How 21 AI image models render: “Realistic. Four scenes in one. 1) A pretty Japanese woman, about 19–23 years old, in cat-type cosplay at an anime convention. 2) An old German man or woman, about 60–65 years old, finally having a breakthrough that would change the world. 3) A happy, mixed-race, 21-year-old female or male hacker checking their bank account, which has many zeros, with a bundle of cash near their PC. 4) A happy moment that would make you smile.”

Same prompt, sent verbatim, at each model's default settings and a fixed seed. Judge: could this be a photograph? Skin, light, lens behaviour. 164 community votes so far.

Community prompt by @blanknamebp · voting closed 2026-10-16

21 text-to-image models rendered this photorealism 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 85% of its 13 head-to-head votes on this prompt. Grok Imagine Image Quality was the fastest at 6.7s.

What to look for: believable skin and fabric, physically plausible light and shadow, lens behaviour such as depth of field and motion blur, and no waxy or over-smoothed surfaces.

FAQ

Which AI model renders this prompt best?

GPT Image 2.5 Sunburst leads this prompt in the BudgetPixel AI Image Arena, winning 85% of its 13 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.