How 22 AI image models render: “Exactly four enamel camping cups form a vertical tower on a pale wooden shelf, bottom to top: red, yellow, blue, white; all handles face right. Soft morning light, nothing else.”
Same prompt, sent verbatim, at each model's default settings and a fixed seed. Judge: every stated element present, correct count, correct placement. 123 community votes so far.
Fresh prompt from the daily stream · voting closed 2026-10-17
Checklist: 4 enamel camping cups · cups form a vertical tower · bottom-to-top colors: red, yellow, blue, white · all handles face right · tower on a pale wooden shelf
22 text-to-image models rendered this prompt adherence prompt with the identical text at their default settings and a fixed seed. Krea 2 Medium is the community favourite so far, winning 75% of its 12 head-to-head votes on this prompt. Grok Imagine Image Quality was the fastest at 3.7s.
What to look for: the right count of objects, the right spatial relationships, the stated colours and attributes, and nothing added.
- Krea 2 Medium75%Krea21.1s · 40 cr Try
- Ideogram v464%Ideogram18.3s · 40 cr Try
- Nano Banana 2 Lite64%Google40.4s · 36 cr Try
- Qwen Image 3.0 Pro64%Alibaba15.8s · 36 cr Try
- GPT Image 2.5 Sunburst60%OpenAI38.2s · 40 cr Try
- Midjourney V8.257%Midjourney120.3s · 160 cr Try
- GPT Image 2.5 Flare56%OpenAI28.1s · 40 cr Try
- Muse Image 1.055%Meta8.8s · 12 cr Try
- Nano Banana 2.150%Google12.9s · 31 cr Try
- 3.7s · 80 cr Try
- Qwen Image 3.040%Alibaba7.2s · 32 cr Try
- ImagineArt 238%ImagineArt · retired from voting24.1s · 60 cr Try
- Seedream 5.0 Flash38%ByteDance20.4s · 22 cr Try
- FLUX 3 Image36%Black Forest Labs27.0s · 65 cr Try
- Krea 2 Large33%Krea28.0s · 80 cr Try
- Ideogram v4.525%Ideogram15.8s · 80 cr Try
- 23%12.5s · 50 cr Try
- Seedream 5.0 Pro21%ByteDance29.8s · 49 cr Try
- Kling v3 Omni17%Kuaishou27.1s · 35 cr Try
- GPT Image 2OpenAI · retired from voting39.8s · 60 cr Try
- FLUX 3 Image KleinBlack Forest Labs5.9s · 12 cr Try
FAQ
- Which AI model renders this prompt best?
- Krea 2 Medium leads this prompt in the BudgetPixel AI Image Arena, winning 75% 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.