Product & commercial
How 21 AI image models render: “Commercial product photograph of an unbranded sculptural desk lamp with a frosted opal glass globe and brushed copper stem, standing on a pale travertine surface against a muted sage background, illuminated by soft overhead diffusion and a delicate warm rim light.”
Same prompt, sent verbatim, at each model's default settings and a fixed seed. Judge: clean surfaces, correct materials, ad-ready composition. 321 community votes so far.
Fresh prompt from the daily stream · voting closed 2026-10-14
21 text-to-image models rendered this product & commercial prompt with the identical text at their default settings and a fixed seed. GPT Image 2 is the community favourite so far, winning 67% of its 18 head-to-head votes on this prompt. Grok Imagine Image Quality was the fastest at 4.0s.
What to look for: clean surfaces, correct materials such as glass, steel and ceramic, controlled studio light and ad-ready composition.
- GPT Image 267%OpenAI · retired from voting90.5s · 60 cr Try
- 4.0s · 80 cr Try
- Nano Banana 2.159%Google9.6s · 40 cr Try
- ImagineArt 258%ImagineArt26.4s · 60 cr Try
- Qwen Image 3.0 Pro58%Alibaba10.4s · 36 cr Try
- Midjourney V8.257%Midjourney106.7s · 160 cr Try
- Ideogram v457%Ideogram11.2s · 40 cr Try
- Kling v3 Omni53%Kuaishou65.8s · 35 cr Try
- Nano Banana 2 Lite50%Google17.5s · 36 cr Try
- Seedream 5.0 Pro50%ByteDance46.2s · 49 cr Try
- GPT Image 2.5 Sunburst46%OpenAI57.4s · 40 cr Try
- Muse Image 1.045%Meta27.1s · 12 cr Try
- Seedream 5.0 Flash41%ByteDance24.1s · 22 cr Try
- Ideogram v4.538%Ideogram12.2s · 80 cr Try
- Qwen Image 3.038%Alibaba6.7s · 32 cr Try
- Krea 2 Large32%Krea47.8s · 80 cr Try
- FLUX 3 Image29%Black Forest Labs24.2s · 32 cr Try
- GPT Image 2.5 Flare27%OpenAI29.7s · 40 cr Try
- 25%12.7s · 50 cr Try
- Krea 2 Medium13%Krea15.5s · 40 cr Try
FAQ
- Which AI model renders this prompt best?
- GPT Image 2 leads this prompt in the BudgetPixel AI Image Arena, winning 67% 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.