Glamour
How 23 AI image models render: “A glamorous woman walking down a busy UK high street in 1977. There are cars, buses and shops full of merchandise. Something surprising catches her eye.”
Same prompt, sent verbatim, at each model's default settings and a fixed seed. Judge: flattering light, natural pose, tasteful styling. 138 community votes so far.
Community prompt by @philbland · voting closed 2026-10-06
23 text-to-image models rendered this glamour prompt with the identical text at their default settings and a fixed seed. GPT Image 2.5 Flare is the community favourite so far, winning 73% of its 15 head-to-head votes on this prompt. Qwen Image 3.0 was the fastest at 7.0s.
What to look for: flattering light, a natural pose and tasteful styling, without distortion or artefacts.
- GPT Image 2.5 Flare73%OpenAI29.7s · 40 cr Try
- Seedream 5.0 Pro67%ByteDance31.4s · 49 cr Try
- Krea 2 Medium63%Krea41.7s · 40 cr Try
- Qwen Image 3.0 Pro58%Alibaba10.6s · 36 cr Try
- Ideogram v4.557%Ideogram16.6s · 80 cr Try
- ImagineArt 256%ImagineArt27.5s · 60 cr Try
- GPT Image 2.5 Sunburst55%OpenAI32.6s · 40 cr Try
- GPT Image 250%OpenAI55.2s · 42 cr Try
- ImagineArt 1.5 Pro50%ImagineArt53.4s · 55 cr Try
- Recraft v4 Pro45%Recraft · retired from voting14.4s · 300 cr Try
- Qwen Image 3.043%Alibaba7.0s · 32 cr Try
- Ideogram v436%Ideogram22.9s · 40 cr Try
- Kling v3 Omni36%Kuaishou48.8s · 35 cr Try
- 33%20.7s · 50 cr Try
- Muse Image 1.033%Meta17.3s · 12 cr Try
- Krea 2 Large23%Krea41.5s · 80 cr Try
- Nano Banana 2 Lite20%Google8.8s · 36 cr Try
- Seedream 5.0 Flash20%ByteDance32.4s · 22 cr Try
- 9.3s · 80 cr Try
- FLUX 3 ImageBlack Forest Labs26.3s · 32 cr Try
- Recraft v4Recraft · retired from voting11.0s · 45 cr Try
- Midjourney Niji 7Midjourney · retired from voting134.6s · 160 cr Try
FAQ
- Which AI model renders this prompt best?
- GPT Image 2.5 Flare leads this prompt in the BudgetPixel AI Image Arena, winning 73% 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.