Typography
How 21 AI image models render: “Inside a rooftop greenhouse at blue hour, tropical leaves crowd iron beams above a quiet potting bench; "MOSS & MERIDIAN" glows in warm amber neon along the glass entrance, with rain beads catching the light.”
Same prompt, sent verbatim, at each model's default settings and a fixed seed. Judge: is the text exactly right, spelled correctly, well set? 113 community votes so far.
Fresh prompt from the daily stream · voting closed 2026-10-01
Expected text: MOSS & MERIDIAN
21 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 72% of its 18 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.
- GPT Image 2.5 Sunburst72%OpenAI29.5s · 40 cr Try
- Recraft v469%Recraft · retired from voting14.7s · 45 cr Try
- Recraft v4 Pro69%Recraft21.2s · 300 cr Try
- GPT Image 2.5 Flare67%OpenAI21.8s · 40 cr Try
- 64%16.2s · 50 cr Try
- Qwen Image 3.062%Alibaba8.4s · 32 cr Try
- Nano Banana 2 Lite58%Google54.0s · 36 cr Try
- ImagineArt 256%ImagineArt27.8s · 60 cr Try
- Ideogram v455%Ideogram17.5s · 40 cr Try
- 5.3s · 80 cr Try
- Krea 2 Large45%Krea42.4s · 80 cr Try
- Seedream 5.0 Pro42%ByteDance34.0s · 49 cr Try
- Qwen Image 3.0 Pro36%Alibaba10.4s · 36 cr Try
- Muse Image 1.033%Meta11.6s · 12 cr Try
- Krea 2 Medium30%Krea21.1s · 40 cr Try
- GPT Image 222%OpenAI54.7s · 60 cr Try
- Kling v3 Omni20%Kuaishou117.8s · 35 cr Try
- Midjourney Niji 717%Midjourney · retired from voting180.6s · 160 cr Try
- ImagineArt 1.5 Pro0%ImagineArt52.9s · 55 cr Try
- Seedream 5.0 FlashByteDance27.6s · 22 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 72% of its 18 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.