Portrait & fashion
How 20 AI image models render: “Atmospheric lighting creates soft background gradients through value blending, and surreal dark textures produce cracked surfaces and splatter via organic mark making. The fusion manifests as lace edges, dramatic chiaroscuro, and sharp focal contrast, transforming any subject through meticulous gothic surface modeling. A gothic woman depicted in 2026, with spiky black hair, blue eyes, and pale skin, wearing a black off-shoulder lace dress with a high ornate collar and puffed sleeves, holding a red rose. Close-up at eye level, the woman facing forward with her head slightly tilted, gazing directly at the viewer, holding a red rose in her right hand near her shoulder. Scene set before a gothic cathedral during overcast twilight, with misty atmosphere, featuring tall church spires in the background.”
Same prompt, sent verbatim, at each model's default settings and a fixed seed. Judge: face and hands, fabric, believable expression. 97 community votes so far.
Community prompt by @justrob · voting closed 2026-09-26
20 text-to-image models rendered this portrait & fashion prompt with the identical text at their default settings and a fixed seed. Seedream 5.0 Pro is the community favourite so far, winning 71% of its 7 head-to-head votes on this prompt. Grok Imagine Image Quality was the fastest at 5.5s.
What to look for: correct anatomy, natural expressions, convincing fabric drape, and hands with the right number of fingers.
- Seedream 5.0 Pro71%ByteDance66.3s · 38 cr Try
- GPT Image 2.5 Flare67%OpenAI26.9s · 40 cr Try
- Recraft v463%Recraft12.8s · 45 cr Try
- 5.5s · 80 cr Try
- Krea 2 Medium57%Krea16.3s · 40 cr Try
- ImagineArt 1.5 Pro56%ImagineArt79.0s · 55 cr Try
- GPT Image 2.5 Sunburst55%OpenAI29.4s · 40 cr Try
- 50%22.2s · 50 cr Try
- Qwen Image 3.0 Pro50%Alibaba10.5s · 36 cr Try
- Krea 2 Large50%Krea30.1s · 80 cr Try
- GPT Image 246%OpenAI89.4s · 60 cr Try
- ImagineArt 245%ImagineArt24.9s · 60 cr Try
- Ideogram v443%Ideogram12.5s · 40 cr Try
- Muse Image 1.043%Meta23.0s · 12 cr Try
- Qwen Image 3.043%Alibaba6.7s · 32 cr Try
- Recraft v4 Pro33%Recraft22.4s · 300 cr Try
- Midjourney Niji 718%Midjourney102.9s · 160 cr Try
- Kling v3 Omni11%Kuaishou27.3s · 35 cr Try
- Nano Banana 2 Lite10%Google17.9s · 36 cr Try
FAQ
- Which AI model renders this prompt best?
- Seedream 5.0 Pro leads this prompt in the BudgetPixel AI Image Arena, winning 71% of its 7 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.