Portrait & fashion
How 22 AI image models render: “Under a narrow window beam, an adult woman in her late 50s wears a sculpted wool cape over a cotton blouse; her wry expression rests against a charcoal plaster backdrop in a black-and-white portrait, shaped by soft angled light.”
Same prompt, sent verbatim, at each model's default settings and a fixed seed. Judge: face and hands, fabric, believable expression. 138 community votes so far.
Fresh prompt from the daily stream · voting closed 2026-10-17
22 text-to-image models rendered this portrait & fashion prompt with the identical text at their default settings and a fixed seed. Krea 2 Medium is the community favourite so far, winning 62% of its 13 head-to-head votes on this prompt. Grok Imagine Image Quality was the fastest at 4.6s.
What to look for: correct anatomy, natural expressions, convincing fabric drape, and hands with the right number of fingers.
- Krea 2 Medium62%Krea16.4s · 40 cr Try
- GPT Image 2.5 Flare59%OpenAI18.9s · 40 cr Try
- Krea 2 Large59%Krea28.5s · 80 cr Try
- 58%14.9s · 50 cr Try
- Ideogram v4.550%Ideogram17.9s · 80 cr Try
- Nano Banana 2 Lite50%Google16.4s · 36 cr Try
- Nano Banana 2.150%Google9.3s · 31 cr Try
- Qwen Image 3.0 Pro50%Alibaba10.5s · 36 cr Try
- Seedream 5.0 Flash50%ByteDance21.0s · 22 cr Try
- Midjourney V8.250%Midjourney105.4s · 160 cr Try
- Seedream 5.0 Pro43%ByteDance24.0s · 49 cr Try
- Ideogram v440%Ideogram13.1s · 40 cr Try
- GPT Image 238%OpenAI · retired from voting48.4s · 60 cr Try
- GPT Image 2.5 Sunburst38%OpenAI39.1s · 40 cr Try
- 4.6s · 80 cr Try
- ImagineArt 233%ImagineArt · retired from voting40.5s · 60 cr Try
- Muse Image 1.031%Meta19.1s · 12 cr Try
- FLUX 3 Image31%Black Forest Labs19.4s · 65 cr Try
- Qwen Image 3.029%Alibaba8.4s · 32 cr Try
- Kling v3 Omni25%Kuaishou27.0s · 35 cr Try
- FLUX 3 Image KleinBlack Forest Labs5.3s · 12 cr Try
FAQ
- Which AI model renders this prompt best?
- Krea 2 Medium leads this prompt in the BudgetPixel AI Image Arena, winning 62% 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.