRecraft · retired from voting18.0s · 300 cr Try
FAQ
- Which AI model renders this prompt best?
- Nano Banana 2.1 leads this prompt in the BudgetPixel AI Image Arena, winning 78% of its 9 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.