Portrait & fashion
How 22 AI image models render: “Portrait photograph of an adult woman in her early 30s wearing a pale apricot linen blazer, her hands gently smoothing its cuff. She looks quietly delighted against a deep teal paper backdrop, illuminated by soft, angled studio light.”
Same prompt, sent verbatim, at each model's default settings and a fixed seed. Judge: face and hands, fabric, believable expression. 137 community votes so far.
Fresh prompt from the daily stream · voting closed 2026-10-10
22 text-to-image models rendered this portrait & fashion prompt with the identical text at their default settings and a fixed seed. Grok Imagine Image Quality is the community favourite so far, winning 67% of its 15 head-to-head votes on this prompt. Grok Imagine Image Quality was the fastest at 4.3s.
What to look for: correct anatomy, natural expressions, convincing fabric drape, and hands with the right number of fingers.
- 4.3s · 80 cr Try
- Nano Banana 2.167%Google12.7s · 40 cr Try
- Kling v3 Omni60%Kuaishou27.0s · 35 cr Try
- Nano Banana 2 Lite58%Google155.8s · 36 cr Try
- Qwen Image 3.0 Pro57%Alibaba9.3s · 36 cr Try
- Krea 2 Medium54%Krea15.0s · 40 cr Try
- 50%9.8s · 50 cr Try
- Ideogram v450%Ideogram10.6s · 40 cr Try
- Qwen Image 3.050%Alibaba6.7s · 32 cr Try
- GPT Image 2.5 Sunburst40%OpenAI38.4s · 40 cr Try
- FLUX 3 Image36%Black Forest Labs18.3s · 32 cr Try
- GPT Image 231%OpenAI58.9s · 42 cr Try
- GPT Image 2.5 Flare30%OpenAI22.8s · 40 cr Try
- ImagineArt 230%ImagineArt26.3s · 60 cr Try
- Seedream 5.0 Pro30%ByteDance29.6s · 49 cr Try
- Seedream 5.0 Flash29%ByteDance26.1s · 22 cr Try
- Ideogram v4.518%Ideogram11.8s · 80 cr Try
- Muse Image 1.017%Meta16.2s · 12 cr Try
- ImagineArt 1.5 Pro17%ImagineArt · retired from voting54.1s · 55 cr Try
- Krea 2 Large0%Krea28.0s · 80 cr Try
- Recraft v4 ProRecraft · retired from voting15.4s · 300 cr Try
FAQ
- Which AI model renders this prompt best?
- Grok Imagine Image Quality leads this prompt in the BudgetPixel AI Image Arena, winning 67% of its 15 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.