Glamour
How 21 AI image models render: “Cinematic city scene at night, with the glamour of 1970s soul romance. In the foreground, a young Black man in a modest brown wide-lapel suit smiles at his adult beloved, playfully turning out his empty trouser pocket while holding an almost-empty wallet. His adult girlfriend wears a burgundy patterned dress and delicate hairband; she holds his arm and gazes at him lovingly, unconcerned by his lack of money. Beside them, a grand department-store window glows amber, displaying a luxurious fur coat, regal evening gown, diamond rings and strings of pearls. In the glass, their reflections appear elegantly dressed, hinting at the lavish life he dreams of giving her. A polished black limousine waits at the curb beside a uniformed chauffeur. Wet pavement mirrors golden lights; deep blue city buildings balance the amber, cream and burgundy palette. Warm, joyful, sincere mood; realistic faces and hands, detailed fabrics and reflections. No text, borders or collage.”
Same prompt, sent verbatim, at each model's default settings and a fixed seed. Judge: flattering light, natural pose, tasteful styling. 200 community votes so far.
Community prompt by @beastxyz · voting closed 2026-10-19
21 text-to-image models rendered this glamour prompt with the identical text at their default settings and a fixed seed. Seedream 5.0 Pro is the community favourite so far, winning 74% of its 19 head-to-head votes on this prompt. Grok Imagine Image Quality was the fastest at 4.9s.
What to look for: flattering light, a natural pose and tasteful styling, without distortion or artefacts.
- Seedream 5.0 Pro74%ByteDance33.2s · 49 cr Try
- FLUX 3 Image Klein64%Black Forest Labs8.3s · 12 cr Try
- Muse Image 1.061%Meta34.7s · 12 cr Try
- Kling v3 Omni58%Kuaishou86.9s · 35 cr Try
- FLUX 3 Image56%Black Forest Labs29.9s · 65 cr Try
- Nano Banana 2.153%Google17.2s · 31 cr Try
- Qwen Image 3.0 Pro53%Alibaba10.7s · 36 cr Try
- Seedream 5.0 Flash53%ByteDance23.7s · 22 cr Try
- 4.9s · 80 cr Try
- GPT Image 2.5 Flare47%OpenAI136.9s · 40 cr Try
- Krea 2 Medium44%Krea40.1s · 40 cr Try
- Midjourney V8.243%Midjourney111.0s · 80 cr Try
- 42%13.9s · 50 cr Try
- GPT Image 2.5 Sunburst40%OpenAI53.6s · 40 cr Try
- ImagineArt 233%ImagineArt · retired from voting27.9s · 60 cr Try
- Nano Banana 2 Lite27%Google8.4s · 36 cr Try
- Qwen Image 3.025%Alibaba6.9s · 32 cr Try
- Ideogram v424%Ideogram16.0s · 40 cr Try
- Krea 2 Large21%Krea31.7s · 80 cr Try
- Ideogram v4.520%Ideogram18.1s · 80 cr Try
FAQ
- Which AI model renders this prompt best?
- Seedream 5.0 Pro leads this prompt in the BudgetPixel AI Image Arena, winning 74% of its 19 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.