Glamour
How 15 AI image models render: “A realistic India ink illustration with crisp black lines depicting a realistic scene, anatomy, and proportions. The ink lines are colored with watercolors, while the black lines remain visible. Full-length composition. A 25-year-old woman named Mandy has a round face and short, trendy hair dyed grayish white. She wears a short, tight halter-top dress with a backless design, fishnet stockings, and high platform heels. She carries a tiny fish-shaped purse over one shoulder. She has smoky eyes and dark brown lipstick. Her entire back is covered with a huge tattoo of a dancing adult woman surrounded by a swirl of roses and rose petals. She poses for a picture in rear view, standing on one foot with the other foot raised and knee bent. She looks at us over one shoulder, making eye contact with the camera and smiling.”
Same prompt, sent verbatim, at each model's default settings and a fixed seed. Judge: flattering light, natural pose, tasteful styling. 155 community votes so far.
Community prompt by @dell · voting closed 2026-10-15
15 text-to-image models rendered this glamour prompt with the identical text at their default settings and a fixed seed. ImagineArt 2 is the community favourite so far, winning 67% of its 18 head-to-head votes on this prompt. Grok Imagine Image Quality was the fastest at 5.5s.
What to look for: flattering light, a natural pose and tasteful styling, without distortion or artefacts.
- ImagineArt 267%ImagineArt27.7s · 60 cr Try
- Seedream 5.0 Flash59%ByteDance21.4s · 22 cr Try
- Seedream 5.0 Pro53%ByteDance76.5s · 49 cr Try
- Qwen Image 3.053%Alibaba6.5s · 32 cr Try
- FLUX 3 Image50%Black Forest Labs29.9s · 65 cr Try
- GPT Image 250%OpenAI · retired from voting49.0s · 60 cr Try
- Qwen Image 3.0 Pro41%Alibaba9.7s · 36 cr Try
- Midjourney V8.240%Midjourney119.3s · 160 cr Try
- Muse Image 1.038%Meta13.0s · 12 cr Try
- Nano Banana 2.138%Google11.2s · 31 cr Try
- 5.5s · 80 cr Try
- 31%13.1s · 50 cr Try
- Nano Banana 2 Lite26%Google14.0s · 36 cr Try
- Kling v3 Omni12%Kuaishou61.2s · 35 cr Try
FAQ
- Which AI model renders this prompt best?
- ImagineArt 2 leads this prompt in the BudgetPixel AI Image Arena, winning 67% of its 18 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.