How 22 AI image models render: “Candid street photograph of an outdoor vegetable market at golden hour, a vendor weighing tomatoes on a brass scale, shallow depth of field, 50mm lens.”

Same prompt, sent verbatim, at each model's default settings and a fixed seed. Judge: could this be a photograph? Skin, light, lens behaviour. 1 community votes so far.

Core suite prompt · voting closed 2026-09-10

22 text-to-image models rendered this photorealism prompt with the identical text at their default settings and a fixed seed. 1 votes have been cast on this prompt so far; win rates appear once a sample has five. Grok Imagine Image Quality was the fastest at 4.9s.

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?

Not enough votes yet; a sample shows a win rate after five head-to-head votes. Vote on the arena page to add yours.

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.