Architecture & interiors
How 21 AI image models render: “At the heart of a restrained Brutalist museum, a folded concrete stair rises beside smoked-oak handrails and terrazzo landings; skylight washes the treads, seen from the lower landing, with aligned flights and believable supports.”
Same prompt, sent verbatim, at each model's default settings and a fixed seed. Judge: straight lines, materials, believable space. 181 community votes so far.
Fresh prompt from the daily stream · voting closed 2026-10-19
21 text-to-image models rendered this architecture & interiors prompt with the identical text at their default settings and a fixed seed. GPT Image 2.5 Flare is the community favourite so far, winning 76% of its 17 head-to-head votes on this prompt. Grok Imagine Image Quality was the fastest at 4.8s.
What to look for: straight verticals, plausible structure, consistent perspective and correct materials.
- GPT Image 2.5 Flare76%OpenAI38.2s · 40 cr Try
- 4.8s · 80 cr Try
- FLUX 3 Image64%Black Forest Labs21.0s · 65 cr Try
- FLUX 3 Image Klein60%Black Forest Labs12.4s · 12 cr Try
- Midjourney V8.258%Midjourney108.1s · 160 cr Try
- Seedream 5.0 Flash56%ByteDance19.4s · 22 cr Try
- GPT Image 2.5 Sunburst53%OpenAI40.3s · 40 cr Try
- 53%16.6s · 50 cr Try
- Krea 2 Large53%Krea31.5s · 80 cr Try
- Muse Image 1.050%Meta12.7s · 12 cr Try
- Seedream 5.0 Pro50%ByteDance24.3s · 49 cr Try
- Ideogram v440%Ideogram13.8s · 40 cr Try
- Qwen Image 3.0 Pro38%Alibaba10.9s · 36 cr Try
- Krea 2 Medium35%Krea18.1s · 40 cr Try
- Ideogram v4.529%Ideogram15.7s · 80 cr Try
- Nano Banana 2 Lite27%Google20.0s · 36 cr Try
- Qwen Image 3.023%Alibaba8.1s · 32 cr Try
- ImagineArt 220%ImagineArt · retired from voting26.8s · 60 cr Try
- Kling v3 Omni19%Kuaishou74.8s · 35 cr Try
- Nano Banana 2.114%Google26.8s · 31 cr Try
FAQ
- Which AI model renders this prompt best?
- GPT Image 2.5 Flare leads this prompt in the BudgetPixel AI Image Arena, winning 76% of its 17 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.