Portrait & fashion
How 22 AI image models render: “Editorial portrait of an adult man in his early 40s wearing a charcoal wool fisherman’s sweater, one hand loosely holding its ribbed cuff. His thoughtful, slightly tired expression rests against a muted ochre studio backdrop, shaped by gentle directional window light.”
Same prompt, sent verbatim, at each model's default settings and a fixed seed. Judge: face and hands, fabric, believable expression. 114 community votes so far.
Fresh prompt from the daily stream · voting closed 2026-10-09
22 text-to-image models rendered this portrait & fashion prompt with the identical text at their default settings and a fixed seed. FLUX 3 Image is the community favourite so far, winning 91% of its 11 head-to-head votes on this prompt. Grok Imagine Image Quality was the fastest at 5.3s.
What to look for: correct anatomy, natural expressions, convincing fabric drape, and hands with the right number of fingers.
- FLUX 3 Image91%Black Forest Labs22.7s · 32 cr Try
- GPT Image 2.5 Sunburst70%OpenAI36.5s · 40 cr Try
- Kling v3 Omni67%Kuaishou61.5s · 35 cr Try
- Krea 2 Large57%Krea48.3s · 80 cr Try
- Qwen Image 3.0 Pro53%Alibaba10.8s · 36 cr Try
- GPT Image 250%OpenAI57.5s · 42 cr Try
- Nano Banana 2 Lite46%Google63.1s · 36 cr Try
- ImagineArt 1.5 Pro45%ImagineArt · retired from voting49.8s · 55 cr Try
- Seedream 5.0 Flash38%ByteDance26.7s · 22 cr Try
- Ideogram v4.536%Ideogram14.0s · 80 cr Try
- Qwen Image 3.036%Alibaba7.2s · 32 cr Try
- Seedream 5.0 Pro36%ByteDance30.4s · 49 cr Try
- ImagineArt 236%ImagineArt26.8s · 60 cr Try
- Krea 2 Medium33%Krea14.3s · 40 cr Try
- GPT Image 2.5 Flare29%OpenAI22.4s · 40 cr Try
- 5.3s · 80 cr Try
- Muse Image 1.029%Meta8.6s · 12 cr Try
- 17%17.3s · 50 cr Try
- Ideogram v48%Ideogram10.4s · 40 cr Try
- Recraft v4 ProRecraft · retired from voting15.6s · 300 cr Try
- Nano Banana 2.1Google9.9s · 40 cr Try
FAQ
- Which AI model renders this prompt best?
- FLUX 3 Image leads this prompt in the BudgetPixel AI Image Arena, winning 91% of its 11 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.