Portrait & fashion
How 22 AI image models render: “Portrait photograph of an adult woman in her early 60s wearing a softly pleated sea-green silk blouse, hands brushing its gathered sleeve fabric. Her amused, open expression stands against a matte rose backdrop, illuminated by broad, gentle studio light.”
Same prompt, sent verbatim, at each model's default settings and a fixed seed. Judge: face and hands, fabric, believable expression. 101 community votes so far.
Fresh prompt from the daily stream · voting closed 2026-10-05
22 text-to-image models rendered this portrait & fashion prompt with the identical text at their default settings and a fixed seed. Qwen Image 3.0 is the community favourite so far, winning 88% of its 8 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.
- Qwen Image 3.088%Alibaba6.3s · 32 cr Try
- Krea 2 Medium73%Krea15.8s · 40 cr Try
- GPT Image 2.5 Flare63%OpenAI202.1s · 40 cr Try
- Seedream 5.0 Pro63%ByteDance31.3s · 49 cr Try
- Qwen Image 3.0 Pro60%Alibaba9.3s · 36 cr Try
- Kling v3 Omni55%Kuaishou53.5s · 35 cr Try
- Muse Image 1.050%Meta10.0s · 12 cr Try
- Nano Banana 2 Lite44%Google27.2s · 36 cr Try
- Ideogram v443%Ideogram11.3s · 40 cr Try
- 42%18.5s · 50 cr Try
- GPT Image 2.5 Sunburst40%OpenAI292.3s · 40 cr Try
- Ideogram v4.536%Ideogram14.0s · 80 cr Try
- Seedream 5.0 Flash36%ByteDance30.7s · 22 cr Try
- Krea 2 Large31%Krea33.3s · 80 cr Try
- GPT Image 230%OpenAI159.6s · 60 cr Try
- 5.3s · 80 cr Try
- ImagineArt 1.5 Pro29%ImagineArt51.5s · 55 cr Try
- Recraft v420%Recraft · retired from voting17.3s · 45 cr Try
- Recraft v4 Pro11%Recraft · retired from voting20.4s · 300 cr Try
- ImagineArt 210%ImagineArt25.9s · 60 cr Try
- Midjourney Niji 7Midjourney · retired from voting218.8s · 160 cr Try
FAQ
- Which AI model renders this prompt best?
- Qwen Image 3.0 leads this prompt in the BudgetPixel AI Image Arena, winning 88% of its 8 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.