Typography
How 22 AI image models render: “An image relating to good health and happiness. The words “Being Healthy Is Good” appear in the background at least a couple of times. 4–7 moments.”
Same prompt, sent verbatim, at each model's default settings and a fixed seed. Judge: is the text exactly right, spelled correctly, well set? 107 community votes so far.
Community prompt by @blanknamebp · voting closed 2026-10-04
Expected text: Being Healthy Is Good
22 text-to-image models rendered this typography prompt with the identical text at their default settings and a fixed seed. Grok Imagine Image 2 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 5.3s.
What to look for: correct spelling, placement and legibility, and type that looks printed or carved rather than pasted on.
- 67%24.8s · 50 cr Try
- ImagineArt 1.5 Pro60%ImagineArt53.4s · 55 cr Try
- Ideogram v4.560%Ideogram14.1s · 80 cr Try
- GPT Image 255%OpenAI254.4s · 60 cr Try
- Krea 2 Medium50%Krea31.3s · 40 cr Try
- Recraft v4 Pro44%Recraft18.5s · 300 cr Try
- Seedream 5.0 Pro44%ByteDance30.3s · 49 cr Try
- Ideogram v442%Ideogram16.0s · 40 cr Try
- GPT Image 2.5 Sunburst40%OpenAI123.0s · 40 cr Try
- Kling v3 Omni40%Kuaishou70.7s · 35 cr Try
- Seedream 5.0 Flash40%ByteDance33.6s · 22 cr Try
- GPT Image 2.5 Flare36%OpenAI100.0s · 40 cr Try
- 5.3s · 80 cr Try
- Nano Banana 2 Lite36%Google50.1s · 36 cr Try
- Qwen Image 3.036%Alibaba7.8s · 32 cr Try
- ImagineArt 236%ImagineArt30.1s · 60 cr Try
- Qwen Image 3.0 Pro33%Alibaba10.3s · 36 cr Try
- Muse Image 1.022%Meta11.3s · 12 cr Try
- Recraft v420%Recraft · retired from voting9.1s · 45 cr Try
- Krea 2 Large0%Krea29.2s · 80 cr Try
- Midjourney Niji 7Midjourney · retired from voting122.0s · 40 cr Try
FAQ
- Which AI model renders this prompt best?
- Grok Imagine Image 2 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.