How 20 AI image models render: “An authentic, historical 35mm photo capturing the fall of the Berlin Wall and German reunification on November 9, 1989. In the center, ecstatic adult East and West Berliners stand together on top of the shattered concrete rubble of the wall, hugging and celebrating with tears of joy. An adult man holds up a bottle of champagne spraying foam. Colorful graffiti covers the remaining segments of the wall. In the background, the glowing Brandenburg Gate stands under a cold night sky. Vintage press photography style, authentic film grain, harsh flashes from adult photojournalists, genuine human emotion, documentary realism.”

Same prompt, sent verbatim, at each model's default settings and a fixed seed. Judge: could this be a photograph? Skin, light, lens behaviour. 181 community votes so far.

Community prompt by @jpruizluna · voting closed 2026-11-09

20 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 83% of its 18 head-to-head votes on this prompt. FLUX 3 Image Klein was the fastest at 7.2s.

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 83% 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.