Typography
How 22 AI image models render: “Realistic. Four to five adults having a very lucky day. One of the people is a clown with a very strange cat on their head. Another is wearing a black crop top and multicolored shorts. The word “Lucky” is seen at least twice in the background.”
Same prompt, sent verbatim, at each model's default settings and a fixed seed. Judge: is the text exactly right, spelled correctly, well set? 125 community votes so far.
Community prompt by @blanknamebp · voting closed 2026-10-07
Expected text: Lucky
22 text-to-image models rendered this typography prompt with the identical text at their default settings and a fixed seed. Seedream 5.0 Pro is the community favourite so far, winning 81% of its 16 head-to-head votes on this prompt. Grok Imagine Image Quality was the fastest at 6.6s.
What to look for: correct spelling, placement and legibility, and type that looks printed or carved rather than pasted on.
- Seedream 5.0 Pro81%ByteDance27.8s · 49 cr Try
- Kling v3 Omni75%Kuaishou31.7s · 35 cr Try
- 73%13.3s · 50 cr Try
- ImagineArt 271%ImagineArt26.0s · 60 cr Try
- GPT Image 2.5 Flare50%OpenAI58.5s · 40 cr Try
- FLUX 3 Image50%Black Forest Labs36.1s · 65 cr Try
- ImagineArt 1.5 Pro45%ImagineArt · retired from voting53.1s · 55 cr Try
- GPT Image 2.5 Sunburst43%OpenAI84.3s · 40 cr Try
- 6.6s · 80 cr Try
- Seedream 5.0 Flash42%ByteDance33.5s · 22 cr Try
- Ideogram v436%Ideogram19.2s · 40 cr Try
- Muse Image 1.031%Meta13.0s · 12 cr Try
- Qwen Image 3.031%Alibaba9.3s · 32 cr Try
- Nano Banana 2 Lite29%Google29.1s · 36 cr Try
- Krea 2 Medium27%Krea19.4s · 40 cr Try
- Krea 2 Large21%Krea29.5s · 80 cr Try
- Ideogram v4.517%Ideogram19.3s · 80 cr Try
- Recraft v4 Pro17%Recraft · retired from voting17.8s · 300 cr Try
- Qwen Image 3.0 Pro9%Alibaba10.3s · 36 cr Try
- Recraft v4Recraft · retired from voting12.9s · 45 cr Try
- Nano Banana 2.1Google11.9s · 40 cr Try
FAQ
- Which AI model renders this prompt best?
- Seedream 5.0 Pro leads this prompt in the BudgetPixel AI Image Arena, winning 81% of its 16 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.